[HN Gopher] An important next step on our AI journey
___________________________________________________________________
An important next step on our AI journey
Author : jmsflknr
Score : 635 points
Date : 2023-02-06 19:01 UTC (3 hours ago)
(HTM) web link (blog.google)
(TXT) w3m dump (blog.google)
| wiremine wrote:
| I agree this is bland corporate speak. But it reminded me of a
| question that's been floating around:
|
| A number of pundits, here on HN and elsewhere, keep referring to
| these large language models are "google killers." This just
| doesn't make sense to me. It feels like Google can easily pivot
| its ad engine to work with the AI-driven chat systems. It can
| augment answers with links to additional sources of information,
| be it organic or paid links.
|
| But I guess I'm wondering: what am I missing? Why would a chatbot
| like ChatGPT disrupt Google vs forcing Google to simply evolve.
| And perhaps make even more money?
| lemursage wrote:
| As an engineer my concern about "google killers" is that I
| can't see an easy way to scale and control/optimize them in
| business settings. Apart from factual misstatements happening
| in the ChatGPT, what about source attribution? How is the
| relevance of a source determined? How is the flow of
| information through the network preserved (sourceA => sourceB
| => sourceC)? With Google we also don't know exactly but I can
| image some version of PageRank as tuneable. Finally, how to add
| new pages to index and measure potential "forgetting" that
| could happen?
|
| Unless somebody could clarify those for me, this is what
| currently petrifies me -- some uncontrolled black box
| presenting its clandestine view of the web with no way to
| follow the breadcrumbs.
| tiborsaas wrote:
| If I'm looking for a specific answer, then with my googling
| skills, I can easily find an article or tutorial written for a
| _target audience_ in mind.
|
| If I on the other hand use generative AI, then the answer (and
| hopefully correct one) would be generated only for me. This is
| the personal touch Google currently misses and I guess it's
| appealing for many people.
|
| Currently LLM-s are not Google killers, they can't find me a
| restaurant, a nice watch or other stuff I'd pay money for. Yet.
| richardw wrote:
| OpenAI has had huge mindshare with students recently. Every
| (ish) kid who writes an essay or needs information summarised
| is hitting ChatGPT. Kids are where change happens, ask
| Facebook. They get on new things instantly - within days we
| were reading reports of kids writing essays with the latest
| tool. Young people are also naturally viral, sharing the cool
| new tool with entire classes. This is a marketer's dream. You
| don't need to change how sluggish corporates work, just focus
| on kids and watch them work.
|
| Google has to fight to get that mindshare back.
|
| Not sure I'd be building my company on the ADHD-fueled Google
| roundabout that generates and destroys systems monthly. You
| just know whatever they release is someone's promotion project,
| until it's in GA.
| Mystery-Machine wrote:
| And that's exactly why the CEO of Google published the blog
| post about Google + AI, because they don't think AI is a
| potential Google killer. /sarcasm Yes, they took the risk
| seriously and that's great. However, Google's lack of good UX
| will probably produce a monstrosity of a tool that no one will
| use. The only usable parts will be what's embedded in the
| Google Search engine.
| cutenewt wrote:
| Unfortunately I don't think it's that easy.
|
| That is, the cat is out of the bag:
|
| ChatGPT not only showed us the power of AI, but it showed us a
| bunch of non-AI things like:
|
| - Ad-free results - Clutter-free results - The elegance of not
| having to click on links
|
| A competitor could capitalize on this, putting Google's ad-
| driven, click-driven, clutter-driven model at serious risk.
| wejick wrote:
| rather than google killers, I would say it is SEO or publishers
| killers. There will be less traffic to websites or blogs,
| certain type of websites will be impacted most than the other.
| in fact google will have more way to recommend and curate
| content in their way.
| mrtksn wrote:
| It still can be a Google killer even if Google comes up with
| something better because Google makes its money from sending
| people to the highest bidder. So far there's no clear path to
| make money from ChatGPT, let alone match the sum Google is
| making from Search.
|
| If this new paradigm dominates the way people use computers and
| it's not as profitable as Search, Google might indeed have to
| scale back.
| greyman wrote:
| ChatGPT can make money by subscriptions, or they can also put
| ads next to the chat?
| mrtksn wrote:
| Can they? Google made $162B from search ads last year, to
| match that with the leaked $40/month subscription you will
| need 340 million subscribers. Can they really get 340
| million subscribers, which is %50 more than Netflix
| subscribers?
| ericmcer wrote:
| ChatGPT will have a very hard time. If I want to get on ChatGPT
| I usually google ChatGPT and click the first link. It is a
| crazy competitive advantage.
| jklinger410 wrote:
| Google was already going this route. ChatGPT is simply pushing
| GOOG and META to go faster.
|
| Simple as.
| kccqzy wrote:
| But without ChatGPT when would Google put a LLM into Search?
| 2025? 2030?
| fosk wrote:
| That's because you are trying to have a nuanced conversation
| about this, but "hot takes" are the most valuable currency on
| social media these days.
| im3w1l wrote:
| If anyone with a couple million dollars can create a great LLM-
| powered search engine then maybe Google's search engine
| division should be valued a couple million dollars.
| BurningFrog wrote:
| Maybe what they mean is Google _Search_ killers?
| ekanes wrote:
| I think it's the first credible challenge to google's results
| in 2 ways.
|
| 1. People are typing questions into it and finding it hugely
| useful in ways that overlap with google. It just answers you,
| and you can ask clarifying questions, argue with it, etc. It's
| proving useful.
|
| 2. More subtly, the excitement around it seems to reveal that
| people are open to alternatives. For decades, alternative
| search engines haven't made inroads. If people are typing
| queries and questions into somewhere new, well that implies
| they're open to something new. So whether it's chatGPT or
| bing.com or ... the zeitgeist is shifting.
| xen2xen1 wrote:
| Hey Google, how big is Maine? G: It's xxx big. Person: Do I
| know anyone there ? G:No one is in your address book. P:
| What's the closest person I know to Maine? G:Bob. G: Is this
| about your asking about Maple Syrup last night? There are
| closer places to get fresh Maple Syrup, how about Michigan?
| Contrived, but not impossible.
| antonvs wrote:
| I think anyone who's used ChatGPT seriously could tell you
| that this isn't the same thing, at all.
|
| You're giving "assistant"-like questions, but the problem
| with those assistants has always been how shallow their
| responses have been, which significantly limits their
| usefulness.
|
| GPT's responses are still shallow in an absolute sense, but
| relatively speaking they're the Mariana Trench compared to
| Google's little creek.
| notahacker wrote:
| Depends what the objective is.
|
| If I want to be amused by a Hacker News comment in the
| style of the Bible, draft a conclusion for my essay or a
| engage in a long and superficially appealing conversation
| about philosophy, I'm not using Google's publicly-
| viewable AI products
|
| Then again, Google - with and without a conversational
| interface - will do just fine with what the capital of
| Maine is, much better with what the weather is like in
| Maine tomorrow, and there's a lot more usefulness and
| revenue in associating it with stuff in my address book
| and selling me flight tickets to Maine which is... some
| way outside ChatGPT's wheelhouse.
| kitsunesoba wrote:
| Its ability to synthesize answers with data from numerous
| sources is also game-changing and not something a traditional
| search engine could ever hope to do.
|
| It's not infrequent that googling for the intricacies of some
| badly-documented library turns up almost nothing useful, or
| the bits that _are_ useful are scattered sparsely among the
| results, some of which are pages deep. It's so much easier to
| ask ChatGPT to explain the struct, function, etc in question
| and have it pull the pertinent info from whatever corners it
| of the internet it found these things in. Even if it's only
| 80% accurate it's a massive time saver.
| generalizations wrote:
| Anyone else remember the beginnings of youtube? Google tried to
| compete with them, with their own Google Videos. It sucked -
| and I remember reading how the engineers running it couldn't
| even figure out why they lost. In the end, Google just had to
| buy their competition, because they couldn't figure out any
| other way to win.
|
| They've tried to compete elsewhere, too, and I don't think
| they've ever been able to make a go of it outside their cash
| cow. The only thing they've really been able to do is 'search
| results + ads'.
|
| I don't think they'll be able to modify that winning combo even
| in the slightest and still be successful. And in this case,
| they can't buy the competition. Micro$oft already did.
| gretch wrote:
| Disclosure: work at google
|
| YouTube was founded in ~2005. Google bought it in 2006. It is
| now 2023.
|
| YouTube has spent 2 years as its own company and 17 as part
| of Google.
|
| Try to remember what YouTube functionality was in 2006. It
| was very different and has grown a lot.
|
| The narrative that Google doesn't know how to innovate
| YouTube doesn't add up.
| saberience wrote:
| Youtube now is 90% of what it was 10 years ago and what
| might it good in 2006 is the same reason it's good now, the
| UI is clean and it's easy to use. That's it. Also,
| following the acquisition, for many years most of the
| people working on it were the original Youtube folk, not
| the "Google people."
|
| Google hasn't shown they can do new product in a very long
| time... see the GCP mess, Stadia, and the hundreds of other
| total failures (Plus, Wave, and many I've forgotten).
| mrkramer wrote:
| YouTube was grabbing lots of attention and with the
| attention comes ad revenue so it made perfect sense for
| Google to buy YouTube and scale it up. YouTube grew into
| something exceptionally valuable for both the Google and
| the people who use it.
| mrkramer wrote:
| Google already has a trackrecord of beating Microsoft. Do you
| remember Windows Phone? Well Google made Android in response
| to Windows Phone + Bing threat not in response to iPhone.
| HarHarVeryFunny wrote:
| Well, Steve Ballmer wasn't exactly an innovator - just kept
| milking the cash cow.
|
| Satya Nadella seems way more tuned into the zeitgeist. His
| heavy bet on OpenAI may seem excessive, but at worst it's
| going to be cheap insurance and at best may be a game
| changer.
|
| I think Google's producing Android was a reaction to BOTH
| iPhone and Windows Phone - they didn't want to be frozen
| out of the mobile advertizing market by competitors that
| owned the platforms.
| killjoywashere wrote:
| I don't think most people realize how much infrastructure
| separates something like ChatGPT from Google-scale deployment.
| OpenAI isn't suddenly building transoceanic fiber and
| datacenters near most major population centers. They aren't
| signing production-ready contract vehicles with most major OEMs
| and governments. And in the gap it would take a new entrant to
| acquire 10% of those assets, Google has 100,000 engineers who
| would iterate on this and 1000 other technologies 1000 times.
| HarHarVeryFunny wrote:
| You don't need to own your own datacenters to do this,
| anymore than someone like Netflix (who run on Amazon cloud)
| does. I'm sure any of the cloud providers would happily take
| the money of any company that had the $$$s to pay for it. The
| barriers to entry really don't seem that great... the tech
| behind ChatCPT is well understood and multiple similar things
| already exist from various companies.
| coredog64 wrote:
| AIUI, Netflix runs a lot of their business in AWS, but
| content streaming isn't something they host in AWS.
| Mystery-Machine wrote:
| Google cannot make a good SMS app for Android. They will
| never be able to launch a simple chat bot. What they will
| launch will be a monstrosity. The only Google AI product that
| people will use is any AI embedded within their existing apps
| and services...which is a great thing, but I wouldn't bet on
| Google being able to launch any new product that would have a
| decent UX.
| [deleted]
| mritchie712 wrote:
| As someone using OpenAI in production, I can attest to the
| lack of stability and consistent performance in the current
| offering. Depending on the time of the day (and who knows
| what else), the same calls to GPT3 can take from 500ms to 15
| seconds.
| doctor_eval wrote:
| Maybe it's changed now, but last time I looked, Google had
| failed to materially diversify its income, so it is
| susceptible to competition. All that expensive infrastructure
| is going to be a weight around Google's neck if their search
| revenues start falling.
|
| Of course, even if search revenue falls, it won't happen
| overnight.
|
| But I honestly don't see how laying all that fibre or owning
| those data centres is a moat around Google. These things are
| hugely capital intensive, to be sure, but theres a big market
| for both.
| tarsinge wrote:
| I'm sure people were saying the same things regarding IBM in
| the 80's, Microsoft or Cisco in the 90's... Google is a big
| corporation with inertia and averse to risk regarding its
| core business, they are not immune to being disrupted.
| Eduard wrote:
| > I don't think most people realize how much infrastructure
| separates something like ChatGPT from Google-scale
| deployment. OpenAI isn't suddenly building transoceanic fiber
| and datacenters near most major population centers.
|
| This feels like "thinking inside the box" to me. None of
| these things are necessary requirements for being a "Google
| killer".
| [deleted]
| kanwisher wrote:
| OpenAI already has the infrastructure Azure and Bing.
| Microsoft has a bigger public cloud then google
| kennethh wrote:
| The public cloud is probably a small part of the Google
| Infrastructure.
| dougmwne wrote:
| You are missing the Microsoft partnership. MS has a 48% stake
| in OpenAI and provides all the infrastructure through Azure,
| including purpose built machines for model training.
| Microsoft has also launched GitHub Copilot, summarization
| features in Teams, and is widely reported to be adding GPT
| features to Bing.
| scarmig wrote:
| Google has far more resources for training models and
| inference. Likely more than all their nearest competitors
| combined.
| yunwal wrote:
| If you're talking about physical hardware, Google pales
| in comparison to Amazon, and Gcloud is still smaller than
| Azure. It's possible google's private compute makes up
| for the Azure difference but it's not like they're in
| different leagues in terms of access to hardware.
| alsodumb wrote:
| Unlike Azure and Amazon, Google doesn't have to rely on
| Nvidia GPUs for training and inference, they achieved
| significant performance gains by using their custom TPUs.
| coder543 wrote:
| Your comment is simply incorrect. Amazon has had their
| own TPU equivalents for training and inference for years:
|
| https://aws.amazon.com/machine-learning/trainium/
|
| https://aws.amazon.com/machine-learning/inferentia/
|
| I really don't think this would be a limiting factor
| regardless, even if Amazon didn't already have multiple
| generations of these products. It's not as if an Amazon
| or Microsoft sized company is incapable of developing
| custom silicon to meet an objective, once an objective is
| identified, and TPUs aren't really that complicated to
| design, especially compared to GPUs.
| redox99 wrote:
| Source?
| dougmwne wrote:
| There's definitely no legitimate source for that info.
| Details of the exact machines that sit in the Azure and
| Google clouds are proprietary.
| paganel wrote:
| MS cannot deliver successful stuff on the web at scale.
|
| They can deliver unsuccessful stuff on the web at scale,
| they can deliver successful stuff that turns out to be
| inconsequential for their bottom line on the web in the
| long-term (AJAX came from MS), but it's just not in their
| DNA to take over the web. They had lots of chances to do it
| during the last 20 years or so, they had all the silver
| bullets at their disposal, they just couldn't deliver what
| it took.
| ctvo wrote:
| > MS cannot deliver successful stuff on the web at scale.
|
| It's this type of confidence that you come back to HN
| over and over for.
|
| Let's ignore Azure, Office 365, and Microsoft's other
| online properties. In just video games: Microsoft owns
| and operates the Xbox network with over 100 million
| active monthly users[1]. That runs on the internet with
| all the features of a social network and more. I think
| they can deliver successful stuff at web scale OK,
| whatever their other shortcomings.
|
| 1 - https://hothardware.com/news/xbox-live-
| surpasses-100-million...
| moufestaphio wrote:
| Uh sorry what? Azure is the second largest cloud
| provider, well ahead of google.. That's like the
| definition of 'web scale'
|
| Not sure what decade you're stuck in here with comments
| about ajax
| sidibe wrote:
| Not agreeing with GP but the capacity of their public
| clouds is very different from total capacity. Amazon and
| Microsoft have bigger public clouds, but Google's own
| workload is probably bigger than anyone else's or even
| the public clouds by a large factor.
| peyton wrote:
| Based on the busy mock-up in TFA I don't think it'll take
| 100,000 engineers to beat them.
| AJ007 wrote:
| As far as I've read, DuckDuckGo doesn't have 100,000
| engineers.
| doctor_eval wrote:
| No but they don't have a search engine either. They
| mostly use bing.
| relaxing wrote:
| They're leveraging Microsoft's engineering.
| Willish42 wrote:
| What is TFA in this context? Does anyone have a link to to
| said "busy mock-up"?
| fredoliveira wrote:
| TFA would be "the f*cking article", in this case.
| kerpotgh wrote:
| I use google in confluence with chatGPT. When I'm researching
| something, chatGPT gets me started and points me in the right
| direction but then I use google to find first hand sources/more
| detail/images/videos etc.
| ZiiS wrote:
| The question becomes dose the best model win; or dose Google's
| existing processes, infrastructure, and advertising
| relationships allow it to purchase or reimplement the best
| model?
|
| Probably still an open question but a better chance then anyone
| has had to disrupt them for two decades.
| badestrand wrote:
| > what am I missing? Why would a chatbot like ChatGPT disrupt
| Google vs forcing Google to simply evolve.
|
| Because it's not clear yet whether anyone else can currently
| develop a chatbot interface as capable as ChatGPT.
|
| For many ChatGPT is already replacing a lot of Google searches
| so G needs to hurry.
| eclipxe wrote:
| For many? Citation needed. Yes there is a lot of hype, but is
| it really replacing a lot of Google searches, if so is that
| your anecdote or is there data here?
| pleadthefifth wrote:
| Branding is one thing. "Google" has been a commonplace verb for
| a long time, which alone is worth billions to them. ChatGPT is
| the first time something has come close to stealing that
| spotlight, since for the time being, it's answer a lot of
| queries far better than Google would. So even if Google makes
| something technically better later, it might be too late to
| replace ChatGPT as the AI king.
| arnvald wrote:
| I think Google is in a tough position, because for them ads
| (both in search and other websites) are a huge portion of their
| business, and they need to find a way to monetize LLMs without
| killing its own cash cow.
|
| Microsoft has a lot of advantages here - they can introduce LLM
| to search at a much smaller scale (order of magnitude), which
| means its cheaper, and they have plenty of other products
| making tons of money, so they can take their time to figure it
| out (also they're already adding ChatGPT to tolls like Teams
| and possibly Office, so they'll be able to increase revenue
| from these products).
|
| Google is also seen as a bit of a dinosaur - they struggle to
| introduce new products, and recently we've been hearing more
| about products they kill rather than huge successes. It seems
| that as a company they lost their innovative spirit, and that's
| why people don't believe they'll evolve quickly enough.
| xen2xen1 wrote:
| Because sitting at a computer or a phone is, in fact,
| unnatural. We are trained to do that. Asking a question of
| another person is natural. If you can get Alexa or Google
| assistant to reliably, without lying, answer questions, that
| could be huge. Caveats, but so much $ is put into those things
| and they suck. Also, if you could get a Google AI to be like a
| real assistant, context and understanding of what you're doing,
| that could also be huge. Just getting the assitants of the
| world to really intract would slice a large piece off the
| Google search pie, and potentially set up whoever does that
| well to be the next major interface to tech.
| leobg wrote:
| Not sure if this is accurate. Voice interaction is very slow,
| and low bandwidth. Visual interaction is much faster. Hence
| people love their spreadsheets.
|
| Even if a voice assistant allowed you to interrupt it, to
| make fast course corrections, it would still be much slower
| than, say, interacting with the filters on Google Flights.
|
| And I am saying this after having built for myself a bi
| directional voice interface to ChatGPT. There are certainly
| situations where it is great to use it, such as while
| driving, or perhaps in the kitchen while having your hands
| full. And probably on mobile, where screen real estate is
| scarce. But those doing information, work, or even just
| online shopping, probably won't be giving up their screens
| anytime soon.
| HarHarVeryFunny wrote:
| I guess a couple of reasons:
|
| 1) Because it _is_ disruptive. Things may get shook up, and
| Google may not end up in as exclusive position as they are
| currently in. There 's risk.
|
| 2) Because it's not obvious how advertising would fit in with a
| conversational interface. Google may stay as #1 search/answer
| engine, but would revenue be adversely affected?
| sharkbot wrote:
| I think it could fit in with a conversational chat bot the
| same way that ads are part of podcasts and YouTube channels:
| a conversational and explicit ad that helps pay for the
| otherwise freely available content.
|
| Full disclosure: I work at Google, but nowhere near the
| chatbot stuff. This is my humble opinion and nothing more.
| relaxing wrote:
| Banner, sidebar, in-line, interstitial, modal... what
| advertising modes _wouldn't_ work on conversational
| interface?
| criddell wrote:
| Conversational interfaces seem ideally suited to voice
| assistants. When you ask "hey google, what's the default
| password for my router?" does it make you sit through a 30
| second ad before saying "the default password is _password_
| ".
| gowld wrote:
| Amazon Alexa does yell ads like that. It's horrific.
| alex7734 wrote:
| That sounds like a complete nightmare. At least in a web
| page I can at least look away from the ad.
| tboughen wrote:
| It may be worse than that if this Sony patent is any
| guide... https://www.techradar.com/news/sony-patent-
| would-have-you-ye...
| cal85 wrote:
| Yes, plus it could introduce of new forms of advertising in
| the conversation itself. Algorithmic product placement. It
| could get weird.
| HarHarVeryFunny wrote:
| If ChatGPT tells me it's enjoying a refreshing Coke, I'm
| not buying it ! :)
| HarHarVeryFunny wrote:
| Well, those are ways you could try to do it, but whether
| they would "work" (attract click-thrus, not alienate users)
| is another question.
| HDThoreaun wrote:
| None of those would work with a chatGPT like search
| platform. Search ads work because they're largely
| indistinguishable from the organic content. You search
| google and get a million links, the first few are ads. The
| entire model of chatbots is completely different. So the
| only truly effective way to advertise on a chatbot is to
| make the response itself into the ad. But would people use
| such a service, or would they move to another one that just
| uses banner ads which monetize at much lower rates? If
| chatbots completely replace the current search ecosystem
| Google will be forced to either lose huge market share or
| make much less money per search.
| alain94040 wrote:
| Those new language models are "Google killers" because they
| reset all the assumptions that people have made about search
| for several decades. Imagine that people start using those chat
| bots massively as a replacement for Google search. Then the
| notion of keyword disappears. Google AdSense becomes mostly
| irrelevant.
|
| Of course, Google is a giant today with a history of machine
| learning innovation. So they have a good chance of being
| successful in that new world. But the point is that many other
| companies get a chance again, which hadn't happened in 20
| years. You couldn't displace Google in the old
| search/keyword/click business model. Now everyone gets a fresh
| start.
|
| Who knows what the economics will be. Just like page rank early
| on, it was expensive to compute. But the money in advertising
| made it worth it, and Google scaled rapidly. Which language
| model do you run? The expensive one, or the light one (notice
| how Google in this announcement mentions they will only offer
| the significantly smaller model to the public). Can you make
| this profitable?
|
| Other fun questions to answer if the industry moves to chat vs.
| search, in a 5-10 year horizon. What is the motivation to write
| a blog post by then? Imagine no one actually reads web sites.
| Instead a blog post to share an opinion, I'll probably want to
| make sure my opinion gets picked up by the language model. How
| do I do that? Computed knowledge may render many websites and
| blogs obsolete.
| kolinko wrote:
| The motivation for writing a blog post may be the same as
| when blogoslhere originally started - for your community to
| read it.
| s3p wrote:
| I think this is the same type of thinking that people had
| when they think technology will "steal" jobs, when in reality
| we have lower and lower unemployment as time goes on.
|
| Most likely this will not actually happen, and even if it did
| your content would still be valuable as an AI is analyzing it
| in a more nuanced way than just looking for keywords. Which,
| by the way, is exactly what search engines do.
| deltree7 wrote:
| Delusional to think Ads work only on Keywords.
|
| Where there is human attention, there will always be ads. The
| more context, the better ads.
| inimino wrote:
| "Attention is all you need"?
|
| Joking aside, there's no reason AdWords can't become
| AdWordVectors and be even more effectively targeted.
| galleywest200 wrote:
| The ads need to be served in context to a conversation and
| cannot just pollute a search page like they do now. Ads now
| are easy, dumb things.
| coredog64 wrote:
| There's a smaller surface are for ads in a targeted chat
| session. At present, Google can show me ads on the results
| page. Each subsequent result that I view is an additional
| slice of my attention.
|
| It's possible that Google can deliver a few targeted ads,
| but what if they can't? What about the rest of the market
| that's now gone? Possible that all those missed
| opportunities remove the ability to discover price.
| runnerup wrote:
| The ads could be slipped right into the chat itself.
| ancientworldnow wrote:
| Which is almost assuredly FAR more effective.
| dubcanada wrote:
| You completely ignore the fact that companies will show
| ads everywhere, there is no reason that they would not
| try to inject ads into chat.
|
| "Here is the answer to your question about oranges. But
| did you know Tropicana is made from 100% real orange
| juice?"
|
| "A project manager is a ... Often the software project
| managers use is Zoho Projects for the best agile sprint
| planning"
|
| If they can put ads in it, there will be ads in it.
| jdgoesmarching wrote:
| Sure, but that doesn't change the fact that Google has
| coasted on an ad model that has depended on Google being
| the information gatekeeper of the web for nearly two
| decades. Over those years, Google has demonstrated a
| remarkable inability to build successful products even
| when they have market advantages and nearly unlimited
| resources to throw at them.
|
| This is the first time that the primary cash cow has been
| seriously threatened, and it's not unreasonable to bet
| against Google winning the scramble to figure out a chat
| AI ad strategy (or any product strategy) that would keep
| them in their current near-monopoly position.
| mochomocha wrote:
| "Native advertising 2.0"
| nektro wrote:
| was this comment satire?
| Denzel wrote:
| All these conversations have one glaring omission. As it
| stands right now, ChatGPT is a _net negative_ on the
| ecosystem it exists in. What does that mean?
|
| ChatGPT extracts value from the ecosystem by hoovering up
| primary sources to provide answers, but what value does
| ChatGPT give back to these primary sources? What incentivizes
| content creators to continue producing for ChatGPT?
|
| Right now, nothing.
|
| ChatGPT (or its descendants) _must_ solve this problem to be
| economically viable.
| adammarples wrote:
| They don't need to solve that problem. Lots of things
| cannabilise on others without needing to pay them back to
| be viable. Wikipedia is really just a collection of
| sources, summarized. It owes nothing to the authors of the
| source material and does not seek to redress the balance.
| Google is a sophisticated filter for sources, it doesn't
| need to pay anything back to them to provide value for the
| searcher. Same with chatgpt, it filters and transforms its
| source material but owes nothing in return. News will still
| be published, data will still be generated at scale.
| aembleton wrote:
| > but what value does ChatGPT give back to these primary
| sources?
|
| The dissemination of their thoughts and ideas.
| guelo wrote:
| Google could ask the llm what products or services would help
| with the question and show ads for that. Just tried it and it
| worked pretty well.
|
| > Me: 8 year old girl birthday party ideas
|
| > Chatgpt: <a list including craft party, scavenger hunt,
| dance party>
|
| > Me: what products or services could I buy for it
|
| > Chatgpt: craft party: craft supplies such as beads, glue,
| paint, and fabric - scavengerhunt: prizes for the scavenger
| hunt and decorations - dance party: Hire a DJ or a dance
| instructor, and purchase party lights and decorations
|
| Though in reality Google already has highly tuned models for
| extracting ads out of any prompt
| freediver wrote:
| The question becomes will you trust information that is
| paid for by advertisers or you will trust information that
| is paid by you, the user?
|
| With ads in link based search engine, you can skip or block
| them, but if it is a part of a one sentence answer, there
| is not much you can do about it, so consuming it will be
| much more frustrating.
|
| Of course, there will still be a lot of people who will
| choose the free information paid by the advertisers, but
| there will also be a growing number of users who will
| prefer not to have advertisers pay for the information they
| put into their heads (it is already clear that such
| information will be of higher quality).
|
| My prediction is that in 10 years, all free information
| paid by advertisers will have 'for entertainment purposes
| only' label, because by then we will understand as a
| society that that is its peak value.
| mrkramer wrote:
| >Those new language models are "Google killers" because they
| reset all the assumptions that people have made about search
| for several decades. Imagine that people start using those
| chat bots massively as a replacement for Google search. Then
| the notion of keyword disappears. Google AdSense becomes
| mostly irrelevant.
|
| Look up the term "native advertising", that should help you
| in understanding how online ad ecosystem works.
| bbor wrote:
| How so? How does native advertising solve the problem of
| diminishing volumes of keyword searches? How does it even
| relate to search ads?
| ragingroosevelt wrote:
| if you inject native advertising into the responses?
| nothing is technically limiting the chat responses from
| being exclusively the output of the LLM. mix LLM model
| output with native advertising copy and it's nearly
| undetectable if you're not looking out for it. and good
| luck catching those integrated ads in your adblock.
| eklitzke wrote:
| The point about the economics of running these models is an
| important one that slides under the radar a lot of times. The
| training costs for large language models like GPT are
| enormous, and the inference costs are substantial too. Right
| now things like ChatGPT are very cool parlor tricks, but
| there's absolutely no way to justify them in terms of the
| economics of running the service today.
|
| Obviously this is all going to change in the near to mid
| future: innovation will drive down costs of both training and
| inference, and the models will be monetized in ways that
| bring in more revenue. But I don't think the long term
| economics are obvious to anyone, including Google or OpenAI.
| It's really hard to predict how much more efficient we'll get
| at training/serving these models as most of the gains there
| are going to come from improved model architectures, and it's
| very difficult to predict how much room for improvement there
| is there. Google (and Microsoft, Yandex, Baidu, etc.) know
| how to index the web and serve search queries to users at an
| extremely low cost per query that can be compensated by ads
| that make fractions of a cent per impression. It's not
| obvious at all if that's possible with LLMs, or if it
| possible, what the timescale is to get to a place where the
| economics make sense and the service actually makes money.
| dan-robertson wrote:
| 1. How much did it cost to train ChatGPT/GPT3? The only
| estimate I've seen was not enormous in the grand scheme of
| things (eg more money than I have but less than Google have
| stuck down the back of the sofa). I think that number
| didn't count training precursor models or paying for people
| to come up with the models/training data/infra.
|
| 2. Don't Google have specialised hardware for training
| neural networks? If the costs of training/inference are
| very significant won't Google (with their ASIC and hardware
| design team) have a significant advantage? It seems to me
| that their AI hardware was developed because they saw this
| problem coming a long way off.
| kerpotgh wrote:
| Why would keywords disappear? Wouldn't you just use keywords
| that appear in the user input and response to serve ads?
| [deleted]
| coliveira wrote:
| The reason is that high amount of usage is itself disruptive.
| The same way Google has an advantage of receiving 90%+ of
| search requests, ChatGPT has the advantage of being tested with
| millions of requests per day. If Google cannot test a similar
| AI technology with the public, it will hardly get results that
| are comparable with ChatGPT.
| stcroixx wrote:
| They burned a bridge already and it's too late now. People will
| be less likely to use whatever AI they release as we'll just
| assume it's trying to financially exploit us like they did with
| search and gmail. Mass adoption will never happen because of
| their spoiled reputation.
|
| Google will not be at the center of the AI future. Watch them get
| even more user hostile as they realize this and cling to their ad
| business even harder.
| whitepaint wrote:
| As long as it is at least as good as ChatGPT, I will definitely
| use it.
| s3p wrote:
| Which planet are you on? Google commands the market in search.
| Its browser is the most popular one in the world. Its operating
| system, Android, has the most users in the world. I agree they
| are not a trustworthy company, but if everyone else is as
| distrustful as you say then these statistics simply do not add
| up.
|
| Google is at the center of nearly every industry they operate
| in, and, in my opinion, AI will be no different. They weren't
| first to market, but they won't be an insignificant player.
| nemo44x wrote:
| "Bard" is a great name because we can all call it "Tard" when it
| gives back awful and wrong answers.
| Ninjinka wrote:
| But can it code though?
| aftergibson wrote:
| Smacks of dropping the ball and not being first mover and trying
| to damage control. All big orgs eventually become the slow mover,
| it's re-assuring that Google is in the same boat and nothing
| really changes.
| yegle wrote:
| But Google's chat bot was smart enough to make people think
| (fool people to think?) that the AI is sentient back in Jun
| 2022, months before ChatGPT. Saying that Google is a slow mover
| is not exactly true.
|
| Disclaimer: Google engineer but has nothing to do with the AI
| products.
|
| https://www.washingtonpost.com/technology/2022/06/11/google-...
| spacephysics wrote:
| It's a testament of how worried Google is about ChatGPT if
| they've sprung up a soon to be public version of the service
| themselves. I'm sure timelines were quickly shortened post
| OpenAI's ChatGPT version update/launch
|
| This is exciting stuff. We're starting to see the wheels of AI
| competition spin fast as they race for first mass adoption. This
| is the fun phase, that's beneficial (typically) for all. Quick
| iterations, competing for more bang for your buck for end
| consumers soon
| blobbers wrote:
| Where bard. Can Bard summarize this article? TL;DR.
| CamelCaseName wrote:
| LLMs provide a brilliant opportunity for search engines to
| justify a paid tier for search.
|
| Would you pay $20/mo for a better Google Search? ChatGPT already
| is.
|
| Ad revenue is dead, long live subscription revenue.
| qwertox wrote:
| There's a Product from Google which I like very much: "Discover"
| in Google Chrome on Android devices.
|
| It is similar to what the normal "Google" app offers: snippets
| with links to articles which may either be currently relevant for
| me (currently as in: this day you searched a lot for X, so we
| recommend you Y), or which may be a bit older but still of
| interest to me. A personalized Google News but much less news
| oriented.
|
| I don't use this in the "Google" app, because there the link-
| sharing is broken: it only shares the link, while in Google
| Chrome the share button shares the link but also provides the
| title of the article.
|
| The point is that I want have this "Discover" feature on Google
| Chrome on the desktop, not only on the phone or on the tablet. I
| don't use my phone for browsing and my tablet only when in bed.
| I'm a desktop-first person. There I have 3 monitors, a surface
| where I can place my cup tea and my pencil.
|
| Google is telling me: We don't want your behavior. We want you to
| use a phone or a tablet, we will reward you for this behavior by
| granting you access to the our analysis of the information which
| we aggregated about you. Else we'll punish you by not giving you
| this tool.
|
| I wonder where they will be offering Bard, and at this point, I'm
| close to considering using Bing, which was always out of question
| for me.
|
| The current message from their CEO: who cares? Publish it, let us
| see for ourselves what it can do.
| Agraillo wrote:
| At least for this audience there's much less sophisticated
| algorithm for discovering - F5 on Hacker News
| nullc wrote:
| https://ourincrediblejourney.tumblr.com/
| rchaud wrote:
| Anybody remember how we used to learn new words and build our
| vocabulary? Perhaps it went something like:
|
| "What does this word mean"?
|
| "Look it up in the dictionary"
|
| "Why can't you just tell me??"
|
| I remember the hassle of looking things up in a paper dictionary.
| Over the long term, it massively helped improve my ability to not
| just recall a simple definition, but also learn new words, as
| they were adjacent to what I was looking for.
|
| It's effectively this hassle ChatGPT and Bard are 'solving'.
| Instead of a group of links that you'd personally evaluate and
| mentally rank in terms of usefulness (thereby building your own
| bullshit detector over time), you will now have a chatbot
| AIsplaining things to you like you were a 12-year old, regardless
| of the topic's complexity.
|
| I'll admit I was concerned about about Grammarly.com ruining
| people's ability to learn to write. That pales in comparison to
| an opaque search engine promising to give you the keys to all of
| human knowledge.
| veec_cas_tant wrote:
| > Instead of a group of links that you'd personally evaluate
| and mentally rank in terms of usefulness (thereby building your
| own bullshit detector over time)...
|
| This sounds an awful lot like email's "Spam" folder, an AI
| driven bullshit detector that I am particularly fond of.
| jw1224 wrote:
| > as they were adjacent to what I was looking for
|
| ...in a dictionary?
| hn_throwaway_99 wrote:
| Question for AI experts out there:
|
| ChatGPT is awesome, but it is obviously hamstrung by the fact
| that it crawled the web at the end of 2021, so all of its data is
| essentially "frozen" and it doesn't "know" of any topics that
| occurred after 2021.
|
| Seems to me like the next "holy grail" in large language models
| is building a model that can be continually updated. If Google
| can achieve that, I think they could leapfrog OpenAI. The example
| in the post about getting new information about the Webb space
| telescope seems to imply Google has this advantage.
|
| So my question is, how hard of a problem is that with LLMs? I get
| the sense that LLMs are trained on a very large data set all at
| once, but that it is difficult to incrementally update them with
| new data. Is that a true assessment? Even incrementally updating
| an inverse text index can be a scalability challenge, and so it
| seems like, given the way that LLMs are trained, that it would be
| even harder to do with LLMs without spending an absolute fortune
| on training.
| gmuslera wrote:
| Not AI expert, not even amateur, but what you said seem to have
| the pattern of a feedback or strange loop. What if your input
| is in good part your own (or similar enough AIs) output? A lot
| of the buzz in internet this year was around ChatGPT and what
| it generated, after all. And you can't just take out what you
| generated of your inputs because the rest of internet is
| talking about or around that anyway.
| Keyframe wrote:
| That's where google's angle is. Not only did they spearhead all
| of these, and sat on it for years now, they also have an up-to-
| date copy of internet.zip vs OpenAI's and others limited common
| crawl and other data sets.
| causalmodels wrote:
| Deepmind has been doing some interesting work around Retrieval
| Enhanced Transformers (RETRO) models [1] that might be relevant
| in this context.
|
| [1] https://www.deepmind.com/blog/improving-language-models-
| by-r...
| joegahona wrote:
| > We call our method RETRO, for "Retrieval Enhanced
| TRansfOrmers".
|
| Wow. Talk about going through contortions to get an acronym.
| devindotcom wrote:
| GRIFFIN takes the cake for me: "General compliant aerial
| Robotic manipulation system Integrating Fixed and Flapping
| wings to INcrease range and safety"
|
| https://techcrunch.com/2022/12/20/this-autonomous-
| ornithopte...
|
| Cool project though.
| chessgecko wrote:
| It seems like google is using search or some knowledge base to
| throw relevant information into the context when it's
| generating to get up to date results. It relies on knowing what
| to retrieve, but google is already pretty good at that.
| twblalock wrote:
| The biggest challenge is going to be filtering out the data
| that was created by ChatGPT itself or the competing LLMs, which
| are going to flood the market (and create a flood of web
| content) in the next few years.
|
| If they don't do that, they will create an AI that is
| essentially inbred.
| paulcole wrote:
| > they will create an AI that is essentially inbred
|
| As the British monarchy has shown us, at the very least this
| can buy you a couple of centuries without any serious
| consequences.
| ben_w wrote:
| A few centuries in human years means something like 7 years
| in the development of AI.
| freediver wrote:
| You do not need to constantly update the model. You just need
| to feed it with fresh data as inpput.
|
| Example to try that in action:
|
| https://labs.kagi.com/ai/context
| ericmcer wrote:
| I am not sure but this did trigger a vision of a dystopian sci-
| fi world where governments attempt spike each others AI with
| false training data to control narratives.
|
| Google can leapfrog OpenAI because they are the entry point for
| 99% of users attempts to answer questions online. Similar to
| how websites for x (weather, lyrics, etc.) existed for years
| but the second google baked them into search those sites dried
| up.
| mrkramer wrote:
| > Similar to how websites for x (weather, lyrics, etc.)
| existed for years but the second google baked them into
| search those sites dried up.
|
| But weather, lyrics, etc. websites are specialized at what
| they are doing and Google is just trying to do basics of
| aforementioned services in hope they will appeal to casual
| Web users.
| jiggawatts wrote:
| > So my question is, how hard of a problem is that with LLMs? I
| get the sense that LLMs are trained on a very large data set
| all at once, but that it is difficult to incrementally update
| them with new data.
|
| It's the opposite. Getting an LLM to learn the _basics_ of
| grammar and paragraph-level language structure is the "hard"
| part. Once you have that, further fine-tuning, specialisation,
| or other incremental changes are comparatively easy.
|
| Catching up to current events could be done in almost real
| time, it's "just" continuous training.
|
| The only challenge is trying to do that _and also_ have an LLM
| that 's filtered to exclude profanity, racism, etc...
|
| That filter is usually added on as a final supervised training
| step, and requires many man-hours to train the AI to be well
| behaved.
|
| I suspect that it would be possible to automate the filtering
| by making another AI that can evaluate responses and score them
| bases on profanity level.
| RangerScience wrote:
| Hmm. Do you also need a way to "forget" things?
|
| Like - hmm. I could see taking a snapshot after the
| grammar/language stuff is in, and then every N weeks
| retraining on the current web, adding in something about
| recentness, but that doesn't seem like "continuous" training.
|
| I'd imagine "continuous" training would be, well, going on
| continuously, all the time, but that would mean that, to
| include "recentness", something would have to change with the
| weights that were from that "old" stuff, which sounds an
| awful lot like the human process of "forgetting".
| EGreg wrote:
| Well, according to Europe's Right to Forget, these AIs have
| to forget some stuff about you if you ask them to :)
| shawntan wrote:
| Grammar is surprisingly easy to learn from unstructured data,
| to an extent. (source: I spent a lot of my PhD doing this
| kinda thing.)
|
| Continual learning seems to be a tough problem though, from
| what I'm seeing of my friends working on this problem. Like I
| said in another comment, just doing gradient updates form new
| data is fraught with problems. RL has a bunch of techniques
| to mitigate issues that arise with that, but I think it's
| still an active area of research.
| BoorishBears wrote:
| > I suspect that it would be possible to automate the
| filtering by making another AI that can evaluate responses
| and score them bases on profanity level.
|
| That sounds like InstructGPT
| pffft8888 wrote:
| It's not about "Well behaved." All we're teaching it is our
| biases.
| airtonix wrote:
| [dead]
| wyager wrote:
| Right now, "well behaved" means "crudely beaten into
| submission". I can only imagine what kind of horrible stuff
| future AI products will do if we keep twisting them into
| giving "friendly" output
| https://twitter.com/cirnosad/status/1622407343358214146
| taneq wrote:
| They're the same thing. Good behaviour just means following
| accepted social rules.
| RangerScience wrote:
| Ehh. From what I've seen in a lot of places - MIRI, AI +
| prisoner's dilemma experiments, moral philosophy, life -
| there do seem to be the categories of "clear good behavior"
| and "clear bad behavior" even if there are also really big
| categories of "unclear good/bad behavior".
|
| In other words, while sure, some "well behaved" is "passing
| on our biases", there does (IMO) seem to be a big chunk
| that's "universally well behaved".
| adastra22 wrote:
| Nothing in morality is universal.
| ben_w wrote:
| Sure, but the iterated prisoners dilemma has a nice
| result that looks like morality if you don't look too
| closely or ask questions about if "altruism" might just
| be a self-delusion.
| XorNot wrote:
| The internet does not accurately reflect our biases. It is
| much cheaper online to post bad content, or hateful
| content, then "good" content. In real life, almost the
| opposite is true.
| inimino wrote:
| We're not even teaching it anything, all we're really doing
| is setting up a behaviorist training regime that lets it
| reproduce some of the biases of some of us, just well
| enough to squeeze through the Overton window that's
| acceptable to big corporates.
| ben_w wrote:
| I think that counts as teaching.
| joe_the_user wrote:
| Broadly, yes. Current AIs (LLMs etc) haves succeeded as brute-
| force prediction at it's lowest level. Of course there are many
| refinements here but this basic situation has meant that
| adaptive learning, updating, doesn't really work for this
| particular approach (as others mention).
|
| The thing about this is if competition forces Google and
| Microsoft to offer a full ChatGPT style interface, they are
| going to be using a vast amount of cpu cycles and thus energy.
| This is going to be costly and potentially environmentally
| destructive. And only companies with vast server farms will be
| in this game.
| tiborsaas wrote:
| > they are going to be using a vast amount of cpu cycles and
| thus energy. This is going to be costly and potentially
| environmentally destructive
|
| How much CPU do you think Google currently utilize? OpenAI is
| a relatively small company compared to Google and they can
| keep their services (barely) afloat. AI at scale is indeed
| server intensive, but probably nothing like what we already
| have.
|
| Also, new chips designs might significantly decrease power
| requirements in the future, so I wouldn't worry about the
| environmental issues.
| joe_the_user wrote:
| _How much CPU do you think Google currently utilize?_
|
| Lots and if they serve a ChatGPT interface, it will be N
| times as much as now since each will be to an LLM and
| involve a back-and-forth. What is N? 3, 10, 100?
|
| _OpenAI is a relatively small company compared to Google
| and they can keep their services (barely) afloat._
|
| OpenAI has negligible income. They're effectively financed
| by Microsoft. I don't how much serving ChatGPT to the world
| costs but it's fairly expensive per transaction. It can't
| not be, since it's calling a model with billions of
| parameters.
| nevir wrote:
| Google already as its Knowledge Graph - which is a pretty huge
| set of (semi) structured data about a bunch of things out
| there:
|
| (totally speculative) If Bard were to form queries against
| knowledge graph, and then summarize the results, it could be
| very up to date for a good amount of information
| krisroadruck wrote:
| I dunno - Google assistant relies heavily on the KG and it's
| pretty garbage - but then that could be more to do with
| Google Assistant than the quality of the KG.
| BobbyJo wrote:
| Knowledge graph is more of an expert system in terms of how
| it i updated and it's data sources. There isn't much magic
| there, so I doubt bard could get much from it if it's capable
| of being trained on unstructured web content.
|
| The more likely dependency would be bard ingesting
| unstructured data and generating structured data to update
| knowledge graph with.
| captaincaveman wrote:
| They should be able to use it to check for contradictions
| against what the Bard has generated and facts in the KG.
|
| For example I asked chatGPT about birds that can't fly and it
| started bullshitting about all sorts of birds that clearly
| can, those facts would likely be in the KG.
| jacooper wrote:
| There is already LLM search engines out there
|
| https://perplexity.ai
| iandanforth wrote:
| https://weaviate.io/ also allows for generative search.
| AlanYx wrote:
| I like the way that site presents results to complicated
| questions, footnoted to supporting pages. I can absolutely
| see that being the future of search engine output.
| smadge wrote:
| Google is an LLM search engine.
| silisili wrote:
| Oh I quite like this.
|
| I asked it, conversationally as I would to a human, "when is
| the super bowl", "what channel is it on", and "who is
| playing" in that order, and it answered all three perfectly.
|
| For fun, I asked it a more complex question - "will ford
| stock go up or down", and it answered with -
|
| Analysts have a median target of $13.00 for Ford stock in the
| next 12 months[1], with a high estimate of $21.00 and a low
| estimate of $10.00[1]. Over the past 50 years, Ford Motor has
| on average risen by 15.7% over the course of one year[2].
| Therefore, it is likely that Ford stock will go up in the
| next year[3][4].
|
| I'm going to use the heck out of this thing.
| mark_l_watson wrote:
| Thanks for mentioning perplexity.ai - I had not seen it
| before. I asked it a rather detailed question about myself
| and it provided good responses with references. It handled a
| follow up question very well also. Well done!
| HarHarVeryFunny wrote:
| You don't need to retrain the model to access fresh data. You
| can just tune the model to generate queries to various sources
| (search engine, etc) to retrieve data.
| awb wrote:
| > You can just tune the model to generate queries to various
| sources (search engine, etc) to retrieve data.
|
| That sounds like a task runner instead of a LLM
| ibejoeb wrote:
| Right. The model is already trained to interpret the
| results. Think of it like automatic prompt creation based
| on the results of a search.
| HarHarVeryFunny wrote:
| Perhaps. I'm not sure that "LLM" is the best description of
| ChatGPT (see my recent comments), but certainly it's
| strength is language and weakness is sticking to factual
| answers (as expected in a search engine context, if not so
| much in an info-tainment chatbot).
|
| Using ChatGPT as a front end for search, maybe also as a
| summarizing/presentation interface, and able to maintain
| context for a conversational interface would all seem to be
| playing to it's strengths.
|
| There was apparently a brief appearance of a ChatGPT
| enhanced Bing (search engine) yesterday which was noted to
| be able to cite sources, which certainly suggest it being
| used more as a front end than as itself the source of
| content.
| smoldesu wrote:
| Disclaimer: I am not an AI expert.
|
| I think it depends on how reliable you want this AI to be.
| Opening search indexing to realtime data is what led to the
| endless mess we call SEO, and I fear that doing the same for AI
| invites the same problems.
| fijiaarone wrote:
| Bingo - the reason ChatGPT looks so impressive now is the
| same reason Google was in 2000 - it was a breath of fresh air
| with a simple interface that was unencumbered by the sales
| and marketing and advertising barrage that targeted users of
| its entrenched competition.
| shawntan wrote:
| Like the earlier responses said, if it is retrieving
| information from an external data source, that would be a much
| easier way to update things. REALM
| (https://arxiv.org/abs/2002.08909) comes to mind as an example
| of active work in this area.
|
| Updating a monolithic LLM seems like a harder problem at the
| moment, and probably would fall under the umbrella of
| "continual learning", though that sub-field would have their
| own subdivisions of different methods.
|
| As for how they would potentially perform, those results would
| be mostly empirically measured, but neither approach would
| completely remove the possibility of (1) missing results --
| which is probably acceptable given Google doesn't always return
| everything relevant, and (2) hallucinating non-factual
| responses -- which can be more dangerous, if not from directly
| instigating / causing harm, then from the incessant worry that
| it might.
| MuffinFlavored wrote:
| > Like the earlier responses said, if it is retrieving
| information from an external data source
|
| I was under the impression it went through like a multi-month
| long ultra expensive training process involving many GPUs on
| terabytes of data "snapshotted" point in time.
|
| Is it possible to do this at a smaller scale once a day at
| the end of the day with "all new content scraped from the
| Internet nightly"?
| visarga wrote:
| Not effectively, because you probably can't return to
| language pre-training after multi-task fine-tuning and
| RLHF. Stage 1 has to go before stages 2 and 3. So they
| would need to fine-tune a stage 1 model and re-apply stages
| 2 and 3.
| shawntan wrote:
| How I imagine what you're thinking of is a kind of small
| update to an existing model by doing backpropagation
| training on 'new' data.
|
| There are existing problems with that, one keyword to
| lookup is 'catastrophic forgetting', where you update on
| recent stuff so much that you overfit on that and forget
| all the prior stuff you learned before. There are methods
| to mitigate that, but I would call that an 'active area of
| research'.
| nicoburns wrote:
| I think the idea might be to effectively provide it with
| the result of a google search (or other datasource) as part
| of the prompt.
| dragonwriter wrote:
| > Is it possible to do this at a smaller scale once a day
| at the end of the day with "all new content scraped from
| the Internet nightly"?
|
| If the model has the ability to browse the web (the tech
| behind ChatGPT by design does, but it is disabled in
| ChatGPT proper, which is, in some respects, a conservative
| public demo) and incorporate data in responses, this can
| "cover" a bit for staleness in the base model.
|
| Even if you can't retrain the model fully daily, with
| enough resources [0] you can have multiple training
| sessions running concurrently and just swap in new backend
| models behind the interface as they arr ready, which,
| combined with browsing ability. acheives something very
| similar. This obviously, barring an enormous advantage in
| underlying tech or access to relevant training data for one
| player, works most in favor of whoever can subsidize the
| biggest hardware commitment.
|
| (Given the different training stages, there may be cost
| efficiency advantages to, say, running less-frequent
| iterations of the lowest-level training stage but more
| frequent iterations of the higher-level ones.)
|
| [0] probably an utterly ludicrous investment for all but a
| handful of firms, but for a ~$trillion firm where this hits
| very close to their core business? Not so ludicrous.
| 1024core wrote:
| The paper about PaLM mentioned that they used 6144 TPU
| chips to train it over several weeks. That's a metric shit
| ton of processing power (pardon my language). If Google
| could dedicate 2 racks of TPUs to just continuously
| training PaLM (note: I'm not sure if LAMDA is PaLM, but
| let's assume they're similar), they could do this
| retraining.
|
| Catch is: consider these statements:
|
| Donald Trump is the President.
|
| Joe Biden is the President.
|
| Barack Obama is the President.
|
| George W Bush is the President.
|
| George H. W. Bush is the President.
|
| Bill Clinton is the President.
|
| All of them were true at some point of time. How do you
| train a model to disambiguate these?
| nestorD wrote:
| Retrieval-based models have a number of strengths that make
| them particularly important from my point of view:
|
| - as said they can be updated with fresh information on the
| fly,
|
| - they can give you sources for their results (meaning that
| you can fact-check the output!),
|
| - they achieve similar performances for significantly smaller
| models (as long as you have a large dataset to retrieve from)
| meaning that they could run locally on consumer hardware
| (coupled with a large dataset on disk or the ability to read
| information from internet).
|
| If I were to spend a significant amount of time building my
| own language model, it would be retrieval-based and try to
| preserve those properties (in particular the ability to run
| on consumer hardware, enabling developers to run models
| locally has proved to be a game changer when stable diffusion
| came out).
| iandanforth wrote:
| If anyone is tempted to do this, here is a good blog post
| on how to build your own retrieval-based LLM powered
| conversational agent.
|
| https://dagster.io/blog/chatgpt-langchain
| Waterluvian wrote:
| Thinking of this and the analogy of the human brain: do models
| "forget" lesser utilized, less significant stuff like humans
| do?
| febeling wrote:
| One more question: apparently LLMs model the human language as
| well as the knowledge encoded in it? Aren't those separate
| concerns? Maybe those can't be separated and that's the reason?
| karmasimida wrote:
| I would say continue update LLM isn't a very good idea, the
| compliance issue will be huge. Also feeding data without
| quality check seems like a sure recipe for disaster.
|
| For the foreseeable future, LLM will be used for a unique set
| of queries that are more operational, like a consult, not for
| stuff that are informational, like what news is published
| today.
|
| If your query is relying on the model to be update to date with
| today's news, you can just put it into the prompt.
| snek_case wrote:
| The obvious fix (which people are already working on) is to
| allow the system to look up information. E.g.: give it access
| to wikipedia.
| baron816 wrote:
| edit: removing comment. I don't think what I wrote was
| confidential, but I don't want to find out the hard way.
| [deleted]
| vitorgrs wrote:
| ChatGPT 4 seems to have newer data/practices already.
|
| At least the Bing ChatGPT integration can get data from
| websites and all of that, and cite the sources. Probably using
| REALM. Not sure if is ChatGPT-4 that would use REALM together
| or if is MSFT integrating both.
|
| https://medium.com/@owenyin/scoop-oh-the-things-youll-do-wit...
|
| Similar to how http://perplexity.ai/ works to get info on
| current data.
| jw1224 wrote:
| ChatGPT 4? I didn't even think they'd announced v2 yet.
| Source?
| vitorgrs wrote:
| I also though that was silly, as we are very early on 3.5
| yet. https://www.windowscentral.com/software-
| apps/microsoft-bing-...
|
| But the leaked Bing Chat feature indeed does show things
| that for now ChatGPT don't have.
| [deleted]
| adastra22 wrote:
| They haven't. Just people making guesses.
| spacephysics wrote:
| Work is being done to create essentially dev ops pipelines for
| faster model iterations. This requires a lot of infrastructure
| from the dev ops side, to the software itself.
|
| Further, depending on the nature of data used, this would make
| such changes more complex (ex PII)
| xnx wrote:
| I believe Google has dealt with a similar problem early in its
| history. In the early 2000's Google's PageRank values had to be
| calculated all at once (approximately monthly). Later they were
| able to move to a continuous/incremental/rolling update.
| Hermel wrote:
| Exactly, so Page and Brin might think that they can pull the
| same trick again.
| greg7mdp wrote:
| Page and Brin's original crawler had the issue, but they
| were unable to fix it, and it was Jeff Dean and Sanjay
| Gupta that rewrote the crawler so that it and the index
| storage would be hardware fault tolerant.
| dekhn wrote:
| The crawler doesn't interact directly with pagerank.
| PageRank is computed later and is attached as a per-
| document value.
|
| I asked Jeff about what it was like in the early days and
| he told me: when they first joined, the entire crawl to
| index to serving stack was documented in a README that
| you would follow, typing commands and waiting for each
| step to complete. A failure in a step meant completely
| starting over (for that step) or even earlier, depending
| on how and where temp data was materialized.
|
| He said he and Sanjay (Ghemawat, not Gupta) then wrote
| mapreduce as a general purpose tool for solving multiple
| steps in crawl to servable index. Not only is mapreduce
| good at restarting (if the map output and the shuffle
| output are persistent), the design of mapreduce naturally
| lends itself to building an indexing system.
|
| If you go back to the old papers you'll see several
| technologies mentioned over and over. protocol buffers,
| recordio, and sstable: the first is an archive format to
| store large amounts of documents in small number of
| sharded files, the second is a key-sorted version of the
| same data (or some transformed version of the data). So,
| building an inverted index is trivial: your mapper is
| passed documents and emits key/value pairs (token,
| document) if a token is in the document. The shuffler
| automatically handles grouping all the keys, and sorting
| the values, which produces a fairly well-organized
| associative table (in the format of sstables).
|
| BigTable came about because managing lots of sstables
| mutably became challenging. | MapReduce was replaced with
| Flume, which was far more general and easier to work
| with, and BigTable was replaced with Spanner (ditto), and
| GFS replaced with Colossus, but many of the underlying
| aspects of how things are done at Google in prod are
| based on what Jeff, Sanjay, and a few others did a long
| time ago.
|
| Note that mapreduce isn't particularly innovative except
| the scaling aspects were fairly esoteric at the time.
| coliveira wrote:
| Why do you think it can't update its dataset? The only reason I
| think they're using a 2021 dataset is because they tested it
| throughly. In the next few weeks they will be releasing more up
| to date databases.
| rushingcreek wrote:
| https://phind.com (YC S22) uses LLMs grounded in internet
| contexts to answer questions.
|
| There's an interesting tradeoff between grounding LLM answers
| in web contexts and answering questions from parametric memory
| like ChatGPT. The former is more accurate and verifiable, but
| the latter can be more creative and specific to you.
|
| We will have both of those answers soon. (Disclaimer: I am the
| co-founder).
| mark_l_watson wrote:
| I had not heard of phind.com either. I asked the same
| detailed question about myself to both perplexity.ai and
| phone.com, and I really liked both answers with references.
| Both are likely more useful to me, right now, than Google
| search. That said, the technique of a accepting a question,
| get content text with web searches, and then use LLMs like
| squad, etc. to answer questions - this is something the
| Google and Bing search will soon do also, with many of their
| improvements.
|
| As a slightly disinterested third party, it will be fun the
| watch the competition.
| ifyoubuildit wrote:
| > ChatGPT is awesome, but it is obviously hamstrung by the fact
| that it crawled the web at the end of 2021, so all of its data
| is essentially "frozen" and it doesn't "know" of any topics
| that occurred after 2021
|
| I think this could be a feature. Things on the internet have a
| life cycle. After a while they can be altered to fit various
| agendas or just drowned out by seo nonsense. Seeing an
| immutable snapshot in time might be a good defense of that.
| notahacker wrote:
| For a chatbot, it's a feature.
|
| For the large proportion of search queries that are "give me
| context for $newsitem", "what is $latestthing", "what is
| $celebrity up to", "can you solve my problem with the latest
| version of x" it's a show stopping bug (frankly Google
| weighting established content higher in most contexts is
| already an issue for the last of those queries: Googling
| error messages etc). And at least all the SEO'd "Best Items
| In $CurrentYear" articles that aren't that up to date
| _attempt_ to look current
| ghaff wrote:
| I'm not sure if, from the perspective of consumers, it's a
| feature or a bug. Sort of the only thing keeping ChatGPT or
| equivalent from being a massive blogspam creator that puts
| mostly young writers cranking out content for pennies out
| on the street is that it can only create relatively
| evergreen content.
| notahacker wrote:
| I think [Chat]GPT's output is _very_ well represented in
| blogspam pages I 've seen recently, so consumers get the
| worst of both worlds: just because it's too out of date
| to properly answer your question directly doesn't mean it
| can't help other people generate filler text that
| outranks pages with the answer in web search...
| jiggawatts wrote:
| > taking another step forward by opening it up to trusted testers
|
| Ah yes, the tried and true method used by Google for ensuring
| wide adoption, which they pioneered with Google Wave. Restricting
| adoption to a small group has never failed to ensure market
| success!
| coliveira wrote:
| "LAME DA" doesn't seem to be a good name for an AI technology.
| nlstitch wrote:
| Seeing is believing at this point. And Im hoping it will be.
| Google (Assistant) development has been stagnant for years now,
| up to the point that I'm often more irritated by it than it is
| useful. This could be the AI to actually power an AI assistant I
| was already counting on years ago.
| [deleted]
| impulser_ wrote:
| For anyone that is interested.
|
| This is the ChatGPT reply to the exact same question asked in the
| preview in the article.
|
| Here are a few things that the James Webb Space Telescope is
| expected to discover that you could share with your 9-year-old:
|
| The formation of stars and planets: The James Webb Space
| Telescope will be able to observe the birth of stars and the
| formation of planetary systems, helping us understand how our own
| solar system was created.
|
| The search for life on other planets: The telescope will be able
| to search for signs of life on other planets, such as the
| presence of water or certain gases in their atmospheres.
|
| The history of the universe: The James Webb Space Telescope will
| be able to look back in time to observe some of the first
| galaxies that formed after the Big Bang, helping us learn about
| the early history of the universe.
|
| Understanding black holes: The telescope will be able to study
| black holes and how they interact with the galaxies around them,
| helping us better understand these mysterious objects.
|
| The study of exoplanets: The James Webb Space Telescope will be
| able to study exoplanets, or planets outside our solar system, in
| greater detail, helping us learn more about the diversity of
| planetary systems in the universe.
|
| The Google reply is obviously better because it tells you actual
| discoveries, while ChatGPT changes the question to expected
| discoveries.
| opinali wrote:
| ChatGPT is a pure conversational model, while Google can
| integrate this into a vast knowledge model to work with actual
| facts. (Just speculation; Googler, but no inside info on this.)
| Of course, as Microsoft adds ChatGPT into Bing they should also
| integrate it into the rest of their search stack. This will be
| an interesting horse-race to watch since it won't be just the
| AI models but also a massive amount of secondary infrastructure
| for desired outcomes with content safety (no erotica or nazi
| pamphlets on demand), IP protection (no plagiarism), political
| and cultural sensibilities, disinfo, and a ton of other
| problems.
| ZiiS wrote:
| This was a quite clever choice; JWST is just newenough that
| ChatGPT's current model wasn't trained on its results.
| valine wrote:
| That's a byproduct of ChatGPTs 2021 training date. If you give
| ChatGPT updated information about JWST and then ask it for a
| summary, it will give a result much more like google's.
| layer8 wrote:
| This difference can be ascribed to ChatGPT's knowledge cutoff
| date in 2021.
| sfjailbird wrote:
| It used to be that Google would find search results on the web
| and send you there. They were good at it. Good for content
| creators, good for users.
|
| Then they started scraping the destination pages and present the
| answer right there on Google's own results page. No traffic for
| you. Well at least there was a link.
|
| Now they take it one step further, and just steal the content and
| feed it into their gargantuan pattern matcher, to be spit out to
| users in a remixed form, swirled up with a bunch of similarly
| scraped content from the open web. Great for Google, RIP content
| creators.
| rchaud wrote:
| "content creator" is a separate category of for-profit online
| media. As it's designed for mass consumption, the content
| creators moved off the open web a long time ago to sharecrop on
| BigCorp's platforms: YouTube, Twitch, Substack, TikTok, etc.
|
| There are lots of non-commercial random blogs out there with
| useful information on long-tail topics. I agree that those will
| disappear from search, as AI will put a lower weight on their
| posts compared to something from a major website.
| dizzydes wrote:
| > Soon, you'll see AI-powered features in Search
|
| Despite this blog obviously being written for Wall St, this line
| is key. This is why anyone is going to struggle to compete with
| Google in AI.
|
| Google Search is used so widely and its taxonomy of meaning so
| vast already that once they flip this on they'll be unstoppable.
| (Assuming any rate of improvement whatsoever as we search.)
|
| I'm not mentioning all other learning data like email, photos and
| drive, in part because other companies have similar, albeit in
| more specialised forms.
| samwillis wrote:
| Google is on a collision course with regulators over search. If
| they are seen to be taking yet more content and knowledge from
| websites and "republishing" it they are going to find
| themselves with large fines and sanctions.
|
| I think they are too "big" to really push AI, it needs smaller
| companies willing to take a higher risk.
| Ajedi32 wrote:
| It's an interesting conundrum because facts aren't
| copyrightable, but in a world with intelligent language
| models that can ingest facts and spit them back out in
| whatever phrasing or format is most useful to the user, facts
| are also the only valuable part of such websites.
|
| On the flip side, trying to make facts copyrightable seems
| like a terrible idea for all sorts of reasons. For example,
| if facts were copyrightable, that would make online
| discussion of factual stories illegal, since it's hard to
| discuss a fact without revealing what it is. Also, it's not
| always clear who should get "credit" for a fact, since facts
| are by their very nature true independent of who first
| reported them.
|
| Maybe journalism will eventually become similar to academia,
| where journalists are funded by governments and large
| corporations who have an interest in learning, and the
| resulting discoveries are (ideally) made freely available for
| everyone to access?
| kolinko wrote:
| In case of Google it's not as much about facts as about
| antitrust.
|
| They can break antitrust laws if they go too much in a
| direction of delivering outright replies instead of
| redirecting to websites.
| dizzydes wrote:
| Fair. Moreover, what _are_ search or even content websites
| for if Google gobble up all that knowledge and distil it out.
|
| But with China, Russia and India lurking, perhaps Congress
| might drag their feet on reigning AI in. Google Cloud are now
| poised to be going for some pretty decent govt contracts.
| cactusplant7374 wrote:
| I know this wasn't your point, but now I'm wondering if
| countries like India can afford GPU intensive search
| results.
| adrr wrote:
| Google's inability execute is why they will lose the AI war.
| The fact the CEO has to write this article to wall street shows
| that they were caught offguard and have no real plans. If they
| had plans, why would Google management declare a code red over
| chatGPT?
|
| Take the difference between Microsoft and Google. Microsoft
| just released tools that will make your life much easier.
| Intelligent Recap of teams meetings, ability to assign tasks
| based on what was discussed etc. Microsoft will announce bing
| with have chatgpt integration tomorrow. MSFT is eating Goog's
| lunch and Sundar needs to go.
| mrkramer wrote:
| Sundar needs to go? And who will replace him? Larry and
| Sergey? They figured out the early web but the web of today
| is the whole another beast that is waiting to be understood.
| 13years wrote:
| After all the buzz of decentralization, AI is going to be the
| new era of centralization. One AI interface to rule them all.
| dizzydes wrote:
| Thats a very interesting point, are all the web3 folks
| looking the wrong way?
| 13years wrote:
| There are a number of decentralized AI projects in that
| space. However, based on how effective web3 has been
| competitively against other big tech competitors for search
| and social media, they will need to be an order of
| magnitude more successful than on previous efforts.
|
| Most projects are focused on privacy, user control and
| being censorship resistant. Which are all important, just
| not that important to the majority of everyday consumers
| who will take features and convenience over those other
| benefits. If decentralized AI is going to be competitive,
| it must actually be better along the lines of its actual
| features that enhance productivity.
| dougmwne wrote:
| Yes, but will their revenue survive flipping that switch or
| will that kill the golden Adsense goose?
| dizzydes wrote:
| Fair question.
|
| Depending on how slimy they're willing to be I'd argue
| there's even more scope to push ads when "advising" user
| through a grey area vs straight up keyword search.
|
| Think going several steps ahead of initial q, increased trust
| and reliance on responses, multiple follow up questions with
| more ads etc.
|
| I'm just envisaging this based on my time with ChatGPT these
| last few weeks.
| jxf wrote:
| This is a huge revenue opportunity. Google would not be
| investing in it if it wasn't.
| theonlybutlet wrote:
| I don't think it's that clearcut. These AI queries are resource
| intensive. Google will have to cut a fine line between quality
| and profit margin. If it's no good people just won't bother and
| it won't gain traction. The searches we make are already
| analyzed and all models tend to use billions of parameters
| anyway, even self generated. Google also are limited by their
| risk aversion, as seen in this extremely sanitized letter by
| Sundar, devoid of substance. Their existing AI tool is severely
| limited. If this new tool comes out looking like that prior
| Google tool, it's going to be very difficult for them to gain
| traction.
| dizzydes wrote:
| 1. ChatGPT have made a decent go of it on a much smaller
| budget
|
| 2. Wall St tends to be very forgiving when the investment is
| something with a strong a moat as AI. Metaverse is an example
| of what happens when they don't believe...
|
| 3. With a few exceptions like weather, their current searches
| provide links to static pages others have built, so much of
| their understanding and analysis is going to waste. Giving
| custom results breaks through that.
| rimliu wrote:
| ChatGPT is notorious for being damn sure about absolutely
| wrong things. If something like that powers the search...
| elorant wrote:
| All the book recommendations I got were for non-existent
| books. Makes you wonder if it creates summaries of the
| titles themselves.
| cactusplant7374 wrote:
| Didn't Altman respond to Elon on Twitter and say an
| interaction cost 1 cent?
| rossjudson wrote:
| If Google handles 10 billion searches per day (guessing),
| what does that work out to?
| theonlybutlet wrote:
| https://twitter.com/sama/status/1599671496636780546?s=20&
| t=p...
| esskay wrote:
| Do we actually know the budget behind ChatGPT? I know
| Microsoft has thrown money at them and are providing a huge
| amount of cloud resources but beyond that I've missed any
| mention of the funding/costs.
| fdgsdfogijq wrote:
| I think the new NLP technology made all their search technology
| obsolete. This company is in trouble.
| rchaud wrote:
| > that once they flip this on they'll be unstoppable. (Assuming
| any rate of improvement whatsoever as we search.)
|
| Unstoppable as measured by what? More ad revenue?
|
| They're already the #1 search engine due to two decades of
| general goodwill and a decade of monopoly power in mobile.
| londons_explore wrote:
| I wonder how long till they open it up to your private data
| stored in Google? Eg.
|
| User: What should I be doing today?
|
| AI: You have a court appearance at 9am. Prioritize that,
| because failing to appear might result in an arrest warrant.
| Next, prioritize your mums birthday - all the other family will
| be there, and with your mums cancer results last week, this
| might be the last. If you travel between them by bus, then you
| can spend the time going through your teams messages that you
| should have replied to last week.
|
| Me: What about the leaking faucet in my house?
|
| AI: You don't have the time to fix it yourself, nor the money
| to pay a plumber to do it, so I suggest you leave it leaking
| for now. I watched the video - its leaking down the basin, so
| won't do damage, and the water cost is around 8 cents a day.
| robterrell wrote:
| Fun exercise for the reader: how much of this is actually
| possible with LLMs and how much is not.
| hooande wrote:
| Google could do this now. They already have your calendar and
| your contacts. Do you think that a conversational interface
| was what was holding them back? Thousands of engineers, but
| if only they could figure out how to merge Gmail and Eliza!
| dizzydes wrote:
| Yea this isn't a huge reach.
|
| At that point the line between commerce and giving the best
| advice is going to get REALLY messy.
| foooobaba wrote:
| User: What should I be doing today?
|
| AI: You have a court appearance today, I have booked a route
| for you on google maps. Next buy a gift for your mum's
| birthday, here are some recommendations sorted by ad spend
| spend. For your travel, I recommend these options, sorted by
| ad spend.
|
| Me: What about the leaking faucet in my house?
|
| AI: You don't have the time to fix it yourself, here is a
| list of contractors that can fix the leak, sorted by google
| ad spend.
| wnolens wrote:
| Is that any different from trying to source it "on your
| own"?
| esskay wrote:
| I'd imagine it'll be something they do. Hooking it into
| things you've told assistant, documents you've stored,
| emails, calendar events, map data, etc.
|
| Pretty creepy and a tad dystopian but thats Google for you.
| Havoc wrote:
| >its taxonomy of meaning so vast already
|
| Can this be integrated for training though?
| revskill wrote:
| I'm curious to see if this article is well SEO by Google Bot
| itself ?
| dougmwne wrote:
| This is a milestone. Google has been keeping the fruits of its AI
| research locked away from the unwashed masses. They did not seem
| to be on any path to commercialization, Google Cloud access, or
| releasing features based on these models. OpenAI (and Microsoft
| most likely) forced their hand and all at once they are releasing
| tech-previews and talking about adding it to the search engine
| results page, all while opening up API access to several of their
| trained models.
|
| Microsoft is rumored to be adding GPT powered features to Bing
| very soon and might beat Google to market.
|
| Very interesting times!
| srajabi wrote:
| This is all fluff with very little substance, OpenAI wow'ed the
| whole world with ChatGPT and all Google can do is post a half-
| baked fluff piece that they're releasing something "soon"
| me551ah wrote:
| AI is the evolution of search that we always wanted. Everytime I
| search, I open the first few links and find the information
| there. It's a very repeatable task, like looking for the right
| stackoverflow answer or digging through imdb to find the right
| movie or searching reddit/HN threads. It's about time this was
| automated.
| xtracto wrote:
| At this point, Microsoft should do whatever it can to make a deal
| with Apple to place a ChatGPT powered platform in the iPhone/i
| Devices.
|
| Most of the people using "computers" nowadays do it through
| mobile phones, and Google has a strong grip in that market with
| Android, with only Apple giving them some competition. Thus the
| only platform where Microsoft could really compete is in iOS.
|
| If Microsoft + Apple could get together in this one, they could
| do a _really_ killer app doing a next level Siri or similar.
|
| Otherwise, What would Microsoft do? Add ChatGPT to Windows? that
| means PCs ... that means a Office/work related agent, which is
| boring and kind of reminds me of the Mac vs PC video-ads of
| 2000s.
| milosmns wrote:
| Isn't ChatGPT still like super expensive to use and run? At
| least compared to Google queries, but maybe in general too?
| While Google still pays Apple a ton od money to remain the
| default search engine... which is close to zero work on Apple's
| side.
|
| Microsoft would then need to pay for ChatGPT computation, model
| retraining, maybe testing of deployments/upgrades, maybe
| sponsor Apple's initial development efforts, plus pay for the
| expensive deal to be Apple's default choice.
|
| Am I understanding the problem correctly? It looks like a lot
| of work and very expensive if I'm getting it right.
| seydor wrote:
| Microsoft has a much larger platform than iOS which also
| happens to be where people do most of their actual work. Apple
| should probably be paying them
| mdasen wrote:
| My question is: what kind of deal are you thinking? Would Apple
| pay Microsoft a lot of money for this ChatGPT-powered platform?
| Would Microsoft be paying Apple?
|
| With search, Google pays Apple with the payoff being that
| people end up seeing Google's ads. With ChatGPT, Microsoft
| wouldn't be getting money so Apple would presumably need to pay
| Microsoft.
|
| You've phrased it like Microsoft needs to get it on people's
| phones rather than Apple needing a competitor to Google's NLP
| (Microsoft should do whatever it can, not Apple should do
| whatever it can which implies that Microsoft should pay Apple).
| However, we haven't really seen what ChatGPT is in terms of a
| product yet (product, not feature).
|
| Let's say Microsoft pays Apple to get ChatGPT onto iPhones.
| What does Microsoft get out of that? Bragging rights? Ads in
| Siri? Or maybe as part of an overall deal of Bing + ChatGPT?
|
| I agree that things like ChatGPT are cool, but I think it's
| unclear (at least to me) a company like Microsoft will make
| money off it without charging for it (or making it terrible
| like allowing companies to pay for placement in ChatGPT
| responses like "what's the best vacuum?" gets you "The best
| vacuum by far is ProductPlacement. It has much better suction
| than CompetitorProduct"). Amazon has tried using Alexa to
| upsell things, but it can make Alexa really annoying at times.
|
| They could come up with a really cool next-level Siri, but I
| guess I'm not sure what's in it for Microsoft in such a deal. I
| see what's in it for Apple and users.
| felipebarreiros wrote:
| Does it really matter if it is boring but is generating $6B
| every year? Ultimately it's not what's cool, but what drives
| user adoption and revenue.
|
| Otherwise it will be just like Magic Leap with a pretty cool
| product nobody ever used.
| pphysch wrote:
| What's less likely? MS+Apple alliance or Google shipping a
| solid product?
| tonymet wrote:
| AI fact summarization like this will further obfuscate the facts
| from the summary. People already believe the top 3 posts from
| Google are the benchmark for truth. Now customers won't even see
| the sources (e.g. MSNBC, Wikipedia) of the "facts".
|
| Google is deliberately biasing results in the name of ML-
| fairness, which may be laudable. Now the bias will be even harder
| to distinguish from fact.
| alecco wrote:
| you.com gives reference links
| jklinger410 wrote:
| Just because AI will tell you answers does not mean it will do
| away with citation.
| tonymet wrote:
| it will mean that citation is less obvious because the user
| will no longer engage with the source material (by clocking a
| link to read it )
| Zetobal wrote:
| Responsible = crisis support...mhm k.
| speedgoose wrote:
| They forgot to include the link.
| greenhearth wrote:
| No thanks! We have enough AI for now, thank you!
| bastardoperator wrote:
| To be honest this feels reactive and reeks of desperation.
| tooltitude wrote:
| This is very good news for us as consumers. We don't want anyone
| of the players to dominate this field, and we want the service to
| be as cheap as possible, ideally free.
| Tepix wrote:
| API access isn't what we want. We want to run those models
| ourselves.
| tooltitude wrote:
| Almost all players in this field publish their work. If need
| arises we will be able to reproduce them, but only large
| company will be able to run the models cost efficiently, and
| there're a lot of scale effects here.
| 13years wrote:
| It will essentially still be locked away by an oligopoly that
| has little distinction among the participants. The influence on
| society held by that oligopoly will significantly surpass the
| current concerns of social media.
|
| For much more in depth take, I wrote recently about that here.
| https://dakara.substack.com/p/ai-and-the-end-to-all-things
| sumoboy wrote:
| Let the API wars begin. Microsoft seems to have positioned itself
| to compete with Google.
| patrickaljord wrote:
| That's been going on for the last 23 years at least.
| sumoboy wrote:
| Now it's really going to be about revenue.
| bobvanluijt wrote:
| Tomorrow https://weaviate.io will also release a generative
| search module that accepts LaMDA when it's in GA besides GPT-
| based models. (I'm affiliated with Weaviate)
| unethical_ban wrote:
| It is absolutely critical for our society that this technology,
| at its full power, be developed open source to the public.
|
| That presents dangers to society. Educating citizens on the
| ubiquity of human-like text being generated by bots is one
| challenge. Knowing that bad actors will be able to use these
| models for evil is another. "Write a convincing 10 page manifesto
| on the dangers this religious minority poses to societal
| cohesion" or "tell me a cost effective way to create an IED that
| won't set off suspected red flags per Texas statutes, and how to
| deploy it in an urban area for maximum impact".
|
| The risk of this technology being contained to Google and
| governments, on the other hand, is to grant them monopoly on
| unmatched analysis of data in the history of the world, purely
| for profit and the continuation of power. Free thought will be
| crippled via only approved questions being permitted, all queries
| analyzes and monitored by the central authority.
|
| We must all own this technology.
| ilaksh wrote:
| Good point on open source. False about "good" and "evil".
|
| The most dangerous thing for society is perpetuating the idea
| of good and evil because that is what motivates war and
| terrorism. It is used as propaganda to make conflicts into
| moral issue and justify mass killing. What do you think the
| terrorists are fighting against? Evil (in their minds).
|
| The real problem is that there are different worldviews and
| political groups, a lack of metacognition about this, and
| governments or dissident groups using this to enable their
| propaganda to further their political causes.
|
| Worldview and group membership are tied together to a large
| degree.
|
| Also as far as being open source, we already have open source
| GPT systems. The problem is that the most powerful models
| require dataset sizes that cannot currently train or run on
| normal GPU setups. Only a few companies have the infrastructure
| for it.
|
| Eventually we will get more efficient models, and/or possibly a
| way to do it with decentralized GPU mesh (assuming that's
| possible), and/or memristor manufacturing will start scaling up
| which will make it possible to run these large models on
| consumer hardware someday.
| LesZedCB wrote:
| interesting, haven't looked into memristors in a while but it
| seems like that's a real possibility
|
| https://www.frontiersin.org/articles/10.3389/fnano.2021.6459.
| ..
| XnoiVeX wrote:
| Google needs a new CEO. Too little. Too late.
| zmmmmm wrote:
| so there are two narratives here:
|
| (1) Google is behind and playing catchup, slow and bloated and
| weighed down by bureaucracy they are sinking
|
| (2) Google has had this tech behind doors for years but not
| released it because of the risk of public perception and
| regulatory blowback. Now under the cover of OpenAI and Stability
| they can do it.
|
| The second one seems plausible but I can't help being struck by
| how much their AI driven products seem to have stagnated over the
| last 5 years. Google Assistant (or whatever it is called now)
| seems worse at understanding my simple requests than it was 10
| years ago. Things that seemed magical and worked very reliably
| like "remind me in 3 months that I left the oil can behind the
| paint tin" now fail so often I've stopped trying. Combined with
| the lack of detail in the blog post, I'm inclined to lean towards
| (1) - even if I do believe thew actual AI knownhow is buried
| somewhere inside Google, I think it is so many layers from
| anybody who could deliver it in the form of a product that it's
| effectively like it isn't there.
| kup0 wrote:
| Can't wait to see the AI corrupted by advertising and money
| tarkin2 wrote:
| Can Bing or Google better integrate ChatGPT or similar to retain
| users? Isn't that the question?
|
| The problem with ChatGPT being confident and wrong brings up the
| chance of litigation, of course.
|
| The problem for search engines, surely, is that people will get
| their answers from AI rather than from a search engine, laden
| with its advertisers.
| hintymad wrote:
| > Soon, you'll see AI-powered features in Search
|
| I was wondering who is the audience of this article. Hasn't
| Google search been powered by numerous machine learning
| algorithms for years? Another thing I don't understand is that
| why Google's product strategy is like Baidu's: AI First. I
| mention Baidu because they are infamous for not having a product
| vision. Since when a technology itself could be a product
| strategy? Information at your finger tips is a product strategy.
| Organizing the world's information is a product strategy. AI is
| just a means to many ends, right?
| topspin wrote:
| > I was wondering who is the audience of this article.
|
| Shareholders.
| whoisthisguy wrote:
| Let's be honest. Google would have never moved an inch if there
| was no ChatGPT. Competition is good.
| dougmwne wrote:
| Of course not. Why would they risk disrupting their major
| revenue source by screwing with search and AdWords!?
| user3939382 wrote:
| The AI I'm interested in is of this sort https://mycroft.ai/ i.e.
| where I run and control it locally.
|
| I don't want to go on any more "journeys" with Google. The last
| one started with me rooting for and trusting them (circa IPO..
| 2004?) and ended with a dystopian nightmare spy apparatus, abuses
| like AMP, the attempt to cripple uBlock, etc.
| afro88 wrote:
| Bit of a sidebar, but I find it sad that people use AI tools to
| connect with their kids. Whether it's getting it to make up a
| little story for them to tell, or a fully illustrated book, or in
| the case of the gif from this post: a list of recent discoveries
| made by the James Webb telescope that the AI thinks a 9 year old
| might like.
| oars wrote:
| I was able to see LaMDA in action about 1.5 years ago. It was
| just as awe-inducing as ChatGPT. Google is not behind in this
| race. They're simply slower to roll out new functionality. And
| maybe rightly so? Some of the things I saw ChatGPT say would have
| been multi-day international bad headlines for Google, if a
| Google AI had said them instead of an upstart startup.
| hidelooktropic wrote:
| Why is there an almost identical comment right below this one
| from a different user?
| cactusplant7374 wrote:
| Yes.
|
| https://news.ycombinator.com/item?id=34683114
| nebula8804 wrote:
| Sometimes people on poor connections click the send button
| twice and it registers as two separate messages.
| nebula8804 wrote:
| Sometimes people on poor connections click the send button
| twice and it registers as two separate messages
| PaulDavisThe1st wrote:
| TLDR: "we're still relevant, honest!"
| IncRnd wrote:
| It's about the stock, not pandering and catering to how people
| think of google.
| PaulDavisThe1st wrote:
| It is completely a statement to try to assure people that
| Google is still doing relevant work in the AI realm. It reads
| like a middle-of-the-night panic attack after waking from a
| dream that Pichai had in which Google had essentially
| vanished.
| crackercrews wrote:
| People are complaining that it's not available yet. I'd guess
| they have something that could be pretty useful right now. But
| they need to make sure it doesn't cause them embarrassment by
| saying racist/sexist/etc things.
| jsnell wrote:
| If that's the problem, they're not going to fix that in a few
| weeks.
|
| More likely this is being done since you can't capacity plan at
| all until you see how real users actually interact with the
| service.
| underlines wrote:
| Is there a way to become a tester?
| verelo wrote:
| Launched, where? Nice try, Google.
| [deleted]
| firecall wrote:
| That is the worst press-release I've read for years.
|
| In that it's overly wordy, lacking in information, generally hard
| to read, boring and left me not knowing if there was an
| announcement of a product of not?
|
| Dreadful.
|
| Maybe Bard wrote the press-release?
| patientplatypus wrote:
| [dead]
| shaohua wrote:
| someone forgot to put in the Call to action
| andrewstuart wrote:
| Lotus 123, Borland and Wordperfect were at the top of the
| software world. They failed to make the transition to
| GUIs/Windows.
|
| Microsoft missed the arrival of the web. Microsoft also missed
| the mobile revolution and ended up with zero mobile operating
| system market share.
|
| Internet Explorer, having vanquished Netscape, declared "job
| done" and stopped developing the web browser further, only to be
| cast to irrelevance for its failure to advance and innovate. Much
| like Google search.
|
| Kodak, Yahoo, Commodore, MySpace etc etc etc all missed the
| critical technology change that left their business behind.
|
| Despite seeing the oncoming train, Google may be too arrogant,
| too internally political, too controlled by it's vast river of
| web advertising gold, to be willing or able to make the changes
| needed.
|
| And it may be that Google simply cannot transition it's search
| over to becoming top dog in AI information seeking - it's
| possible that AI interfaces aren't a "winner take all" market
| like search is. If that turns out to be true then Google won't be
| finished but it will be diminished.
|
| ChatGPT brings a laser focus that Google simply cannot.
|
| It's possible Google's time has passed.
|
| I remember distinctly when Google arrived how instantly old and
| out of date Altavista suddenly looked - that's how Google search
| looks now.
| returningfory2 wrote:
| I feel like all the examples you give are actually counter
| examples to the thesis that Google will decline?
|
| Like, those are all examples of companies which failed to adapt
| to some new reality. This announcement is Google seeing AI as
| the next thing and proactively engaging with it.
| miramba wrote:
| The results of Google today really look like Altavista in 1999.
| I started using you.com, which looks like Google 10 years ago.
| You get actual non-SEO-optimized search results on the first
| page. I'm sure that will change once more people use it, but at
| the moment I have a working search engine again.
| MeriB wrote:
| Same. switched to you.com since day and never looked back.
| Once in a while I'll use DuckDuckGo for very specific
| queries.
| pleasantpeasant wrote:
| Google should release whatever that ex-dev was going on about
| some sentient AI that Google has looked up.
|
| I think Google has enough capital, brand recognition, and
| customer dependence, that they could get away with missing
| some of the AI hype train for now.
| codegeek wrote:
| "Microsoft also missed the mobile revolution"
|
| I remember getting a Windows Mobile phone and loved it. Their
| UI (tiling etc was cool) was superior to iOS and Android at the
| time ( at least for me). I was sad to see them disappear.
| chipgap98 wrote:
| Microsoft feels like an outlier on this list. They are thriving
| right now.
|
| Also, there are still many categories of things that ChatGPT-
| like bots can't help with yet, such as shopping. I think we're
| still very early in this cycle. That doesn't mean Google will
| succeed, but it feels premature to be writing their obituary.
| Miraste wrote:
| Windows, Office, and more recently Azure are big enough to
| make these failures survivable and give Microsoft more
| chances, but IE and Windows Mobile are textbook examples of
| complacency.
| mrkramer wrote:
| IE stood no chance against Google Chrome because just like
| Microsoft shoved down IE down the users' throats the same
| thing happened with Chrome and Google.
| daveidol wrote:
| Very true. Although, as an aside since you brought it up: I
| will say shopping on Google has gotten far worse these days
| days with all the SEO optimized "top 10 best X" pages that
| are basically just affiliate link spam with extremely limited
| value / product testing / insight.
| chipgap98 wrote:
| That's a fair point about shopping. I was more thinking
| that I end up googling things that then lead me to
| ecommerce sites and its unlikely that ChatGPT will replace
| that any time soon.
| firebaze wrote:
| This is probably true, but I honestly wonder why. Windows is
| a commodity as far as I understand, which you can get for
| free with not-so-hidden tricks, which are also apparently
| approved by Microsoft themselves.
|
| O365 etc. survive due to corporate inertia (Excel), but I
| wonder if growth stems from new customers vs. big, large
| customers growing and requiring more licenses while actively
| looking for replacements.
|
| Azure is good, sure, but AWS is better (yeah, the console)
| and google will probably do anything to not go into
| irrelevance in this area, so they're stuck between a rock and
| a hard place.
|
| I still have MS stock (with a large payoff atm), but I
| honestly wonder when it's time to sell.
| anthropodie wrote:
| You forgot Nokia. They had touch screen prototype before Iphone
| but they thought world was not ready. When Android came they
| took too long to admit S60 is dead.
| adrianmonk wrote:
| > _Microsoft also missed the mobile revolution and ended up
| with zero mobile operating system market share._
|
| OTOH, Google got scooped when in January 2007, Apple changed
| computing by launching the iPhone.
|
| But, though it had not been announced, Google already had the
| Android project in progress, which pivoted to a more iPhone-
| like concept (full-device touchscreen, no keyboard) and ended
| up doing OK in the market.
|
| Presumably you can see the parallel I'm trying to make with
| today's situation. Obviously it doesn't prove anything, but if
| we're looking at past history as a guide, this is something
| that also happened.
| rchaud wrote:
| > and ended up doing OK in the market.
|
| Thanks in no small part to Samsung. Google honestly would
| probably not have gone beyond their initial Blackberry-style
| design approach without the iPhone. And Samsung's Android
| flavour pushed hardware capabilities way past what Google
| provided out of the box.
| status200 wrote:
| Agreed on the trust part - at this point i would expect Bard to
| start incorporating ads into its responses as soon as they had
| any sort of market dominance (If it is even competitive enough
| to achieve that).
| wilsonnb3 wrote:
| Google was already next when they missed the social media boat.
|
| That said, Microsoft is still the second most valuable company
| in the world a decade after missing out on mobile, so it
| doesn't really seem like a big deal.
| ignite wrote:
| I certainly didn't kill Microsoft, but it's tens of billions
| of dollars they didn't get. It's significant, even at
| Microsoft's scale.
| chipgap98 wrote:
| There is also opportunity cost though. Maybe if they
| succeeded in mobile then they would have missed Teams. Its
| hard to say that the side effects from missing that wave
| were exclusively negative.
| xiphias2 wrote:
| Quite the opposite. If they have owned mobile + desktop,
| they could have a much stronger integration, and we
| wouldn't be Google first with our apps.
| chipgap98 wrote:
| Yeah that's a good point with regards to integration. I
| still think the Microsoft that wins in mobile looks very
| different from the Microsoft we know today.
| lotsofpulp wrote:
| Using Teams as a not negative example is very odd.
| chipgap98 wrote:
| They have crushed Slack with Teams and it is the backbone
| of their enterprise offering. Am I missing something?
| lotsofpulp wrote:
| I am referring to the near universal opinion that Teams
| is shit software that is only worth forcing employees to
| use because it is free.
| bombcar wrote:
| Arguably Microsoft is actually well-placed to
| _continually miss_ major advancements in areas they
| should be king in (or adjacent to them) and yet continue.
| neffy wrote:
| And this is Google's core business. Nothing came along yet
| that replaced corporate use of microsoft office, and that
| is were they make most of their money.
| rchaud wrote:
| How did they miss the boat when they have YouTube? I assume
| by 'social media' you mean "user-generated content that we
| can slap ads on".
|
| Facebook doesn't make any money when people talk to each
| other, they make it when people click ads. Same goes for
| Google. "Social Media" is just another ad vector.
| Tepix wrote:
| Google has YouTube.
| wvenable wrote:
| It's a big deal. It's just that Microsoft has _lots_ of other
| businesses. They could have had a billion dollar mobile
| business too, but they don 't.
| jliptzin wrote:
| Plenty of cases where you just want to type something in a
| search box and see a bunch of different options - like
| shopping. Let's say you're in the market for a keyboard. Would
| you ask ChatGPT what's the best keyboard on the market right
| now, and just buy that? I wouldn't. I want to see a few
| different options and I'm not even someone who enjoys shopping.
| Where there's a list of options to display, google will have
| plenty of room to throw their ads in. If anything Amazon is
| more of a threat to google, if all online shopping ends up
| there.
|
| I can search for, find, and order virtually anything I want in
| less than a minute. Unless an AI is going to anticipate exactly
| what I need, order it for me, and have it delivered before I
| even think about it, I don't see these two things competing
| much.
| zenkat wrote:
| I would definitely ask ChatGPT what the best keyboards are,
| summarizing their strengths/weaknesses, and then use that as
| the starting point of my search.
|
| Comparison shopping is a major PITA with current sites,
| clicking back-and-forth between various product pages and
| review sites, and trying to distill it down to a few relevant
| choices -- things that ChatGPT's excellent abilities at
| summarization could really help with.
| impulser_ wrote:
| Crazy to say this about a company with a 5y CAGR of 25% at
| nearly 300b in yearly revenue. That more growth than Microsoft,
| Apple, Amazon, and pretty much any other large tech company.
|
| Google time has passed?
|
| They still have 7-8 products with more than a billion monthly
| users.
|
| If you go back and look at the company you listed. They die
| because they were poorly ran companies. Google isn't a poorly
| ran company.
| mejutoco wrote:
| Not a dog in this fight but an alternative to dying would be
| to become ibm (to be seen as irrelevant).
| [deleted]
| michelpp wrote:
| I agree and just want to add to your list, Intel missed the low
| power mobile processor market and may never even achieve a
| foothold.
| ThrowawayB7 wrote:
| > " _Microsoft missed the arrival of the web._ "
|
| How did Microsoft miss the arrival of the web and have the
| dominant web browser for years?
|
| > " _Microsoft also missed the mobile revolution and ended up
| with zero mobile operating system market share._ "
|
| That's kind of disrespectful to the competitors who duked it
| out during the pre-iPhone phase of the mobile revolution.
| Microsoft competed with and defeated Palm Computing, the market
| leader, and others in the marketplace to become the top dog in
| PDAs and smartphones around the release of Windows Mobile 5 and
| 6. They didn't "miss" anything.
|
| Apple, to their credit, managed to hit the right combination of
| timing and consumer appeal that they swept everyone away,
| Microsoft, Blackberry (remember them?), and what was left of
| Palm. The iPhone would probably have killed Palm even if they'd
| managed to fend of Microsoft.
| andrewstuart wrote:
| >> How did Microsoft miss the arrival of the web and have the
| leading web browser for years?
|
| That's a well known part of computing history.
| https://www.inc-aus.com/tess-townsend/what-bill-gates-got-
| wr...
| sethbannon wrote:
| I was able to see LaMDA in action about 1.5 years ago. It was
| just as awe-inducing as ChatGPT. Google is not behind in this
| race. They're simply slower to roll out new functionality. And
| maybe rightly so? Some of the things I saw ChatGPT say would
| have been multi-day international bad headlines for Google, if
| a Google AI had said them instead of an upstart startup.
| cuteboy19 wrote:
| They should have had the courage to weather through that
| noise. Or do something like Microsoft and acquire after
| release. These are just excuses tbh
| joshuamorton wrote:
| Acquire _what_ after release?
|
| The point GP is making is that Google's technology has been
| (at least to a non-expert) on-par with the external things.
| Why would they acquire something they already have?
| cuteboy19 wrote:
| My point was that this public relations issue could have
| been easily solved. A tech first company can easily get
| PR to solve it. That they didn't implies they they are
| past their prime. This is Xerox-Apple thing again
| warning26 wrote:
| _> We're releasing it initially with our lightweight model
| version of LaMDA. This much smaller model requires significantly
| less computing power, enabling us to scale to more users,
| allowing for more feedback_
|
| Interesting; I wonder if their use of the "lightweight" model
| will make it less capable than ChatGPT.
| minimaxir wrote:
| Given that Google/DeepMind is one of the few labs actually
| trying to make smaller models that are just as performant (e.g.
| Chinchilla: https://arxiv.org/pdf/2203.15556.pdf ), I'm
| optimistic.
| renewiltord wrote:
| OpenAI: Actually usable
|
| Google: We'll let you use it. We have it. Honest
|
| Meta: Ours is so good. It's better than anything. It honestly is
| the best. No you can't see it
|
| So much for all those "What's so open about OpenAI" people. This
| is what's open about it. Anyone can use it.
| kypro wrote:
| Assuming this is as good as ChatGPT it's interesting that they
| have had this up their sleeves but decided not to release it - I
| wonder why?
|
| I've heard a lot of people comment about how only a private tech
| startup like OpenAI could realistically have released something
| like ChatGPT today, because ChatGPT requires a huge amount of
| capital to build (and run) and provides some fairly controversial
| answers which public investors might not like.
|
| I suppose it's interesting that Google seems to disagree with
| this. Although the "lightweight model version" line makes me
| suspect this is a slightly different system and perhaps more
| easily sandboxed than ChatGPT.
| influx wrote:
| It's challenging to take a CEO seriously who lacks enough self-
| awareness to un-ironically use the term "journey".
|
| Similarly, just open it up for everyone to use, I'm using ChatGPT
| now, ship your product, don't just write a blog post about it.
| [deleted]
| lern_too_spel wrote:
| It was probably written by Bard. Lack of self awareness is to
| be expected.
| [deleted]
| smoldesu wrote:
| ChatGPT didn't just "exist" one day. OpenAI made a half-dozen
| models before getting to GPT-3, and even had demos like Talk to
| Transformer freely available for anyone to play with _long_
| before ChatGPT was in development.
|
| Just because you didn't hear about it until the news got there
| doesn't mean it's not a journey.
| biomcgary wrote:
| Would you consider Google to be mid-journey?
| smoldesu wrote:
| Sure, I think that's a fair characterization. They have AI-
| accelerated hardware in client and server-side devices now,
| as well as a decent catalog of AI-powered demos and
| features.
|
| They're not exactly a leading force in the AI world, but
| they're dedicated to making the pilgrimage all the same.
| gundmc wrote:
| If Google isn't a "leading force in the AI world", who
| would you consider to be the leading forces?
| smoldesu wrote:
| Probably Nvidia and OpenAI, at the moment. Everyone else
| seems to be following in their footsteps, or putting
| together the pieces those companies commercialized.
| booleandilemma wrote:
| That would be Midjourney: https://midjourney.com
| brap wrote:
| I'm curious to hear why Google isn't going to win in this AI arms
| race.
|
| The way I see it, Google:
|
| * is effectively the gateway to the internet, owning the most
| popular website in the world, mobile OS, and browser
|
| * has infinite _LIVE_ data, both unstructured and structured
| (knowledge graph)
|
| * has infinite compute resources
|
| * employs the world's best AI scientists and invests heavily in
| AI
|
| * has decade(s) of experience in AI products
|
| * has one of the most popular suit of apps already in people's
| hands (gmail, calendar, maps, docs, YT, drive, wallet, photos etc
| etc)
|
| * is a popular cloud provider (which is another vector, ie
| platformizing AI)
|
| * has infinite money
|
| * is probably the most well positioned company to actually
| monetize AI
|
| Honestly I don't see why HN seems to think it's over for Google.
| Outside of tech, most people have never heard of ChatGPT or Bing.
| Everyone on the planet knows Google.
| CDRdude wrote:
| Couldn't you write something similar about IBM and early
| personal computers?
| Patrol8394 wrote:
| ... and yet a good chunk of their revenues is driven by ads. On
| the other hand Microsoft can deploy ChatGPT tech in all their
| enterprise products.
|
| Google does have the means and knowledge, but they are not as
| good at monetizing them. See also the cloud space and Google
| Cloud vs Azure.
| brokencode wrote:
| I do agree that Google search AI will most likely win against
| Bing search AI due to brand recognition and resources.
|
| But I also think that Microsoft will be a huge winner for
| enterprise software. They are already integrating GPT into
| Teams, and no doubt they plan to integrate it into pretty much
| everything they can think of.
|
| I hope we will see a lot of independent startups making
| innovative AI products as well. This space has incredible
| potential, and there could be many winners.
| dpflan wrote:
| I also think Google is well resourced/positioned. Though, I am
| wondering: what does winning the AI arms race mean? The AI
| needs to be in some useful products/services?
|
| Perhaps it creates specialization for the "internet gateways",
| where the dominant companies for each major type of internet
| gateway entrench themselves further?
|
| - Meta (FB) as the social door, with more useful AI for
| socializing?
|
| - Microsoft is the document app door, with more useful AI for
| creating documents?
|
| - ...
| sshnuke wrote:
| You could make a similar argument about companies with
| "infinite" resources that reached the highest peaks of
| technology at the moment and nowadays are mostly irrelevant:
| IBM, Xerox, Nokia, Blackberry, Yahoo... Maybe the question is,
| why do you think Google is different from these companies?
| [deleted]
| mrbungie wrote:
| Ozymandias. There have been large and powerful corporations
| (with supposedly """infinite""" resources) like the East India
| Company that eventually transformed into no more than dust and
| rubble.
|
| I think the same is going to happen with Google (in due time,
| maybe 100 years), mainly because its product management is
| completely out of focus due to mismanagement and lack of a
| proper incentive structure.
| jpeter wrote:
| Because they are to scared to release a public version of their
| AI
| alooPotato wrote:
| One possibility is that they get sued by 1000's of companies
| for "stealing their knowledge". Bogged down in the courts
| forever a la MS antitrust. Even though all the other LLM
| services will be indexing the same data, Google will be the
| ones that bear the brunt of the lawsuits because they are a
| rich target. Kind of like the Yelp lawsuit but on steroids.
| twosdai wrote:
| To add some noise, and my own opinion which had literally no
| weight.
|
| I think Google's ties to ads is the evil which creates the
| infinite money and computer and ai scientists etc.. however
| it's an extreamly negative part of their product suite for the
| end consumers.
|
| If ads eat the rest of the business faster than they can
| deliver killer features which make them too good to leave then
| I think google will be doomed.
|
| If their ads remain in check with their ability to provide
| great product expiernces then it will likely survive.
|
| I'm optimistic that Google will do well.
| jjcon wrote:
| That may all be the case but then why has Google been failing
| to innovate and also maintain anything the past few years?
|
| The past fews years we've seen Google products die and
| deteriorate. Search has gotten worse, they've killed dozens of
| products and services (even ones that they promised would be
| around for the long haul). GPhotos is no longer free (after
| putting most competitors out of business).
|
| Google lack any institutional commitment and consistency to
| succeed at much these days. One only need to look at their
| recent past to see why everyone is skeptical. Maybe they will
| pull a rabbit from their hat but I'm not holding my breath.
|
| That is all not to mention the pending real antitrust issues
| they are facing.
| camgunz wrote:
| I'm still salty about Google Reader, but they've innovated
| (Bard is the subject in the Op and a pretty big AI
| innovation) and maintained (Gmail, Docs, Chrome, Golang,
| Android) a bunch of stuff.
| dougmwne wrote:
| Search is so very bad. I tried to figure out what the largest
| MicroSD card was and was served ads and real results to buy
| fake 2tb cards from Amazon. Several searches were useless
| packed with ads and SEO spam. Only Reddit could tell me that
| the largest currently available card is 1tb.
|
| It left me pretty shocked at how bad it's gotten.
| indeedmug wrote:
| I looked up "largest available microsd" and the first item
| was a pop up box that said the largest available one is
| 1TB. I put the same query into bing and the result as the
| same.
|
| That's not to say that happen to you didn't happen.
| Information on the internet evolves rapidly and far from
| static. One problem is that people game Google with SEO. We
| end up with an arms race of people gaming signaling for
| information and Google search having to find different
| signals for information. The high noise to signal ratio is
| a very hard problem to solve.
| dougmwne wrote:
| That's entertaining, because I just tried your query. I
| got this from the Google curated info, all of which is
| wrong:
|
| (Summarizing) People also ask
|
| What's the largest MicroSD card you can get? 256gb
| (wrong)
|
| Will there be a 2tb card? Yes (press release of company
| I've never heard of that I'm pretty sure is not legit.)
|
| What the largest card you can get? 512gb with 1 and 2 on
| the horizon. (Out of date and also wrong, no legit
| company has announced a 2tb)
|
| Who makes a 2tb card? (List of companies that are
| scammers and make fake cards.)
|
| Do 1tb cards work? All 1tb cards are fake (wrong or out
| of date)
| julianeon wrote:
| I also don't understand why everyone is sure that "search is
| over" because you can ask AI to teach you, for example, first
| semester calculus.
|
| That's great and all but that's not where the money is. Where
| is the money? It's in queries like "greek food near me", "best
| earbuds 2023", "replace sparkplug Honda motorcycle." Simple,
| monetizable questions that are extremely context dependent and
| constantly changing.
|
| For that you'll continue to need search.
| TillE wrote:
| But imagine Google takes that query, does the search, then
| feeds the search results into an LLM and gets it to
| synthesize all that information.
|
| Basically, what if Google's little info boxes weren't
| garbage? That alone would be a huge step, without even
| getting into potentially more sophisticated ways to use an
| LLM.
| aliqot wrote:
| This is an interesting take that I also share to an extent,
| however there is a catch, it depends on Google's ability to
| sustain an offshoot product, which as time has shown despite
| endless amounts of money and talent, they're unable to do.
| [deleted]
| minimaxir wrote:
| Google plz give me access to QA Bard.
|
| I promise I will not break it _too_ hard.
| Octokiddie wrote:
| > Beyond our own products, we think it's important to make it
| easy, safe and scalable for others to benefit from these advances
| by building on top of our best models. Next month, we'll start
| onboarding individual developers, creators and enterprises so
| they can try our Generative Language API, initially powered by
| LaMDA with a range of models to follow. Over time, we intend to
| create a suite of tools and APIs that will make it easy for
| others to build more innovative applications with AI. Having the
| necessary compute power to build reliable and trustworthy AI
| systems is also crucial to startups, and we are excited to help
| scale these efforts through our Google Cloud partnerships with
| Cohere, C3.ai and Anthropic, which was just announced last week.
| Stay tuned for more developer details soon.
|
| I'm not sure how any Google representative can make such a
| statement with a straight face at this point. Google has such an
| abysmal history of pulling the rug out from under third party
| developers (and users) that it seems irresponsible to trust
| Google at this point.
| abledon wrote:
| seems like no english noun is going to left safe from being
| duplicated into having the meaning of some type of software item
| cyrux004 wrote:
| chatGpt summary
|
| >Google has created a new conversational AI service named Bard
| that uses the company's language model, LaMDA, to provide answers
| to user inquiries by drawing on information from the internet. It
| is being made available to trusted testers before a wider release
| in the coming weeks. Google intends to use AI to improve search
| and make it easier for users to find information and insights
| more efficiently. AI-powered features for Google Search will soon
| be rolled out to distill complex information into easy-to-digest
| formats. Additionally, Google is working to make it easier for
| developers to use AI by making the company's best models
| available for use in their projects
| computing wrote:
| In a classic PM fashion, Sundar couldn't resist taking all the
| credit for this launch.
| joshhart wrote:
| Many in the investment community are touting ChatGPT as a
| Google-killer. I don't think it's the case, but I do think the
| expectation is that Sundar will drop everything to personally
| treat it like an existential threat. If it were anyone other
| than Sundar it would appear that he isn't treating it seriously
| enough.
| jacquesm wrote:
| This message reminds me very much of the kind of press release
| that Intel would put out when caught flat-footed by AMD.
| thunkle wrote:
| Is this like chatGPT?
| theonlybutlet wrote:
| seems like Bard will be similar, however judging by its
| omission from being cited as an example, help with coding won't
| live up to that of chatGPT.
| alexb_ wrote:
| >AI can be helpful in these moments, synthesizing insights for
| questions where there's no one right answer. Soon, you'll see AI-
| powered features in Search that distill complex information and
| multiple perspectives into easy-to-digest formats, so you can
| quickly understand the big picture and learn more from the web:
| whether that's seeking out additional perspectives, like blogs
| from people who play both piano and guitar, or going deeper on a
| related topic, like steps to get started as a beginner. These new
| AI features will begin rolling out on Google Search soon.
|
| This is actually really huge. If done right, Google will be
| increasing the amount of "no-click" searches an incredible
| amount. I'm interested to see how good of a job the "factual
| grounding" works - this linked blog post in the article is pretty
| interesting https://ai.googleblog.com/2022/01/lamda-towards-safe-
| grounde...
| toddmorey wrote:
| The skeptic in me can't help but think this experience has been
| designed to keep more people on Google properties longer. It
| feels parasitic.
| throwawayjdjd wrote:
| They make money when you click away from their properties
| sleton38234234 wrote:
| i for one, hope that the AI will mostly stick to analyzing the
| content, rather than search intent because Google has had a
| history of misreading my search intent, quite frequently.
| drcode wrote:
| Yeah what I totally want when I have a nuanced question is an
| AI that just gives me a mealy-mouthed, non-committal response,
| such as in the example for this post on whether guitar or piano
| is easier to learn.
|
| If you asked your friend, who's a serious musician, and they
| gave this kind of couched answer, you would be really annoyed
| at them.
| dougmwne wrote:
| That could be incredibly dangerous for their Adsense revenue.
| cwillu wrote:
| The missed innovation is always a threat to the core
| business, that's the trap.
| elorant wrote:
| I like that, and that's the one thing I enjoy most about
| ChatGPT, but the problem with this scenario is that it breaks
| the web. If a search engine can give me all the answers I want,
| then there's no point in visiting sites anymore, aside for
| e-commerce. So if you have a site you wouldn't want the next AI
| search engine to crawl your content because you get no traffic
| back. So either they find a way to give traffic back, or soon
| enough there will be no content to provide through an AI search
| engine.
| visarga wrote:
| What traffic are you getting back from commenting on HN. If
| you're not getting any, why are you wasting your time? Of
| course you can post online for other reasons, like
| participating in a debate, building a community, working on a
| project, or just for hobby. And usually that's the good part
| of the web. Otherwise why would people be using
| site:reddit.com in their searches.
| elorant wrote:
| Getting on HN doesn't cost me a dime though, aside from
| spending personal time. Having a web site costs money both
| to maintain the hardware, and the content. And if someone
| wants to index the content he should give me back traffic.
| That's the premise upon which search engines were build.
| You break that, we end-up with a walled off garden that
| handles all the information.
| pastor_bob wrote:
| Companies will have to start opening up their wallets to pay
| for their "Bard-Rank"
|
| BULLISH for GOOGL
| volkk wrote:
| i wonder what kind of downstream effects on the ad click
| industry this will have. would kill for it all to die and be
| reinvented in a different, more personalizable and clever way
| layer8 wrote:
| People will still visit websites that provide entertainment,
| social media, shopping, services, web applications, source
| material, porn, etc. Enough opportunity for clickable ads.
| volkk wrote:
| isn't the vast majority of ad market surfaced via google?
| CabSauce wrote:
| That's good for users, potentially. But not good for the sites
| where google is sourcing the information.
| [deleted]
| armchairhacker wrote:
| I'd rather get my information without having to click on a
| site. I get the need for attribution but Google can cite the
| sources it gets it's content from, and I don't really care
| about losing ad money.
|
| But another issue is accuracy. Of course real sites aren't
| always accurate, but they're way more reliable than AI (and
| sometimes the site is ground truth like official docs so it
| _can_ be trusted...unless...the official docs are wrong....).
| woeirua wrote:
| Customers may not care, but content producers absolutely
| will. Chatbot like interfaces that lead to "no-click"
| searches are going to get sued out of existence, OR are
| going to lead to the establishment of lots of paywalls that
| lead the chatbot to have blindspots about information
| behind them.
| visarga wrote:
| News sites can reword information from other news sites,
| AI can train on reworded web text. It will keep the
| information but not learn the exact original expression,
| as it should be. Copyright protects expression, not
| ideas.
| echelon wrote:
| The web was a stepping stone.
| jjeaff wrote:
| Potentially good for users initially. But I can't see how
| anyone will be incentivized to create and post content for
| Google to scrape if they won't have any traffic from Google.
|
| It could actually be a huge benefit in some ways if it chokes
| out the content mills. However, something tells me that they
| have little to no overhead compared to the people who
| actually toil away to post good, original content.
| moffkalast wrote:
| This may actually be fantastic for the web. The current
| incentives are terrible anyway: cheat, scam and SEO your
| way to the first search result page and then do whatever
| since you'll get visits and decent ad revenue regardless of
| content.
|
| Most people that make good content don't make it for money
| anyway. Did people back in the pre-google days think "oh
| I'd make this site but gosh darn there's nobody to pay me
| for it". They just went and made the site regardless.
| rchaud wrote:
| > Did people back in the pre-google days think "oh I'd
| make this site but gosh darn there's nobody to pay me for
| it".
|
| Google is a huge part of the reason the old web doesn't
| exist anymore. Artisanal websites cannot compete for
| visibility against corporate websites that have staff
| dedicated to figuring out SEO tricks from every
| imaginable source: page speed, HTTPS, image compression,
| meta tags.
|
| The hobbyist back then didn't need to know all this.
| Today, not having HTTPS alone can cause your site to be
| hidden from search, even if it is read-only. In that kind
| of world, only the infinitesimally small minority will
| bother to make a website on their own dime.
| moffkalast wrote:
| I don't see why SSL is that much of an issue these days.
| Cloudflare does it for free, lots of hosting providers
| can handle let's encrypt for you.
| bnralt wrote:
| > But I can't see how anyone will be incentivized to create
| and post content for Google to scrape if they won't have
| any traffic from Google.
|
| The problem right now is that the incentives have caused
| most of the output online to be garbage.
| nabakin wrote:
| Exactly. If Google is able to provide better answers than
| the garbage websites with their SEO hacks, those garbage
| websites will not get clicks. I could see this improving
| the incentive system significantly
| [deleted]
| daveidol wrote:
| That's one of the big problems with these types of AI -
| piggybacking on everyone else's work, typically with no
| attribution _whatsoever_.
| kerpotgh wrote:
| Google brings visitors to your site for free or no one
| would find it in the first place. You can always robot opt
| out and then your information is "secure".
| amelius wrote:
| Yet you better cooperate otherwise you won't get any
| visitors at all.
| visarga wrote:
| Nobody owes you visitors.
| talhof8 wrote:
| Where's the link though?
| mrkramer wrote:
| I don't expect much from Bard but we shall see.
|
| For few weeks now I had a thought experiment of creating a LLM
| search engine trained on books. Such LLM search engine would be
| most reliable if you seek knowledge but as other mention if you
| want up to date information search engine is probably your
| fastest and easiest way to go. But actually I wonder and somewhat
| doubt that data, information and knowledge in books is lagging
| significantly behind Web's data, information and knowledge. One
| big advantage of books is that they are more reliable and more in
| depth source of information and knowledge than some random site,
| blog or Wikipedia article. Scientific research papers also come
| to mind as a highly reliable source of information and knowledge.
| beoberha wrote:
| I'll admit I don't know a ton about stage of the art AI
| techniques (just a couple grad level AI courses in college), but
| one of the things I don't love about ChatGPT is that it doesn't
| really "know" things and essentially just word vomits based on
| probabilities. This manifests in it often getting things wrong,
| though I would argue it was never intended to answer questions
| with any level of detail. I feel like a killer application of
| LLMs would be to wrap a knowledge graph similar to what Google
| has already. Hopefully that's what they did with LAMDA.
| dauertewigkeit wrote:
| Good news for us in the field. I hope the ramp up hiring as the
| competition heats up.
| VLM wrote:
| "a high bar for quality, safety and groundedness"
|
| This sounds like its going to be cringy. Not a guarantee and I
| hope not, but it sounds bad.
| techn00 wrote:
| "But increasingly, people are turning to Google for deeper
| insights and understanding"
|
| I'm just trying to just get relevant results for my query man ...
| nblgbg wrote:
| My standard habbit when I don't find what I want is to append
| site:reddit.com site:news.ycombinator.com site:github.com
| site:stackoverflow.com. Mostly I get what I wanted!
| carom wrote:
| Which is funny because those results get us human insight
| into our topics. Most top results now are completely non-
| sensical SEO generated word dumps. Google's search engine
| rating programs have failed beyond belief.
| nblgbg wrote:
| Completely agree, most of the search results are SEO
| generated. Lets imagine what happens in near future with
| ChatGPT ?
| olivierduval wrote:
| Yeah... instead of trying to give more false results with AI,
| Google should first try to get good result with just simple
| search (and give me back my booleans operators!!!!)
| oldgradstudent wrote:
| In recent years I have to use quotes much more aggressively and
| use verbatim search almost all the time.
|
| Google is getting less and less helpful.
| dwighttk wrote:
| Do quotation marks do anything for you?
| frozenlettuce wrote:
| unless you are searching for recipes that include a fake intro
| about the author's childhoold in Alabama
| [deleted]
| dwighttk wrote:
| "But increasingly, people are turning to Google for deeper
| insights and understanding"
|
| Neither of which are provided by AI
| gpt5 wrote:
| Translation: I received a lot of pressure from investors and
| Larry/Sergey, so I had to rush out an internal competitor to
| ChatGPT.
|
| It's not going to be as good as ChatGPT initially, so I'm
| excusing it ahead by saying that we are using a smaller model
| than what we really have, in order to make it available to more
| users. However, we are really making it available only to a small
| group of users, because we need to control the bad PR.
|
| But hey, our dataset is more fresh than ChatGPT, so it can answer
| a JWST question!
| muchospandas wrote:
| The tech behind Bard was announced before ChatGPT, so I doubt
| this is reactive.
|
| I mean the statement is, not Bard itself.
| cube2222 wrote:
| Time will tell (a few weeks, according to the article) if it's
| any good, as that's when it will be released to the public.
|
| However, an interesting piece of info was
|
| > It draws on information from the web to provide fresh, high-
| quality responses.
|
| which seems like it will possibly be able to use some kind of
| external repository of information, instead of needing to be
| retrained? Very curious about that.
| layer8 wrote:
| It may works similarly to https://labs.kagi.com/ai/sum, just
| based on the first couple of Google hits instead of a single
| page.
| bjterry wrote:
| Perplexity.ai processes Bing search results through GPT-3. It
| works really well, and you can see the prompt they use at
| https://blog.ouseful.info/2022/12/09/combing-chatgpt-and-sea...
| leodriesch wrote:
| Perhaps it won't take information from the training data but
| rather take the content from the pages a regular search would
| return and convert it to a nice answer to your query.
|
| This seems to be the approach https://www.perplexity.ai/ is
| taking.
| karmasimida wrote:
| So is 10B for OpenAI still worthy it?
| borland wrote:
| Tech Pundits: ZOMG ChatGPT is going to make Google Obsolete
| tomorrow even though it makes up false answers constantly.
|
| Google Investors who know nothing about tech: Hey Google. Why U
| No AI?
|
| Stock Market: Google
|
| Google: Look we have some bullshit AI too! Don't forget about how
| smart we are!
|
| Stock Market: Google
|
| That's the entire point of this article, particularly why it's
| written by the CEO.
|
| Will they actually have any decent AI? Who cares!
| neosat wrote:
| The blog post is an example of why when you go through a number
| of edits and additions from various internal groups, marketing,
| legal, compliance etc. you end up with a message that's a lot of
| words but not a lot of information for any key audience.
|
| I went through the article 3 times thinking I missed the link to
| try out Bard, get some sense of timeline, roll-out
| plan...nothing. Come on Google...
| aantix wrote:
| Have you ever tried utilize one of their APIs..?
|
| It's an atrocious experience. They're leaving so much money on
| the table.
| verelo wrote:
| Also good luck signing up and making your first API call.
|
| OpenAI made that very easy, Google no doubt will make it a
| total pain.
| dbish wrote:
| Having worked in big tech for a while, my written-by-a-
| committee alert went off quickly for this. Founders are the
| only ones who seem to get away without doing this when running
| large companies. Personality and substance are very important
| for communication and committees (and the folks who want to
| edit as part of one) never get that right.
| blihp wrote:
| It's corporate-speak for 'we're not letting the threat going
| unanswered' without actually delivering anything yet. It's
| mostly a placeholder for shareholders and especially the media
| to move the story away from 'Google's in trouble'
| [deleted]
| jillesvangurp wrote:
| Exactly, he announced that they are doing a thing. With a very
| ambiguous screenshot of the thing and zero evidence of just how
| good the thing is. And no link to the actual thing.
|
| So, the thing doesn't exist yet in a form that is concrete or
| demoable. And it definitely isn't ready for users. Which is the
| same thing really. Also there's no timeline of the thing
| actually getting there either. So, there's nothing here really.
|
| Why is Sundar Pichai still in charge of this company? Months of
| excitement around chat gpt and then the best he came up with is
| this?! This reads to me like "The dog ate my homework, sorry. I
| have nothing of substance to announce today. Or tomorrow. Or
| any time soon.".
|
| Also, Bard. Really?! Cringeworthy doesn't begin to describe how
| bad that is as a brand name. It' sounds like Bad spelled wrong.
| [deleted]
| rom-antics wrote:
| It seems like a very reactionary move. ChatGPT went viral, and
| now they have to rush something to market to try and compete.
| So of course the product doesn't exist yet, but they've had
| enough time to put together a project plan and some mockups.
| It's not a great position to be in.
| anotheryou wrote:
| Exactly. With their partner Anthropic's bot "Claude" they
| have something on the same level as ChatGTP already though.
|
| You can test Claude on ios with the app "poe" (the other two
| bots in the app are some sort of chatGTP and OpenAI based).
| quanticle wrote:
| Google was in this position in relation to Apple and the
| iPhone, and that worked out all right for them. First-mover
| advantage isn't the be-all, end-all.
| hn_throwaway_99 wrote:
| I think the real fear is that there has been a brain drain
| of high-level AI talent to well-funded startups because
| those startups can move faster without having the extreme
| fear/caution of a large company like Google/Facebook. E.g.
| my guess is that OpenAI doesn't have an "Ethical AI" team
| who sees their role as primarily to put up roadblocks to
| releasing.
|
| Hence not surprised by the big investment in Anthropic by
| Google.
| neosat wrote:
| There was a different dynamic there. Apple was clearly
| focussed on the higher end of the market (price point) and
| unwilling to compromise on profit margins, while willing to
| sacrifice pure market share. Google took advantage of that
| to win the distribution space focussing on lower price
| point phones on Android (and then expanding to higher price
| point devices).
|
| With ChatGPT the threat is different and both are going
| after expanding usage.
| c7b wrote:
| It is a bit surprising that Google got scooped by OpenAI, but
| the product surely has existed before ChatGPT went public.
| LaMDA was the model behind the 'Our AI has become sentient'
| controversy last year, if you remember that [0].
|
| [0] https://www.washingtonpost.com/technology/2022/06/11/goog
| le-...
| behnamoh wrote:
| I don't think so. Google has had its own internal LLMs for
| quite some time now. Some of them are even more powerful than
| GPT 3.5. The only question has been: "Why release it to the
| public?"
| cmrdporcupine wrote:
| Exactly. I played with "Meena" when I was an employee there
| and it was ... disturbingly human-like. I can understand
| why Google didn't want to release it. And even more so
| after the Blake Lemoine incident.
|
| Google is already accused of operating a panopticon, the
| last thing they want to be accused of is running SkyNet.
|
| People who think Google has fallen behind here are sorely
| mistaken. They just don't/haven't-had a way to make money
| off of it and are likely worried about reputational
| fallout.
|
| I want Google's lunch to get eaten as much as the next guy,
| but I don't think it will be on this front.
| cmrdporcupine wrote:
| It's not rushed to market. It already existed for years.
|
| I've tried to say this before elsewhere, but Google has had
| something internally that's competitive with ChatGPT already
| for years, under various names. They were just naturally
| reticent about letting it loose on the world. Esp after the
| Blake Lemoine incident.
| make3 wrote:
| as someone who did nlp research at Google, Google had a
| ChatGPT level chatbot 3 years ago and did nothing with it
| sbazerque wrote:
| This sounds a bit like those stories about Kodak having a
| digital camera before anybody else did, and they just
| fearfully watched the thing from a distance doing nuthing
| until someone else brought it to market and ended the party
| for them.
|
| May be an entirely different thing this time of course. But
| still...
| make3 wrote:
| Well they had a giant conversational size bigger than
| GPT3. It was not as safe or good at following
| instructions as ChatGPT. But it was as flowing as it is.
| So maybe it's an exaggeration (this word has two gs in
| english!?) to say that it's as good, but it was also
| extremely strong and impressive
| MichaelZuo wrote:
| It does seem slightly amateurish. If there was more self-
| confidence like Apple, there wouldn't be a need to announce
| anything until it's ready.
|
| EDIT: Especially if it was already available internally for
| several months as some others say, waiting another month or
| two until it's ready to go doesn't seem like a big burden.
| LesZedCB wrote:
| i don't think anybody knows how to monetize it.
|
| really it's kinda a public service, maybe these models should
| be run that way?
| CyanBird wrote:
| Just picture monetizing it via embedding slant onto the
| answers it provides like how Alexa suggest purchases but in
| a way that users can barely just notice...
|
| Or purchasing "market share space" on it in the same way
| that companies buy shelf space on supermarkets to place
| their products in...
| [deleted]
| jjeaff wrote:
| Monetization seems pretty straight forward.
|
| User: What is the most durable shoe?
|
| AI: Some of the most durable shoes are ... Here are some
| affiliate links where you can buy these durable shoes...
| [deleted]
| dbish wrote:
| It reminds me of a blander Yann Lecun-like response where he
| responded on Twitter to a bunch of people saying Facebook ai
| could have done this and that, without acknowledging they
| were beat to the (shipping) punch and are now just reacting.
| Building a roadmap on what is in the zeitgeist and trying to
| pretend you're winning a fight you don't realize you already
| lost (at least the first battle) is not a way to capture
| mindshare imho
| hn_throwaway_99 wrote:
| What are you referring to? My overall impression of Yann
| Lecun is he feels quite hamstrung by all the extreme
| caution at Facebook (which obviously exists at Google too)
| of releasing anything that could produce content that is in
| any way objectionable to one of a million different
| subgroups.
| dbish wrote:
| I like Yann and think he's brilliant and also generally
| appreciate how he engages on Twitter. However, he spent a
| lot of time recently downplaying openai and I don't see
| why that was needed other then to try to say FAIR is
| important, see one of the most recent of these related
| tweets
| https://twitter.com/ylecun/status/1620533783702433792
| ddalex wrote:
| It is a reactionary move, but Bard existed for months on the
| intranet, but not as a public offering. So they have the
| technology but not the product.
| qbasic_forever wrote:
| Presumably this was the infamous tech that got that one
| worker fired because he thought it was sentient and wanted
| to blow the whistle on unethical AI treatment right? This
| story: https://www.cnn.com/2022/07/23/business/google-ai-
| engineer-f...
|
| It would be funny if Google hastily rehires him as a
| marketing evangelist to show people their AI is so good you
| think it's alive.
| CobrastanJorji wrote:
| In one sense, yes, but to me that felt more like a mental
| illness story than anything else, which would make it
| much less funny (apologies to the person involved if it
| was not).
| optimalsolver wrote:
| While I don't think LaMDA is sentient (merely based on
| what I understand about its architecture), what would it
| look like if some mega corp had a conscious AI on its
| hands, and an insider was trying to blow the whistle?
|
| Wouldn't it look exactly like this?
| charlesma wrote:
| They've been doing internal testing for while, but I guess
| they never thought to release it publically until chat GPT
| became public.
|
| There was even someone who thought it was sentient!
| https://www.cnn.com/2022/07/23/business/google-ai-
| engineer-f...
| blobbers wrote:
| Still can't find the link.
| MrGilbert wrote:
| Maybe the Bard announcement was written by Bard?
| ribosometronome wrote:
| Out of curiosity, I copied all the text from the website (so
| it got header, footer, unrelated text) into ChatGPT and asked
| it to summarize:
|
| This is an article written by the CEO of Google and Alphabet,
| Sundar Pichai, about the company's journey with Artificial
| Intelligence (AI). Pichai discusses how the company has been
| working on AI for the past six years and how they have been
| advancing the state of the art in the field. The article
| mentions the release of an experimental conversational AI
| service called Bard, which seeks to combine the breadth of
| the world's knowledge with the power and intelligence of
| Google's large language models. The CEO also talks about how
| the company is working on bringing the benefits of AI into
| its everyday products, starting with Search, and how AI can
| deepen people's understanding of information and turn it into
| useful knowledge more efficiently.
| giarc wrote:
| "making it more widely available to the public in the coming
| weeks."
| warent wrote:
| Got you:
| https://labs.kagi.com/ai/sum?url=https://blog.google/technol...
| Sundar Pichai, CEO of Google and Alphabet, has announced the
| release of Bard, an experimental conversational AI service
| powered by Google's Language Model for Dialogue Applications
| (LaMDA). Bard seeks to combine the breadth of the world's
| knowledge with the power, intelligence and creativity of
| Google's large language models. It draws on information from
| the web to provide fresh, high-quality responses. Bard is
| initially being released with a lightweight model version of
| LaMDA, which requires significantly less computing power and
| will allow for more feedback. Google is also working to bring
| its latest AI advancements into its products, starting with
| Search, and will soon be onboarding individual developers,
| creators and enterprises to try its Generative Language API.
| Google is committed to developing AI responsibly and will
| continue to be bold with innovation and responsible in its
| approach.
| KennyFromIT wrote:
| Wow, thank you for that link. Now I have a new bookmarklet...
|
| javascript:location.href='https://labs.kagi.com/ai/sum?url='+
| encodeURIComponent(locati...
| nickstinemates wrote:
| Formatting is a little messed up, but great idea here.
| oars wrote:
| Thanks for the bookmarklet!
| warent wrote:
| They probably launched this for free as marketing to
| increase visibility into their startup! Enjoy it while it
| lasts before the service is paywalled
|
| Note I've been using Kagi happily for several months and it
| has successfully replaced Google Search for me. Highly
| recommended.
| dougmwne wrote:
| There is nothing concrete available today because Google is
| scrambling to get ahead of a major announcement from Microsoft
| on integrating GPT into Bing. Internal sources from MS are
| saying it might be the first we see of GPT-4.
| enneff wrote:
| Why do you say google is scrambling when they have been
| working on AI stuff just as impressive as OpenAI, which you
| could spin differently to say Microsoft "scrambled" to make a
| partnership with and are now attempting to cram GPT into
| their tech stack.
|
| FWIW I don't think either company are really scrambling
| except in the performative sense of making announcements to
| appease the market.
| dougmwne wrote:
| Because while Google has been researching, OpenAI has been
| productizing. We will have to judge it once we get access
| to Bard, but it's possible Google is years behind on
| creating a chat model that won't spew toxic waste, as GPT-3
| did when it was first released a few years ago.
| enneff wrote:
| I work at google and have used their AI tools and they're
| just as impressive as the OpenAI ones (which I use
| personally, outside of work). Both have been developing
| products, just google hasn't released any of them.
| dougmwne wrote:
| Have you done adversarial testing? How easy is it to
| jailbreak Bard vs. ChatGPT? Can Bard produce code?
| enneff wrote:
| Obviously I am unable to discuss the details, as much as
| I might like to. Sorry.
| sidibe wrote:
| Not spewing toxic waste is actually a big part of what
| Google has spent years working on here. The fact that
| someone else released the first such product allows them
| to do it too without solving the problem with less media
| flak.
|
| Productionizing this stuff is where Google gets the most
| advantage because they have the hardware and software
| efficiencies that comes form years of experience training
| and running inference on the most massive AI workloads
| for many many years in their data centers
|
| I don't think this is going to be what damages Google,
| much more optimistic about antitrust stuff.
| enneff wrote:
| Yeah I keep thinking about how different the reception to
| ChatGPT would have been if it were released by Google.
| People would be way more focused on how you can make it
| spout total nonsense with supreme confidence. (Which imo
| is the major flaw in all these ML models.)
| [deleted]
| lolinder wrote:
| Microsoft's partnership with OpenAI is a years-long affair,
| not something they're just starting on now. Google should
| have seen this coming and been able to beat them to
| release, but they seem to have been caught off guard with
| some great research projects but no product.
| enneff wrote:
| Both companies have been doing AI work for a long time.
| Do you really think google is behind on AI here just
| because they haven't released any products? What do they
| stand to gain by pushing out half-baked toys? They have
| nothing to prove.
| lolinder wrote:
| Google isn't Apple. Google's strategy for the last 10
| years at least has been to throw out half baked products
| and see what takes off. If they had anything usable, we
| would know by now.
|
| And, on the contrary, Google has everything to prove.
| ChatGPT exploited a years-long dissatisfaction with
| Google search and has millions of people using it in lieu
| of Google's primary product. This is the most existential
| threat that Google has faced since its birth, and they
| are not handling it well.
| enneff wrote:
| You're living in a fantasy land. If I had a major
| criticism of Google in the past decade it's that they
| don't release early or often enough.
|
| If you think people are dissatisfied with google search
| then you're missing the point that people don't think
| about google search at all, they just reflexively use it
| all day. I don't know anyone who uses chatgpt with such
| frequency or in a way that is so central to their daily
| life, and I have a much more tech-savvy circle of friends
| than most people.
| seaourfreed wrote:
| Or maybe they had ChatGPT write their blog post. ha ha ha...
| ljm wrote:
| Or they asked their new AI to write the post and they got a
| result that sounds amazing but is still total fluff
| sytelus wrote:
| This kind of no information exec-speak is very painful to read.
| I had to pass it through ChatGPT to summarize. THe whole
| article can be summarized in 1 sentence without any loss of
| information: "Google will name it's chatbot Bard and it be
| based on Lambda model, initially small size". No link, no other
| details, basically a lot of words to say nothing at all.
| wilsonnb3 wrote:
| > we're taking another step forward by opening it up to trusted
| testers ahead of making it more widely available to the public
| in the coming weeks.
|
| this is in like the 5th paragraph, right under the 'Introducing
| Bard' title.
| berkle4455 wrote:
| > that's a lot of words but not a lot of information for any
| key audience
|
| So they used ChatGPT to generate it?
| [deleted]
| minimaxir wrote:
| There is an event on Wednesday which will likely provide more
| information.
| htrp wrote:
| If you have to ask, you're not invited.
| bredren wrote:
| It means they are not a "trusted tester."
| [deleted]
| enumjorge wrote:
| We know how well that worked out for Google+
| OnlineGladiator wrote:
| It worked for gmail. Maybe some people are too young to
| remember it was invite-only for years.
| lotsofpulp wrote:
| Gmail was objectively far, far superior than all the
| other competing email offerings, so people wanted to be
| invited.
| mupuff1234 wrote:
| That's because there was no competition and they were the
| first movers.
| bryanlarsen wrote:
| Hotmail preceded gmail by most of a decade.
| thesuperbigfrog wrote:
| I had a Hotmail account for about a year in 2000 or so.
| It had a 10 MB inbox and worked quite well. I got a bit
| of spam, but it was obvious and manageable.
|
| My girlfriend got a GMail invite from a friend and sent
| me an invite. It was huge. A 1 GB inbox, built-in Google
| search of your email, and incredible spam filtering.
|
| They marketed it something like "With GMail, you don't
| have to delete your emails. Just search . . .". Really
| killer features compared to their competitors.
|
| Later on, they added automatic email thread grouping
| which made using Outlook for work a chore until it got a
| similar feature.
| crazysim wrote:
| Not with a 1GB (!!!!!!) inbox.
| MonkeyMalarky wrote:
| Coincidentally also why ChatGPT won.
| [deleted]
| [deleted]
| gundmc wrote:
| For free email? That is patently untrue.
| lotsofpulp wrote:
| No one came close to gmail's 1GB free inbox at the time.
| Which kept increasing and showed you at the bottom of the
| inbox. Plus it had amazing spam detection, and was stupid
| fast, and got better and better very quickly.
|
| I remember having a gmail email was almost a litmus test
| to whether or not you were paying attention to what was
| going on in tech. Not having a gmail email indicated you
| might not be keeping up with the times.
| gundmc wrote:
| Agreed on all your points! But I think offering a better
| service in an established sector is the opposite of "no
| competition" and being a "first mover".
| lotsofpulp wrote:
| Like how we would say a professional sports player
| playing against an amateur has no competition.
| Technically, yes, but effectively...
|
| The context of the discussion is whether or not an
| "invite only" tactic works for building hype and
| launching a successful product. In that sense, I would
| attribute Gmail's success not to the "invite only"
| tactic, but to the fact that it was so superior that it
| had no competition.
| ribosometronome wrote:
| I remember asking for an invite on what was probably a
| phpbb.
| jliptzin wrote:
| It was written by ChatGPT
| hammock wrote:
| There is no information to give. This "announcement" is a
| reaction to all the stories about how ChatGPT is going to eat
| Google's lunch. The company needed to do something to defend
| against that in the market - for the sake of its shareholders
| and its advertising revenue.
|
| That said, here is the chatgpt summary I generated:
|
| Google CEO Sundar Pichai announces the release of their
| conversational AI service "Bard," which combines the world's
| knowledge with the company's large language models. Bard seeks
| to provide fresh, high-quality responses to questions and allow
| users to explore new information. The release is part of
| Google's effort to bring the benefits of AI into everyday
| products and deepen people's understanding of information.
| frozenlettuce wrote:
| I'm still waiting for their appointment registering AI that they
| promised 5 years ago https://www.youtube.com/watch?v=fBVCFcEBKLM
|
| Instead, we got some souless corporate-speak PR spam - and I'm
| sure that if I type "create a product release text for a new AI
| product" on ChatGPT I will surely get something better.
|
| Compared with the comic that introduced Chrome, this feels like
| another company - well, sadly, it is indeed.
| sxp wrote:
| It exists. I tried to book a reservation with a small
| restaurant via Google Maps which didn't have an OpenTable site.
| It called the restaurant and then emailed me a confirmation a
| few minutes later.
| xnx wrote:
| Google Duplex: https://9to5google.com/2022/12/03/google-duplex-
| web-shutting...
| andrewstuart wrote:
| AI needs to pay for its source information.
| woeirua wrote:
| How long before the major news publishers band together and sue
| Google to put a stop to this? It already happened once with
| Google News, and Google's response was to pull article snippets.
| As the number of "no-click" searches increases with Bard the
| publishers are 100% going to sue over lost revenue.
| fnikacevic wrote:
| Assuming you can find the sources of the AI response this is a
| game changer.
| loloquwowndueo wrote:
| Won't be long before ads start making their way into answers "you
| want to know how to make popcorn? Try this amazing air frier from
| company X!". The internet is enough of a billboard as it is.
| [deleted]
| skybrian wrote:
| I tried Kagi's summarizer [1], and it's okayish but misses one
| important point:
|
| > Sundar Pichai, CEO of Google and Alphabet, has announced the
| release of Bard, an experimental conversational AI service
| powered by Google's Language Model for Dialogue Applications
| (LaMDA). Bard seeks to combine the breadth of the world's
| knowledge with the power, intelligence and creativity of Google's
| large language models. It draws on information from the web to
| provide fresh, high-quality responses. Bard is initially being
| released with a lightweight model version of LaMDA, which
| requires significantly less computing power and will allow for
| more feedback. Google is also working to bring its latest AI
| advancements into its products, starting with Search, and will
| soon be onboarding individual developers, creators and
| enterprises to try its Generative Language API. Google is
| committed to developing AI responsibly and will continue to be
| bold with innovation and responsible in its approach.
|
| The point missed is that is that they're starting to test Bard
| with "trusted testers," their closed beta program, so it's not
| really "released" yet.
|
| The context is that they had to announce it now because it's
| likely to leak anyway; trying to get outside testers to keep it
| confidential would be difficult and not worth it.
|
| [1] https://labs.kagi.com/ai/sum
| whalesalad wrote:
| Bard is such a funny name. I tried to, no pun intended, google it
| and it autocorrected to brad.
| duckmysick wrote:
| I don't know what to think of it, but I saw it in a comment on
| Hacker News by raesene9 three days ago:
|
| > The way I've come to look at ChatGPT is via a D&D analogy.
|
| > It's like a helpful Bard with 1 rank in all the knowledge
| skills and a good bluff roll.
|
| > It'll give you good answers to a lot of basic queries, but if
| it doesn't know, it'll just make up something and provide that.
|
| https://news.ycombinator.com/item?id=34642666
| sytelus wrote:
| Definitely not a good name. The first similar word that came
| into mind was "lard" and then "retard". Also, looks like they
| will release smaller model to save on compute. This doesn't
| look like a good strategy. They need to come out solid and
| strong over competition, not watered down.
| aftergibson wrote:
| Should've named it brad.
| bradleykingz wrote:
| A bard is something along the lines of a "poet" or "musician".
|
| More concisely, it's someone that's good with words.
| unity1001 wrote:
| Its a nice name but also a bit grandiose. They would need to
| make the final product good enough to back up the grandoiose
| name that they chose.
| GrantS wrote:
| Possibly a reference to the 1956 Isaac Asimov short story
| "Someday": https://en.wikipedia.org/wiki/Someday_(short_story)
|
| "The story concerns a pair of boys who dismantle and upgrade an
| old Bard, a child's computer whose sole function is to generate
| random fairy tales. The boys download a book about computers
| into the Bard's memory in an attempt to expand its vocabulary,
| but the Bard simply incorporates computers into its standard
| fairy tale repertoire..."
| TillE wrote:
| If you name something Bard, it's at least partly a reference
| to Shakespeare. Also known as The Bard.
|
| What are Shakespeare's works best known for? Language.
| rllearneratwork wrote:
| so, nothing is available right now. Why make this announcement? I
| can play with ChatGPT now, nothing similar from Google yet.
| [deleted]
| doctoboggan wrote:
| > We're releasing it initially with our lightweight model version
| of LaMDA. This much smaller model requires significantly less
| computing power, enabling us to scale to more users, allowing for
| more feedback.
|
| Seems odd to release something worse than the competition. Is
| there a reason why google wouldn't just come out with the best
| the have? Are they afraid this will eat into their ad revenue if
| people no longer need to click on links? Or are they just not
| able to build and deploy something on the scale of OpenAI's GPT3?
| wilsonnb3 wrote:
| > Is there a reason why google wouldn't just come out with the
| best the have?
|
| They literally stated the reason in the sentence you quoted.
| londons_explore wrote:
| Google has so many users that not even they have enough GPU's
| and TPU's to service them all.
|
| I personally think they should use their best models, and just
| make it trigger very rarely. For example, only ~once per week
| per user (ie. 0.3% of queries).
|
| Use a tiny model over the input query to decide if LaMBDA will
| do a far better job than regular search results, and only
| trigger in those cases where it will most benefit the user to
| begin with.
| cma wrote:
| Same reason Gmail/Gdrive wouldn't give everyone 100TB for free
| if a startup came out that did.
| jsnell wrote:
| > Seems odd to release something worse than the competition.
|
| This isn't actually what it says? It's saying that it's a
| smaller model version of Lamda, there's no comparison to GPT-3.
| minimaxir wrote:
| > Is there a reason why google wouldn't just come out with the
| best the have?
|
| Given that ChatGPT has hit scaling issues, a faster model with
| higher uptime is actually now a plus assuming quality is the
| same.
| zaptrem wrote:
| They're likely not willing to stomach suddenly being
| unprofitable again for a few years.
| w0mbat wrote:
| "Everybody else is just copying us. We are miles ahead of our
| competitors who are cheating by shipping actual products instead
| of our ground-breaking vaporware. Our revolutionary AI never
| gives the wrong answer because it never ships."
| meindnoch wrote:
| So, is this going to be the Google+ of large language models?
| gundmc wrote:
| I'm interested in what the "Check It" button at the bottom of the
| generated chat response will do. If that shows information
| attribution this could be huge. I also can't help but notice the
| responses in this article and the linked research blog post seem
| to be much shorter than those given by ChatGPT. I wonder if this
| is a character limit imposed to reduce compute overhead?
| enumjorge wrote:
| > And today, we're [...] opening it up to trusted testers ahead
| of making it more widely available to the public in the coming
| weeks.
|
| It feels like a mistake to make the big announcement for this,
| but not open it up to a wide audience. It's not like ChatGPT
| hasn't been out for months now. Not sure how much they gain by
| making headlines before it's ready for people to play with it.
| nlh wrote:
| Was thinking the same. My hunch is that their PR department
| thinks this will "create a buzz" much like the old waiting list
| for Gmail.
|
| But that feels like slow old thinking. The way you create a
| buzz these days (in the era of limited attention) is by
| releasing a kick-ass product for people to use and play with.
| I'll probably forget about Bard the second I hit submit on this
| comment and go right back to using ChatGPT.
| hnuser123456 wrote:
| Same way they shot themselves in the foot with g+. Maybe they
| know being top of web search and email is already a wide enough
| vertical and offering a dystopian chat AI so soon would be too
| disruptive for them and get too much attention.
| eachro wrote:
| Those trusted tester will likely be their RLHF part of the
| pipeline.
| impulser_ wrote:
| All they have to do it add a link to the front page of Google
| and they will automatically get more users in day than ChatGPT.
| speedgoose wrote:
| I would guess they don't have enough available computing
| resources for that.
| impulser_ wrote:
| Might be the reason why they are choosing to use a
| lightweight version of the model.
| wvenable wrote:
| They failed to learn any lessons from the Google+ launch.
| xiphias2 wrote:
| Google and Facebook had a deal that Google stops doing social
| and Facebook stops doing search.
|
| I don't see the same thing happening between Google and Bing
| HarHarVeryFunny wrote:
| The announcement is probably targeting Wall Street more than
| any potential "user" (aka advertising target). The press was
| already bad - internal "code red" at Google due to panic that
| people saw ChatGPT as an alternative to search.
|
| Meta/FaceBook's head of AI, Yann LeCun, is in similar panic
| mode, issuing a non-stop torrent of tweets about how useless
| and unimpressive ChatGPT has... Presumably a reflection that
| FaceBook does NOT have anything comparable ready to release
| anytime soon.
| smoldesu wrote:
| FWIW, Facebook's AI division has made some pretty insane
| contributions to the field relative to Google or Apple. I
| wouldn't disregard the stuff they're doing, even if I
| personally don't have a stake in Facebook or Meta's success.
| alecco wrote:
| If things keep the current trend, Deepmind, Meta AI, and
| many other remarkable labs will be this generation's Xerox
| PARC.
|
| OpenAI and Stability-AI will be be Apple and Microsoft.
| vagabund wrote:
| Like what? Basically every research breakthrough from
| industry has come through Google.
| smoldesu wrote:
| Facebook was first to the punch on AI photo tagging and
| facial recognition in their systems, but they also did a
| lot of foundational research on GANs and self-supervised
| learning. Plus, they do a lot of other tangential
| research around language and life sciences that might not
| get funded otherwise.
|
| Some of it is marketing bullshit, but Facebook seems to
| have a genuine interest in pushing the field forward.
| Admittedly Google is also not the best example though,
| seeing as they're the Tensorflow maintainers :p
| KeplerBoy wrote:
| Stuff like PyTorch? They're building large parts of the
| infrastructure everyone uses.
| aka878 wrote:
| I don't understand Yann LeCun's reaction considering
| reputation of the company he works for - they should have
| already copied and integrated it somewhere.
| espadrine wrote:
| This may put it into perspective: Yann pushed for and
| released Galactica.org, a website that generated articles
| for any prompt requesting information, on 15 November,
| before the release of ChatGPT. Internal pressure inside
| Meta caused it to shut down three days later, because it
| was thought to risk the company's reputation more than
| Libra and the Metaverse.
|
| The issue isn't that Yann didn't publish an AI app; it is
| that they did, and it was not as good.
|
| The reality is that OpenAI was lucky. Inside the company,
| there is an alignment department whose effort was driven to
| help models share human ethics, and that was initially a
| bit marginalized. However, one of their projects, RLHF,
| ended up producing a much superior language model, when
| they could have initially assumed it would be worse.
| Barrin92 wrote:
| I just hope if they introduce this into search there's a way to
| turn this off and just get the normal search results because as
| it stands these models are basically just Borges Library of Babel
| and make up whatever they want.
|
| The uniform natural language interface makes it impossible to
| make an individual judgement whether the source of what result
| you get is reliable at all.
| asim wrote:
| People forget that Larry Page's ultimate goal was to have Google
| predict what you wanted before you even asked for it. This isn't
| about hype. This isn't about beating the competition. This is
| about delivering on a 3 decade dream that's now coming to
| fruition and Sundar just happens to be the one leading the org as
| it manifests in the real world. We're going to end up with 10+
| vertically integrated AI solutions like this. Google will be core
| infrastructure for the world and this thing will be an assistant
| to everyone who buys into the Google ecosystem.
| sekai wrote:
| > Google will be core infrastructure for the world and this
| thing will be an assistant to everyone who buys into the Google
| ecosystem
|
| Pretty optimistic, considering things Google "delivered" in the
| past 5 to 10 years.
| wiz21c wrote:
| Considering what ChatGPT does with internet knowledge, I'm
| scared to have it trained on my internet history of clicks...
| It will be massively dangerous and totally centralized in so
| few hands...
| lstodd wrote:
| This "core inrastructure for the world" will also be maintained
| about as well as HVAC in the seminal film Brazil
| roody15 wrote:
| Imagine a government controlled AI that partners with mega
| corporations to "assist" AI in getting you the "correct"
| results you desire. Call me a pessimist but we may already be
| staring down the gun of a dystopian future
| CatWChainsaw wrote:
| It was _literally Dune_. Men handed their thinking over to
| machines. That let other men with machines control them. It
| wasn 't even subtle!
| lstodd wrote:
| [flagged]
| serf wrote:
| >Ye, u got a brain no? Go learn some history.
|
| artificial intelligence as a concept is at least as old
| as 300-400BC. Government corruption as a meme goes much
| further back.
|
| I wouldn't be so quick to consider someone 'without
| brain' for having inadequate movie trivia knowledge; nor
| would I consider encyclopedic knowledge of movie trivia
| to be evidence of knowing history.
|
| I don't know where the 'bureaucratic to a fault' concept
| of Brazil was first used, but similarly metaphors and
| complaints can be found in lots of Roman historical
| anecdote, many times older.
|
| These concepts have all been explored in fiction to a
| huge degree, the novelty of what's going on right now is
| that it's been the first time where any of it has
| actually approached reality.
|
| The concept of a government 'on autopilot' is now
| actually being realistically considered, rather than
| humorously/dramatically fantasized.
|
| It's now becoming apparent to the public at large that
| such concepts are stepping out of fiction; that's huge.
|
| tldr; don't fault other people for not knowing about the
| recent revision of ancient ideas and concepts that _YOU_
| prefer to discuss.
| lstodd wrote:
| I do fault people for not knowing shit that was screaming
| in their faces for at least a hundred years and an half.
|
| I do fault them for ignoring it since it's about they did
| understand that this is what was going on.
|
| Do not attempt to whitewash persons as some anonymous
| 'members of public'. A decision to not think is a
| decision none the less.
| criddell wrote:
| Maybe the way Google will know what you want before you ask for
| it is by showing you ads to manufacture demand.
|
| Google wants to serve you
|
| .
|
| to ad buyers.
| theropost wrote:
| I'd love for this to be true. I bought into the Google
| ecosystem in a huge way, but it seems like they have been more
| focused on the data collection, and advertising end of things,
| rather than the innovation, and productivity enablement one.
| Their ecosystem has consitently been a let down in many
| regards, and they have lost a lot of forward momentum. I hope
| they can super charge this stuff, but I feel their corporate
| structure/environment is their biggest hurdle at this point.
| They have capable people, and brilliant minds, but the
| structure of the organization, and them being beholden to their
| market/shareholders gives them little room to innovate in these
| areas. Hopefully the prove me wrong.
| radicaldreamer wrote:
| Similar sentiment here. I look at the state of my android
| phone today and see a company that seems like it got bored of
| building out a mobile platform after they "won" on usage.
| jensensbutton wrote:
| They just brought this extremely innovative thing to market
| in very little time. The problem may have been that they
| haven't really had any competition in their core business to
| push them in a long time.
| dougmwne wrote:
| This thing that no one except those bound by NDA has ever
| tried. I think I'll reserve judgement for just a little bit
| before declaring Bard "extremely innovative."
| layer8 wrote:
| Having all humans as the target audience means that it will
| always be more profitable to make users the product instead
| of making them the customer. This in turn means that
| incentives are not geared towards being in the interest of
| the user.
| JPKab wrote:
| I also want this to be true.
|
| I've just been soul-crushingly disappointed with Google's
| execution over the last few years, particularly the outright
| degradation of so many products (Gmail) or just not keeping
| up with competition (Hangouts is garbage compared to Zoom,
| Sheets still is barely usable, etc), or just screwing over
| users by deactivating features (I used to be able to play a
| youtube video's audio over my Google Home speaker, but they
| long ago removed that ability and I can only play Youtube
| music now).
|
| All of the above are just consumer rants, but let's not
| forget how frighteningly bad the Customer Support or support
| in general is for G Cloud. I WANT to get off of AWS, but
| these clowns at Alphabet have this amazing ability to snatch
| defeat from the jaws of victory with anyone trying out
| GCloud.....
|
| I hope Bard is great..... I want it to be.... but I'm not
| confident it will be.
| btown wrote:
| One thing's for sure - it's much easier to quantitatively
| define an OKR for growing advertising mindshare (especially
| when you operate the exchanges that measure that mindshare!),
| than it is to, say, define an OKR for how a project loosely
| contributes to Google leading the mindshare in the movement
| towards generative AI outputs as they redefine practically
| every job in the world.
|
| And I'm certain that however much Google historically
| stressed that OKRs aren't tied to performance reviews,
| there's a lot of fear that deviating from OKRs could trigger
| one being on the top of the list for the next round of
| layoffs. So there are definitely headwinds that could stifle
| experimentation and innovation in such a brave new world. For
| Google's sake I hope that top leadership is redoubling its
| efforts to get buy-in up and down the management chain for
| redesigning structures to allow innovation to take place.
| JPKab wrote:
| So gross, and so true. I get bouts of nausea every time I
| hear "OKR" now.
| gchokov wrote:
| Sundar did nothing but failed projects. Google is still where
| it was many years ago.
| pphysch wrote:
| My Google phone can instantly translate almost any foreign
| language, embedded in an image, without an internet
| connection. Pretty sure that was not a thing 8 years ago.
|
| If/when Google embeds an (local and/or lightweight) Bard
| model into every Pixel phone, _that_ will be a game-changer.
| pleadthefifth wrote:
| While cool, that's a feature, not a product. Sundar has not
| led the company on any new products that have succeeded.
| The chat apps failed, Meet/Hangouts/whatever lost to Zoom,
| Stadia got cancelled, etc. All their current cash cows made
| their names before him.
|
| At least he didn't oversee the introduction of Google Plus,
| though.
| thehappypm wrote:
| He's leading Google Cloud to strong growth, which is more
| important than something niche but innovative like
| Stadia.
| gchokov wrote:
| That was a feature of google translate _many_ years ago.
| Absolutely nothing new.
| ROTMetro wrote:
| And was came from a purchase of Word Lens not something
| in house if I remember right.
| rippercushions wrote:
| That's WordLens, which Google acquired in 2014, 9 years
| ago.
|
| https://techcrunch.com/2014/05/16/google-has-acquired-
| quest-...
| ekanes wrote:
| Meh. Enthusiasm about Larry Page's ultimate goals and dreams
| went out the window right about the time don't be evil went out
| the window.
| pleadthefifth wrote:
| I think Google was always "evil" however you define that. The
| plan from the start was to focus on the product, build the
| brand, and eventually switch to monetization mode like they
| are now. That's what the slogan meant, think long-term.
|
| The founders still own >50% and make decisions, but the
| employees still act like Larry and Sergey are some founding
| fathers spinning in their graves. "_____ wouldn't have
| happened under them," oh yes it would, and it did.
| rchaud wrote:
| At this point in SV history, harkening back to what a founder
| said as an anonymous PhD in his pre-billionaire 20s, sounds a
| lot like when people talk about "what the Founding Fathers
| wanted".
|
| Nothing is set in stone, and the world is very different from
| the Web 1.0 era in which Google formed.
| par wrote:
| Meh, lot's of corporations have had all kinds of outlandish
| visions. I don't think this one is any more or less aligned
| with any other vision statement from 20+ years ago. They're
| just capitalizing on the technology that's available at the
| time, like any good company should be doing.
| Eduard wrote:
| [flagged]
| dzdt wrote:
| How many parameters?
|
| The LaMDA paper describes 2B, 8B, and 137B parameter variations.
| Sundar says "We're releasing initially with our lightweight model
| version of LaMDA. This much smaller model..."
|
| So it sounds like the 2B or 8B model variations, compared to
| GPT3's 175B. [edit: corrected]
|
| I can't imagine such a smaller model coming across as anything
| near as impressive as ChatGPT.
|
| So the announcement today is for a much smaller, more limited
| thing than ChatGPT and even that is not actually available today
| nor even with an announced release date.
| cypress66 wrote:
| GPT3 is 175B parameters, but I agree with you.
| dzdt wrote:
| Oops. Corrected. Thanks.
| dougmwne wrote:
| Yeah, I think you're onto something here. Clearly we won't know
| till we can use them side by side, but there's lots of hints
| that Google is a ways off from matching ChatGPT. A small model,
| a closed beta, a press release annd mock-up instead of a link,
| chest pounding about how they invented it all anyway.
| rvz wrote:
| But but but 'Google is done', 'it is all over for Google Search',
| 'Google will be dead in 2 years'. /s
|
| Such recent headlines and early proclamations of Google's
| competitiveness in AI have been erroneously under-estimated here.
| As soon as OpenAI announces their AI advancement and model,
| someone else with more money (i.e Google) scales up the
| parameters, training data to surpass them.
|
| The only way to make both of Google and OpenAI's LLM solutions
| irrelevant is for someone else to scale up the parameters with a
| resulting smaller model size and then open source it to all.
| Neither OpenAI or Google is willing to do that, but it is highly
| likely that someone else will.
|
| The real 'disruption' and game changer is an open-source smaller
| model with multi-billion parameters matching the capabilities of
| ChatGPT.
| sshnuke wrote:
| Well, I see a big problem with this release.
|
| Let's imagine a user journey:
|
| User makes a request and then there's text, no ads (for now) no
| links to get you out of search page. So where does Adwords get
| triggered if there are no linked events? Then advertisers will
| see a drop in traffic because Google is literally giving the
| answer instead of making people click to search. This will
| accelerate the cycle of reducing ad spending, which will make
| things more difficult for Search. Then SEO marketers and
| basically all the web industry around Google will see a massive
| impact as well, because they cannot "optimize" anything that
| makes people click. The main problem is the dependency of
| Google on ads (60% of revenue). I see Bard as a negative
| downwards trend that will decimate the company even further.
| ipaddr wrote:
| Google hasn't released anything.. overhyping and under
| delivering so far.
|
| This product if successful initially kills content creators
| reason for creating content and creates this cycle where the ai
| has less information to use and becomes useless.
|
| I would block google if they took content and provided no
| visitors.
| throwaway4233 wrote:
| I do not follow regularly on the ads market and technology around
| it, so I might be asking a question with an obvious answer.
|
| What is changing here as a user for me ? I search on Google for
| `x` or `y` and it shows me a list of resources available on the
| internet. I scour through them and pick a link that relates to
| what I am looking for.
|
| > you'll see AI-powered features in Search that distill complex
| information and multiple perspectives into easy-to-digest
| formats.
|
| How would Google or it's AI know what are the right answers, it
| can distill and provide me with ? Will the crawled content be
| filtered based on what Google perceives to be the right answer ?
| And wouldn't that force governments to ask for more controlling
| power in what content the AI serves ?
| OJFord wrote:
| To me that sounds like an evolution of the cards/widgets that
| show at the top for certain searches.
| sethbannon wrote:
| I was able to see LaMDA in action about 1.5 years ago. It was
| just as awe-inducing as ChatGPT. Google is not behind in this
| race, they're simply slower to roll out new functionality. And
| maybe rightly so? Some of the things I saw ChatGPT say would have
| been multi-day international bad headlines for Google, if a
| Google AI had said them instead of an upstart startup.
| kccqzy wrote:
| There is a phrase called "all publicity is good publicity" in
| fact. It expresses the very real truth that a media outlet
| reporting a bad interaction by Google AI would probably make
| people even more curious to try out the AI. If they get the
| business model nailed down, they should not be afraid of bad
| press.
| Miraste wrote:
| Caution is well and good, but when I look at top selling
| computers there's a conspicuous lack of Xerox branding.
| cypress66 wrote:
| And would have such headlines actually affected them, at the
| end of the day?
| Tepix wrote:
| Hey google, if your model is so lightweight, let me run it!
| zalyh wrote:
| It would be brilliant if Google can pull this off and take
| marketshare away from ChatGPT/OpenAI. Just like how people stuck
| with MS Teams and stopped subscribing to Slack and Zoom. Not
| because it was better, but it was well-integrated users who are
| already subscribed to MS Office 365 gets it for free.
| madspindel wrote:
| This reminds me of when Slack bought a full-page newspaper ad
| about upcoming Microsoft Teams:
| https://www.theverge.com/2016/11/2/13497766/slack-microsoft-...
| college_physics wrote:
| I asked chatGPT "will Meta come up with an accelerated AI journey
| and what direction will it have?"
| pastor_bob wrote:
| Bard seems like an inappropriate name for this, but I guess they
| had to rush something out because some execs were fuming about
| ChatGPT.
|
| It's crazy how a company the size of Alphabet still embraces
| these reflexive whims.
| ryeights wrote:
| This looks pretty bearish for Google. Bard is clearly a half-
| baked/unfinished product, and its release represents Google
| blinking in fear at OpenAI/Microsoft and the like. Google has
| been undergoing years of stagnation and this announcement is a
| good hint that they don't have any aces up their sleeve.
|
| If there were ever a time for Google's operational problems and
| inefficiencies to finally catch up with them, this would be it.
| rafaelturk wrote:
| I've read the article a few times and I still don't know what
| Google will do..
| Oras wrote:
| Missing the point of positioning by miles.
|
| I'm sure Google will release something good, but it will be
| called: Google's ChatGPT.
|
| Should have made something to distinguish their AI solutions from
| just being a copy to trendy solution.
|
| Saying AI will be used in search is not news, AI is already part
| of Google search.
| djha-skin wrote:
| > Today, the scale of the largest AI computations is doubling
| every six months, far outpacing Moore's Law.
|
| That seems really fast.
| [deleted]
| sytelus wrote:
| Is this release of screenshots? Where is the link to try things
| out?
___________________________________________________________________
(page generated 2023-02-06 23:00 UTC)