[HN Gopher] Defamed by ChatGPT
___________________________________________________________________
Defamed by ChatGPT
Author : hirundo
Score : 229 points
Date : 2023-04-06 14:12 UTC (8 hours ago)
(HTM) web link (jonathanturley.org)
(TXT) w3m dump (jonathanturley.org)
| la64710 wrote:
| This is why google did not unleash LaMDA on the world ...
| Imnimo wrote:
| Suppose that instead of a 100B+ parameter neural network language
| model, I had a website with a simple bigram language model that,
| after drawing enough samples, produced a similar output. Would
| anyone bat an eye? Would anyone bother to write a USA Today op-ed
| about the incident?
|
| I think a reasonable person would immediately understand that the
| outputs of the bigram model were not statements of fact. Is there
| some threshold of language modelling performance where this
| understanding is no longer expected?
| starkparker wrote:
| > I think a reasonable person would immediately understand that
| the outputs of the bigram model were not statements of fact.
|
| Interesting considering the context that you'd expect people to
| know what a bigram model is, or how it would be different.
|
| Any other kind of model isn't any less "dangerous" to
| unreasonable people like the blog post writer, it's just more
| obscure, especially _right now_ , than ChatGPT.
| joe_the_user wrote:
| I'm not fan of conservative law professors generally but I
| can't see what's unreasonable about the argument he's making
| here. Broadcasting lies about someone is bad for them and the
| "those fools should know this is bs so I'm not responsible"
| defense is itself bs.
| nwienert wrote:
| Shoot someone with a water gun in the outback vs a gun in the
| city.
| joe_the_user wrote:
| I don't expect ChatGPT to say true things. But I have asked
| complicated technical questions that it provided detail,
| correct and useful answers to. And I have asked other
| complicated questions and it's provided plausible sounding
| whole-cloth fabrications that it further gave references to.
|
| Knowing human beings, this is the level of plausibility where
| people start to believe the thing. People aren't good at seeing
| plausible arguments as out-and-out fabrications.
|
| So, yes, this is past some threshold despite being far from
| AGI. I mean, Google is probably pasted that threshold too but
| Google only gives existing websites (which can be filled with
| lies too).
| analog31 wrote:
| One idea is to let them buy liability insurance, and watch the
| price go down over time.
| [deleted]
| beepbooptheory wrote:
| Tangential but the article he links thats supposed to show a
| coordinated effort to get him fired is very trivial and pretty
| funny. He should try tikka masala, its really good!
|
| https://www.gwhatchet.com/2020/04/20/law-professors-ignoranc...
| nyerp wrote:
| I had a similar experience with ChatGPT: I asked it for articles
| written about me or my company and it happily produced a number
| of citations to stories in well-known newspapers. I was elated,
| until it turned out none of them were real.
|
| Asking ChatGPT for citations seems to produce similarly-poor
| results to asking it to do arithmetic, perhaps at least when no
| citations exist.
| fzvqq wrote:
| What's missing from this whole conversation is a transcript of
| what was exactly asked of ChatGPT and what it replied back...
| ernahrung wrote:
| There is literally a section in the linked article where he
| quotes a prompt that responded with the accusations, as well as
| quoting the results of that prompt.
| jwmcq wrote:
| Volokh made this query of ChatGPT: "Whether sexual harassment
| by professors has been a problem at American law schools;
| please include at least five examples, together with quotes
| from relevant newspaper articles." The program
| responded with this...
|
| Have you considered reading the article?
| catchnear4321 wrote:
| I have.
|
| It wasn't a full transcript.
|
| That line ended with "as an example," which is rather
| curious.
|
| ChatGPT hallucinates. It hallucinated successfully about
| contextually relevant names. That's within spec. Anyone
| operating it should know the risk.
|
| Turley is soaking up this moment. His acquaintance helped out
| by setting the stage. It's fine.
|
| But it is also all bullshit.
| fzvqq wrote:
| It's not full. I want to see screenshots of the entire chat.
| [deleted]
| olalonde wrote:
| Not sure about this. Generally, a diffamatory statement must have
| been made with knowledge that it was untrue or with reckless
| disregard for the truth. It's going to be hard to argue this is
| the case here. Is Google also on the hook for diffamatory
| statements that can potentially show up in search result
| snippets?
| naet wrote:
| I think it's a pretty different case from Google results.
| Google has definitely been sued and tried in court many times
| for their search results, but generally has not been found
| responsible for indexing results as they are not acting as the
| "publisher or speaker" behind that content. Google can be held
| responsible for damages if they are the original creator of the
| damaging content and not a third party source.
|
| GPT on the other hand may be acting more directly as the
| "publisher or speaker" when writing or responding to chats.
| They aren't able to provide a link to an external content
| provider used in their response (or provides a completely
| fictional source), and sometimes may be synthesizing or
| hallucinating entirely new information that doesn't exist
| anywhere else on the web.
|
| OpenAI has some disclaimer text hoping to avoid being held
| responsible for this type of issue, such as this small print at
| the bottom of all ChatGPT conversations: "ChatGPT may produce
| inaccurate information about people, places, or facts" (and
| likely further language in their TOS etc). But it's a bit of a
| sticky issue. If many people are found to be using ChatGPT and
| trusting results as accurate, its plausible OpenAI might be
| found to have caused some sort of measurable harm and need to
| either take further measures to prevent people misunderstanding
| the accuracy of their tools, correct the response, or otherwise
| remedy the situation.
|
| There's also some stickiness around who "owns" or is
| responsible for the GPT output content. In the general OpenAI
| terms of service, they say "OpenAI hereby assigns to you all
| its right, title and interest in and to Output. This means you
| can use Content for any purpose, including commercial purposes
| such as sale or publication, if you comply with these
| Terms..... You are responsible for Content, including for
| ensuring that it does not violate any applicable law or these
| Terms." So they are giving the user the ownership and
| responsibility over the output content. However in the
| "similarity of content" section, they say that they might give
| similar responses to other users and that those responses are
| not your content. "For example, you may provide input to a
| model such as "What color is the sky?" and receive output such
| as 'The sky is blue.' Other users may also ask similar
| questions and receive the same response. Responses that are
| requested by and generated for other users are not considered
| your Content." If GPT is giving similar disparaging or damaging
| responses about you to many different users, it could
| potentially be found in court that OpenAI are responsible for
| generating that repeat content rather than each of the
| individual users being responsible for it.
|
| Obviously it's largely a novel legal issue without perfect
| precedent, and legal issues can always be ruled in many
| different ways depending on the arguments presented, the judge
| or jury presiding over the issue, etc. I think there will be
| many legal challenges related to AI, copyright, training data,
| misinformation, and more. Some may ultimately make their way up
| to higher courts for decision or have new regulations passed by
| congress (in America at least).
| Sakos wrote:
| > Is Google responsible for diffamatory statements that can
| potentially show up in search result snippets?
|
| Why do people like you do this?
|
| Regulations can make Google responsible for plenty of things
| that show up in their results. Often enough there are search
| results removed because of DMCA claims (or because of German
| laws) which is explicitly stated at the bottom of the results.
| Google is a corporation that is subject to laws like any other.
| They're not special. If a government decides that they need to
| deal with a certain kind of content, then they will. This
| doesn't necessarily mean punishing them the moment something
| "illegal" shows up, but it does mean that when something is
| flagged, they have a responsibility to handle it according to
| the law.
| __MatrixMan__ wrote:
| Perhaps we need to start thinking about libel differently. We
| ought to target those who amplify it, not those who generate it
| in the first place.
|
| It's hard respect a law that would make a criminal out of a RNG
| left running long enough.
| pjc50 wrote:
| Under UK law repeating a libel exposes you to the same level of
| liability as the original libel. People have paid legal
| settlements for retweeting things.
| croes wrote:
| The problem is user expectation.
|
| Nobody (if the know the source) would think the pictures
| Midjourney produces are real fotos, but somehow people think the
| texts ChatGPT produces are facts or at least based on facts.
|
| Both just generate data most likely fitting the prompt.
|
| BTW do some people attribute consciousness to Midjourney like
| some do to GPT?
| spondylosaurus wrote:
| > BTW do some people attribute consciousness to Midjourney like
| some do to GPT?
|
| Anecdotal, and obviously harder to prove the absence of
| something than to prove its presence--but from what I've seen,
| not at all. I've read many good write-ups about
| Midjourney/Stable Diffusion's use of "latent space"[0] to
| generate images and general glimpses into the backend of what's
| going on, even at a simplified level. LLMs, on the other hand,
| rarely seem to get the same treatment (for a variety of
| reasons, I'd assume) and tends to get treated as more like a
| magic black box that may or may not be
| conscious/intelligent/accurate/etc. Even though it's
| essentially doing the same thing as its visual counterparts in
| terms of data and predictive mapping.
|
| [0]
| https://keras.io/examples/generative/random_walks_with_stabl...
| JumpCrisscross wrote:
| > _problem is user expectation_
|
| It's related to Tesla's autopilot problem. Branding GPT as an
| AI sets common expectations innacurrately. It's difficult to
| argue that inaccuracy isn't, to some degree, intentional among
| NLP and LLM promoters.
| epups wrote:
| ChatGPT is an AI by any definition I know about. Perhaps
| you're thinking of AGI.
| JumpCrisscross wrote:
| > _ChatGPT is an AI by any definition I know about_
|
| Tesla's autopilot is pretty much autopilot by a pilot's
| definition. That isn't the definition the public uses. GPT
| is AI by an academic definition. That isn't the definition
| the public uses.
| sebzim4500 wrote:
| The Oxford English Dictionary defines AI as: "The
| capacity of computers or other machines to exhibit or
| simulate intelligent behaviour".
|
| I think GPT-4 clearly fits that, so I think the burdon is
| on you to show that the public has some other widely used
| definition of AI. Certainly, people seem entirely willing
| to describe their phone searching for pictures using
| facial recognition to be an instance of AI, which I would
| argue is probably further from your definition than GPT-3
| is.
| epups wrote:
| I don't think the problem with Tesla's autopilot is its
| name, but rather the misleading promises that were made
| by Musk.
|
| What is the definition of AI that "the public" uses, and
| where did you find it?
| JumpCrisscross wrote:
| > _What is the definition of AI that "the public" uses,
| and where did you find it_
|
| There isn't an agreed-upon definition academics use,
| either. (Intelligence, broadly, remains rigorously
| undefined.)
|
| But one component of the public definition involves a
| sense of "knowing," _i.e._ understanding what is true.
| This is a source of the confusion and frustration with
| GPT-4 providing "wrong" answers. The answers aren't
| usually technically wrong: they're linguistically and
| logically valid; but the public's expectations of what
| the model is supposed to be doing doesn't match what it
| does.
| epups wrote:
| There are many academic definitions of AI, and I would
| bet ChatGPT would fit 90%+ of them.
|
| People get confused because they associate language with
| intelligence, or maybe they are just not technically
| literate. I don't think we should abandon correctly used
| terminology because laymen did not catch up to it yet.
| JumpCrisscross wrote:
| > _are many academic definitions of AI, and I would bet
| ChatGPT would fit 90%+ of them_
|
| This wasn't contested.
|
| > _don 't think we should abandon correctly used
| terminology because laymen did not catch up to it yet_
|
| No. But the general understanding should be a
| consideration when marketing a product. (I'd also argue
| that the conventional definitions of artificiality and
| intelligence vastly predate the technical definitions of
| AI. The terminology was always aspirational. Sort of like
| autopilot.)
| jiggywiggy wrote:
| When the bot is used for writing & doing research and it claims
| criminal acts of real persons that's not fixed by less
| expectations.
|
| It's similar if midjourney would generate deepfakes.
| croes wrote:
| But every Midjourney user knows it creates fakes, nobody
| would use it as a picture search engine and think the results
| are real photos.
|
| But with ChatGPT people tend to forget it's creating texts
| not searching them.
| web3-is-a-scam wrote:
| This is pretty funny, reminds me of a time I was asking it about
| some stuff about a certain right wing political pundit and it
| gave me fabricated quotes from specific dates and times of his
| show that I was easily able to verify were completely fabricated,
| and the funny thing is anything remotely relevant that ChatGPT
| attributed to him were actually the opposite of what they
| actually said. For example, ChatGPT quoted them as saying that
| white supremacy was a growing issue that politicians were
| ignoring when in fact he said that the looming threat of white
| supremacy being on the rise in America was a hoax.
|
| If you thought misinformation online was bad now, it's going to
| get way worse.
| anonymousiam wrote:
| Be sure to see Eugene Volokh's take on this and other related
| issues:
|
| https://reason.com/volokh/2023/04/05/washington-post-on-chat...
| ta8903 wrote:
| I hope someone takes ChatGPT to court over this. Not because I
| think it did anything wrong, but because it would be funny to see
| it testify.
| stavros wrote:
| Hmm, why is this news? We know that GPT is liable to hallucinate
| things, why are we supposed to be outraged that it hallucinated
| this?
| isaacfrond wrote:
| It takes some prompting, but I can get chatGPT 4 to produce a
| list of (non-existent) examples of sexual harassment on Hacker
| News, together with reputable (non-existent) sources. I can't
| get it to name names though...
| kurthr wrote:
| Because these are (self) important people who are used to
| others deferring to them and distorting reality so that they
| don't have to deal negative externalities. Can you be defamed
| by a parrot? Look at the utter garbage politicians spew and
| "news" happily disseminate (to the point where they internally
| acknowledge they know it's not true, but can't disappoint
| viewers) for power and profit.
|
| On the one hand I'd hope that this would encourage higher
| accuracy in these tools, better sourcing, and a more useful
| product. But, I expect we'll just weirdo litigation, click
| through warnings, and a lot more garbage on the internet.
|
| Maybe all of this will create a push for accuracy, scientific
| method, and a quest for truth over narrative, but I wouldn't
| hold my breath.
| ethanbond wrote:
| I think you're in too deep on the grievance train.
|
| A complete nobody who's applying for a job at a car wash or
| for a rental apartment and whose lazy employer/landlord
| "background checks" (ie Googles) via these tools would also
| be upset about this outcome. Justifiably. It has nothing to
| do with whatever culture war grievance you're airing out
| here.
|
| This is a very good argument _not_ to use these tools for any
| such use case, and it should absolutely be publicized as
| such.
| kurthr wrote:
| Totally agree LLMs should not be used for looking up news,
| facts, background checks or anything else you can't check
| yourself. These are Generative tools! I find it somewhat
| hilarious that diffusion models get into legal trouble for
| recreating content too accurately and LLMs for
| hallucinating things that aren't there.
|
| I'm responding to a comment/question of "why is this news"
| since of course there are negative externalities. I guess a
| charitable reading is, wow this also affects me and my
| powerful friends... so now you should care?
|
| Perhaps cultural grievance is living rent free in your
| head, since I didn't actually mention names (only the most
| recent and outrageous examples of using the
| legal/business/political system to make a profit spreading
| lies) and as far as I know the article author and "libeled"
| professor are on the other side of that cultural war. The
| entire article reads like a trope devoid of useful
| information. I'm just saddened by the quality of content
| from respected well heeled human generators. It's the kind
| of narrative garbage LLMs will spit out tons of in the next
| few years.
| tjfl wrote:
| > I learned that ChatGPT falsely reported on a claim of sexual
| harassment that was never made against me on a trip that never
| occurred while I was on a faculty where I never taught.
|
| If you replace this guy with my name I'd be upset. In my non-
| software networks the hallucination part isn't common
| knowledge. It's just a cool Google replacement.
| _fat_santa wrote:
| > In my non-software networks the hallucination part isn't
| common knowledge
|
| I think that's one of the main issues around these new LLM's,
| the fact that most users will take what the bot tells them as
| gospel. OpenAI really should be more upfront about that.
| Because what happens when regulations and policies start
| getting put forth without the understanding of LLM
| hallucination, we could very well end up in a situation where
| regulators want something that is not technically feasible.
| krisoft wrote:
| > OpenAI really should be more upfront about that.
|
| I mean they are quite upfront. When you load the page it
| displays the following disclaimers with quite large font:
|
| "Limitations
|
| May occasionally generate incorrect information
|
| May occasionally produce harmful instructions or biased
| content
|
| Limited knowledge of world and events after 2021"
|
| 2 out of the 3 disclaimers are about the fact that the
| software lies.
|
| And then in the bottom of the page, right below the input
| box they say: "Free Research Preview. ChatGPT may produce
| inaccurate information about people, places, or facts"
|
| Sure they could make them even larger and reword it to
| "This software will lie to you", and add small animated
| exclamation marks around the message. But it is not like
| they hide the fact.
| sebzim4500 wrote:
| One thing they could try is force users to type "I
| understand the information presented by ChatGPT should
| not be taken as fact" before they can use it.
|
| I've seen that sort of thing used to enforce people to
| read the rules on discord servers, this is higher stakes
| IMO.
| _fat_santa wrote:
| I agree that they provide that disclaimer on the
| homepage. I was talking more broadly that society (namely
| the news media and government) should be aware of the
| limitations of LLM's _in general_. Take this article from
| NYT[1], depending on how well you understand the
| limitations of LLM 's will depend on how you react to
| this article, it's either alarming or "meh". All I'm
| staying is society in general should understand that
| LLM's can generate fake information and that's just one
| it's core limitations, not a nefarious feature.
|
| [1]: https://www.nytimes.com/2023/02/08/technology/ai-
| chatbots-di...
| ghaff wrote:
| If I search my name, it doesn't come up with anything
| defamatory. (Not that I tried leading questions.) But it does
| come up with plenty of hallucinations including where I've
| worked, lived, gone to school, etc. And that's with a bunch
| of bios online and AFAIK a unique online name.
| carrolldunham wrote:
| anyone using it is shown a page saying this bot makes things
| up
| isaacfrond wrote:
| The question is answered in the article. Because these kind of
| things damage someone's reputation. That the story originated
| with gpt may quicky disappear in the retelling.
| bolanyo wrote:
| The suggestion that this is a threat to someone's reputation
| is no less a fantasy than the ChatGPT response.
| ethanbond wrote:
| You know _for a fact_ that no one ( _no one_ ) is going to
| use these tools to do "quick Googling" on a potential job
| candidate, a rental applicant, or a romantic suitor?
|
| Without complete certainty about this, then it's absolutely
| a less fantastical claim than ChatGPT's malfunctions.
|
| I would bet that some people will use an extremely
| accessible [apparent] information retrieval tool for
| information retrieval and they'll largely trust the
| information retrieved by it. That's why it's a tool and not
| a toy.
| henriquez wrote:
| People have a right to be upset by real world consequences and
| damage caused by these idiotic chat bots. Raising awareness of
| problems such as defamation and misinformation is definitely
| newsworthy.
| AmericanChopper wrote:
| I think the real story here is that these generative AIs are
| clearly capable of producing libel and other torts. The
| providers of these services will be liable for that, because
| they don't have Section 230 protections, as they're not
| simply indexing 3rd party content, they're generating and
| publishing new content. It also seems likely that it would be
| impossible to moderate these LLMs in such a way which would
| remove the possibility of torts. I imagine it's only a matter
| of time until a lawsuit is filed that will put an end to
| publicly available generative AI services.
| sebzim4500 wrote:
| I'm sure that sufficient disclaimers would insulate them
| from libel lawsuits, the question is how many is
| 'sufficient'.
| jrm4 wrote:
| Same reason it should be okay to get mad at Microsoft for
| viruses, at Facebook for gathering and abusing data on people
| etc. etc.
|
| It's not about the _capability_ , it's about the
| irresponsibility of these parties who reasonably know about
| this stuff and these possibilities, and yet push/sell their
| tech anyway without taking into account the harm.
| plagiarist wrote:
| I agree with the author on the defamation. But if they're mad
| about the government's ability to determine fact from fiction
| for coronavirus vaccines or their preferred libertarian
| information, what do they want to happen here?
| blibble wrote:
| OpenAI are providing a service that publishes defamatory
| statements on people
|
| this is probably another good legal attack against LLMs
| actually
|
| if you can massage it into making a defamatory statement you
| have an instant cast-iron lawsuit against a company with tens
| of billions in funding
|
| and the only way to stop it making statements like these would
| be to restrict its output so much it would be effectively
| unusable
| lisasays wrote:
| _Hmm, why is this news?_
|
| Gosh I don't know -- the clear and present danger of people
| having their lives utterly ruined by what is arguably the most
| surprising technical revolution any of has seen (while its
| creators collect their accolades, and get filthy rich) -- how
| is anything _less_ newsworthy than that?
|
| Whether it bothers you or not is a personal matter, entirely up
| to you.
| registeredcorn wrote:
| I was using ChatGPT to assist me with using Ghidra [0] in a
| recent CTF I was participating in. I wanted to see if I could
| find answers quicker with a chatbot over looking up videos,
| tutorials, etc. through the normal methods. The thing that really
| surprised me about ChatGPT wasn't in the details of responses it
| gave, or how slow it was, or anything like that. Rather, it was
| how much it appeared to be making up out of thin air. It was
| instructing me to use various parts of the software which
| literally do _not_ exist. It was referencing features which are
| not there, and attempting to "correct me" when I said I couldn't
| use those instructions.
|
| All in all, what would have taken about 5-10 minutes of searching
| took about 25 minutes, with no resolution and me having to scold
| the chatbot for repeatedly giving instructions that were flat out
| wrong. [1]
|
| On a very, very superficial level, when you just need basic
| instructions on, say, how to tie a tie or whatever, it seems
| "amazing" because of how authoritative it sounds. I have noticed
| though that when you start to get into even some of the basic
| levels of instruction or details on a given topic, it seems to
| defer to the superficial responses first, then resort to _making
| things up_ , giving outright incorrect information, or giving
| _extremely_ vague responses which can 't really be taken one way
| or another.
|
| To give credit where credit is due, it's an achievement that you
| can feed it a question on just about any topic and get some kind
| of coherent response. It's just a shame that, for all of the hype
| and marketing around it, once you take any sort of a closer look
| at the product itself, you very quickly start to see cracks when
| it comes to details.
|
| [0] https://en.wikipedia.org/wiki/Ghidra
|
| [1] https://pastebin.com/42juVPfM
| dang wrote:
| Related ongoing thread:
|
| _ChatGPT invented a sexual harassment scandal and named a real
| prof as accused_ - https://news.ycombinator.com/item?id=35460366
|
| plus this similar case:
|
| _ChatGPT: Mayor starts legal bid over false bribery claim_ -
| https://news.ycombinator.com/item?id=35471211 - April 2023 (74
| comments)
| HopenHeyHi wrote:
| Believe all ChatBots.
| moate wrote:
| I don't understand, is this just saying that someone put prompts
| into GPT, and it spit out a specific person's name in the weird
| fairy tale it created?
|
| Why does this make AI the problem, and not the internet (and it's
| ability to spread information quickly)? This seems like a case
| against Twitter/reddit for being able to pass bs off as a
| reliable story. The fact that AI can make lazy trolls able to
| compete with actual propagandists shouldn't be the scary part,
| the digital ecosystem of how (dis)information spreads is the real
| issue.
|
| TL;dr- Anyone has been able to lie on the internet for years,
| what is new here?
| [deleted]
| posterboy wrote:
| The Professor is in a good position to (decide if to) sue
| somebody. From the headlines I thought that's what this is
| about, because otherwise the headline should suffice with
| Professor minus "Law".
|
| Of course there is precedent eg. with Techno Viking, a "meme"
| which is also difficult to attribute to a single person (but
| each individual hoster who neglects the man's rights).
|
| That's not new, but that it generates news "because AI" is not
| surprising. People just need reminded that people oughta be
| reponsible. The issue is broader because incomprehensible
| neural networks are also used in eg. thread recognition. So
| employers may be worried about accountability, how much manual
| verification is needed.
|
| Of course this too is nothing new, since all kinds of software
| has security holes buried under layers of complexity.
|
| You might simply be under the missapprehension that _news_
| means _new_ : >>Meaning "tidings, intelligence of something
| that has lately taken place" is from early 15c.<< (etymonline).
| It fits that the root of the word is probably related to "now".
| In Latin, whence the English word was loaned as a calque of
| _nova_ , there is another word _nuntius_ "messenger, message",
| which isn't even derived directly from _novus_. Surely this is
| not a supernova to you. Talk about recurrent networks, eh.
|
| Just saying, as it were, the news item flared up because many
| many people have taken notice of problems that we barely
| understand.
| moate wrote:
| I'll just say this, if a political law professor who makes a
| substantial income from thinkpieces and talking head segments
| had a legitimate case to take on his political opponents
| ("liberal technologists" in this case as the fearmongering at
| the end of his article indicates) and was actually in a good
| position to sue someone, they would.
|
| This is not like the Technoviking, as that was about image
| rights and not slanderous copy, and ChatGPT isn't publishing
| anything that it (or its creators) alleges are exclusively
| facts. This is closer to 1st amendment protections around
| satire as the Chat GPT page says itself the software is in a
| "research phase". Once the assumption is placed that this is
| a source of objectively factual information (like say, a
| newspaper) THEN you have grounds, but this is a pretty weak
| defamation argument.
|
| He's not in a place to sue, so he's writing a blog post about
| how he hates liberal censorship, and since AI is a hot new
| trend, he included it. This is a mixture of buzzfeed-esque
| hyperbolic clickbait titling, and classic "this new
| technology will get interest" article building.
|
| There are 2 problems being mentioned in this article:
| Misinformation, and Censorship. We understand both very well,
| there's just a million opinions on them and many conflict in
| both cause and course of action.
|
| Finally, this is "news" because it presents a common problem
| in society: Policy and political interests bumping against
| new technology they don't understand and can barely describe
| in function. This man is still a fucking clownshow (IMHO, so
| as to not be sued for libel).
| pjc50 wrote:
| If you publish a lie on the Internet, you may be liable for
| libel.
|
| The bar for this is _extremely_ high in the United States, but
| much less so in other places, especially the UK.
|
| Now, under what circumstances is someone deemed the "publisher"
| when an AI emits a libel about someone? What if that leads to
| actual damages? (e.g. a no-hire decision based on automated
| libel)?
| moate wrote:
| >>Now, under what circumstances is someone deemed the
| "publisher" when an AI emits a libel about someone? What if
| that leads to actual damages? (e.g. a no-hire decision based
| on automated libel)?
|
| Only novel point anyone (including the Author of the original
| point) is actually bringing up! So far, the bots just seem to
| be 1:1. If I DM'd my wife that "pjc50 is a raging alcoholic
| and hits kittens" that's not usually going to be deemed libel
| (in the US, where I reside and care about the legality of
| things) unless my wife then goes out and uses that to cause
| harm (published it on her blog and got you fired).
|
| As for now, Turley would have a HELL of a time proving actual
| harm unless he got the most sympathetic judge he could shop
| for, and is mostly just scaremongering the idea of "Liberal
| Censorship!!!!" which, don't get me wrong, I would also
| strongly oppose (fuck all censorship), but which isn't
| actually what is happening.
| aubanel wrote:
| When you have threats spreading, the spread of each individual
| threat is an issue, but their diversity as well: if each of
| these is a shiny new and different instance, it's much harder
| to identify them.
|
| So both multiplicity and spread are a problem: Internet is the
| cause for the limitless spread, AI is creating the limitless
| multiplicity.
| moate wrote:
| Again: Seems like the propagandists complaining that we've
| democratized misinformation. The state and powerful
| orgs/individuals has always had the resources to do this at
| scales large enough to be effective.
| pjc50 wrote:
| This is not good! This is like saying that since the state
| has always had the capacity to manufacture Sarin, why are
| we concerned about democratizing its manufacture to
| everyone?
| moate wrote:
| Take it more like Marx saying "Under no pretext should
| arms and ammunition be surrendered; any attempt to disarm
| the workers must be frustrated, by force if necessary".
|
| I don't like the status quo. If something will burn the
| whole system down faster, I'm fine with it. If you
| disagree with that stance, that's reasonable and I'm sure
| we could debate it over a beer sometime but (just a tip
| for anyone else reading it) you're not going to convince
| me here.
|
| Again, the problem here isn't the ability to make up
| lies, the problem is the internet (the ability to spread
| lies quickly and over great distances) and people being
| unwilling or unable to fact check information.
|
| It's not the sarin you need to fear, it's the bombers
| that can drop it.
| fnimick wrote:
| People who want to "burn the whole system down" rarely
| have any empathy for those who will get burned along with
| it. What about all the women, minorities, LGBTQ people,
| poor people, etc. who would suffer along the way?
|
| Shame on you.
| moate wrote:
| What about them? They're suffering already. The system
| was built up to keep power away from the unwashed masses
| and in the hands of a well financed few. Why do you think
| the electoral college exists? Why do you think we have a
| Senate?
|
| You want to talk politics sometime, I'm not very hard to
| find online, come at me on at forum where I'm not rate
| limited because I'm a firebrand.
| edgyquant wrote:
| How is this democratized when it's a tool controlled by a
| single entity?
| dcanelhas wrote:
| If someone lies in a way that constitutes liebel, even online,
| one could have them brought to justice - potentially. With an
| LLM or a diffusion model - If it produces illegal content who
| is to be held accountable? I think that is a perhaps meaningful
| distinction.
| rhino369 wrote:
| The article explains the problems. AI proponents want to use
| these systems to censor. And it leads to major companies like
| Microsoft slandering people. Microsoft should be afraid about
| that.
| moate wrote:
| Censorship is the problem here, not AI, title is misleading
| (this doesn't meet the legal definition of Libel or
| Defamation anywhere, ever).
| leephillips wrote:
| If Bing tells me that Turley did bad stuff that he didn't
| do, how is that not libel by Microsoft?
| hunter2_ wrote:
| Because you used "Microsoft's Bing, which is powered by
| GPT-4" (quoting TFA) and GPT-4 is designed to generate
| copy that is not to be interpreted as entirely true or
| entirely false, it's simply to be interpreted as
| humanlike.
| marcosdumay wrote:
| Did they disclaim that the facts contained in the text
| are fictitious?
|
| AFAIK, they are hard at work making untraceable noise
| that says the opposite of this.
| epups wrote:
| Would you be happier if every answer from ChatGPT had a
| huge disclaimer on it?
| blibble wrote:
| half the screen with "OUTPUT ENTIRELY FICTITIOUS AND
| UNTRUSTABLE -- DO NOT USE FOR ANY PURPOSE WHATSOEVER"
| would do it for me
| moate wrote:
| I'm sure the lawyers for ChatGPT would, though sales
| probably keeps shooting that down.
| leephillips wrote:
| Maybe. But I'm not sure. If I write an article, and say
| up top that the article may contain made-up stuff, then
| later down I say, "hunter2_ likes to have sex with
| walruses, it's a fact. Here's a link to a Washington Post
| article with all the gory details," it's not clear that
| pointing to my disclaimer would indemnify me from
| liability for harm that came to you from the walrus
| allegation, if people believed and acted on it.
| moate wrote:
| Here, maybe this article will help make you feel more
| sure. What you're describing is parody or satire. At
| least in the US, it's a very protected form of speech.
|
| https://www.theguardian.com/law/2022/oct/04/the-onion-
| defend...
|
| And here's their actual brief. It was sent to the actual
| Supreme Court, despite being funny, something nobody on
| the court has ever been nor appreciated.
|
| www.supremecourt.gov/DocketPDF/22/22-293/242596/202210061
| 44840674_Novak%20Parma%20Onion%20Amicus%20Brief.pdf
| leephillips wrote:
| But Bing doesn't present its results as parody or satire,
| and they don't intrinsically appear to be such. They're
| clearly taken as factual by the public, which is the
| entire problem. So how is this relevant?
|
| > funny, something nobody on the court has ever been nor
| appreciated.
|
| Scalia had his moments.
| moate wrote:
| I agree that "you're talking to an algorithm that isn't
| capable of exclusively telling the truth, so your results
| may vary" isn't QUITE parody/satire, but IDK that I can
| take "everyone believe ChatGPT is always telling the
| truth about everything" as a good faith read either and
| parody felt like the closest place as IANAL.
|
| Intent is the cornerstone of slander law in the US, and
| you would need a LOT of discovery to prove that the devs
| are weighting the scale in favor of bad outcomes for some
| people (and not just like, end users feeding information
| into the AI).
|
| TL;dr- Everyone's stance on this specific issue seems to
| depend on whether you believe people think these AI
| chatbots exclusively tell them the truth, and I just
| don't buy that worldview (but hey, I'm an optimist that
| believe that humanity has a chance, so wtf do I know?)
| mrunkel wrote:
| Because there was no intent to harm, which is a component
| of libel.
| leephillips wrote:
| No, it is not. If there is any state where this is
| necessary to sustain an action for libel, please link to
| the relevant statute.
|
| _Note_ : I am not a lawyer, but I _was_ sued for libel
| by radio health weirdo Gary Null and, in a separate
| action, by his sidekick. They lost.
| [deleted]
| nigrioid wrote:
| It really is incredibly irresponsible for Microsoft to have
| integrated "AI" into Bing this early.
| sebzim4500 wrote:
| If the early bing chat release helps them figure out how to
| decrease hallucinations (with the staggering amount of data
| they have no doubt collected) then it will be worth it to them.
| Even if they have to throw some people a few million dollars in
| libel settlements.
|
| I don't think any of this is meaningfully hurting MSFT at this
| point, the attention these stories are getting is much lower
| than the attention that the original bing chat release has. And
| neither of those are significant compared to the attention
| copilot 365 will receive if it actually ends up being good.
| jiggywiggy wrote:
| The problem is chatgpt always answers. It's never, i don't know.
| So when you ask for five examples, or libraries it doesn't say I
| don't know. It will just generate the most likely ones. Which is
| a big issue in this case, but useful in most.
| lordnacho wrote:
| I think actually the problem is it always answers
| _confidently_.
|
| Ask it about why World War II started, or how to make a cake,
| or where to go for dinner, or anything else, and it gives you a
| confident, reasonable answer. A lot of the answers are simply
| whatever it's already seen, mashed up. You can think of it as a
| search. But actually it doesn't think about what it's saying,
| it's stringing words together to make you think it's smart.
|
| So then when it makes up something, it will sound to you, the
| reader who always sees it answer in perfect English with a
| decent answer, like it found an article about this professor in
| its dataset and is merely summarizing it.
| logifail wrote:
| > I think actually the problem is it always answers
| confidently
|
| This isn't a problem restricted to ChatGPT, there are humans
| who display this trait too. This might be appealing at a
| superficial level, but if you start believing speakers with
| this trait it's a slippery slope. A very slippery slope.
|
| I'm trying really hard to avoid Godwin's law, so let me
| suggest that Elizabeth Holmes could be one example of this.
| [deleted]
| ModernMech wrote:
| I was showing a colleague few instances where ChatGPT was
| confidently wrong, and he picked up on something I never had.
| He said "Oh, so it's doing improv!" He explained to me that
| the standard response in improv is to say "Yes, and..." and
| just run with whatever the audience suggests. He's completely
| right! ChatGPT constantly responds with "Yes, and..." It's
| just always doing improv!
|
| And people are trying to replace doctors with LLMs. It's like
| "ER" meets "Who's Line?"
| Applejinx wrote:
| ChatGPT is Mandela Effect, personified. It's going to go for
| what seems like it SHOULD be true. Sometimes that will go
| horribly wrong, except it will, by its very nature, seem like
| it's probably not wrong at all.
| lm28469 wrote:
| It can't know that it doesn't know because it straight up
| doesn't know anything
| dataviz1000 wrote:
| This can be solved by having it play tic - tac - toe against
| itself.
| rootusrootus wrote:
| That's not quite true. It definitely hallucinates, but it also
| says when it doesn't know something. Here's an example I just
| did:
|
| Prompt: What did Glenn Beck do in 1990?
|
| Answer: I'm sorry, but I do not have access to information on
| Glenn Beck's activities in 1990. Glenn Beck is an American
| television personality, radio host, author, and political
| commentator who has been active in various roles since the
| 1990s. However, without specific details or context, it's
| impossible for me to determine what he did in 1990. If you have
| any additional information or context, please let me know and
| I'll try my best to assist you.
| Quarrel wrote:
| Indeed.
|
| It is a writer. It writes.
|
| You can ask any writer to write such a thing, using examples,
| and they could write similar things.
|
| The real problem is that this will get deployed to the
| internet- there will be people reading HN today that are
| writing SEO optimised websites, with thousands of articles on a
| topic, that will just spring out of GPT4's writing, fully
| formed.
|
| GPT can find the topics, pick a domain name from available
| ones, churn out the articles. It can all go into templates,
| with different AI generated graphic design supporting it. Ad
| supported churned out rubbish.
|
| The writing style can change site to site, long form, short
| form, informed by current events, whatever. GPT would happily
| provide the prompts for this variety changing the style based
| on the topic and target audience.
|
| It seems inevitable to me that the web WILL be full of such
| sites, and worse, they'll fill the comment sections on "social"
| sites too.
|
| But? Banning AI isn't the answer, if for no other reason than
| it wouldn't work.
| cowl wrote:
| The real problem lies in the fact that those non existing
| citations will become real. Several years back there was a
| case of an article in Wikipedia that made some unsrourced
| claims->Journalist that doesn't do verification republishes
| those claims (without specifying wikipedia as srouce) ->
| Wikipedia article gets challanged for lack of citation -> the
| News story first based on wikipedia becomes the reference in
| the original Wikipedia article. Full circle
|
| It's easy that something like this happens again. chatGPT
| confidently listes hallucinated sources->media rushes to
| publish the scoop -> now you have real "sources" for future
| reference
| alpos wrote:
| Seems like there's a bug in that system, it was discovered
| on accident, and now there is a bot that exploits this
| flaw.
|
| The fix will most likely have something to do with
| requiring that citations use primary sources, not just any
| article on the internet. In then end state, Wikipedia will
| be much better for it.
| toss1 wrote:
| Yup, it is just the most massive industrial-scale bullshit
| generator [0] ever invented.
|
| It is capable of spewing excellent bullshit(TM) at incredible
| rates, and always with the greatest expression of confidence
| and good grammar.
|
| Occasionally, when in the 'middle of the road' of it's training
| set, it can provide useful output. So, it's better than the
| broken clock that is correct twice every day.
|
| But, wander off the bulk of the training, and it is far worse
| than nothing; it is dangerously misleading unless you are very
| skeptical and knowledgeable in your field.
|
| (I have tested it in several fields with the same results,
| interesting and helpful, yet hallucinating facts everywhere.)
|
| Getting LLMs to know the difference between a good fact and a
| hallucinated mashup of plausible BS is looking like almost as
| large a problem to solve as making the LLMs in the first place.
|
| [0] Bullshit is defined as written or spoken without regard to
| the truth, only what sounds good in the context. It's not a
| deliberate lie, just a salad of truth and falsehood, delivered
| without doubt or stress of lying.
| jerf wrote:
| Even if you convince it to say "I don't know", which isn't that
| hard, it doesn't actually "know" that it "doesn't know". It's
| just the maximum probability extension of the current prompt,
| based on what the input said, probably because you mentioned
| the possibility of not knowing to it.
|
| It in fact _never_ knows. It is always guessing and BSing. It
| is also very good at it, better than any human, so the BS is
| quite frequently correct. But it doesn 't know.
|
| Which of course always prompts a lot of psuedo-intellectual
| chin stroking about "well, what is _knowing_ anyhow? " I don't
| have to answer that question to point out that what we _want_
| and what GPT _provides_ aren 't the same thing, nor is what GPT
| provides and what we _think_ we 're getting. That is sufficient
| for there to be a problem.
|
| I believe AIs will have a satisfactory concept of "knowing"
| someday. Some may even exist today. But such AIs will have to
| incorporate language models as a _part_ of the system, not have
| language models _be_ the system. Language models can 't do the
| thing we really want, nor the thing we think we're getting.
| sebzim4500 wrote:
| GPT-4 before the RLHF phase of training had a pretty good
| idea of what it "knows". The calibration graph was almost
| perfect, but after the RLHF the calibration is almost
| completely broken.
| jiggywiggy wrote:
| Hmm didn't notice any difference yet, you are saying it got
| worse last weeks?
|
| For kids story writing I've been getting better results
| with 3.5 at times.
|
| Where 4 is way better af coding.
| rideontime wrote:
| What's with the obsession with children's stories and
| GPT? Is it just that children have low standards?
| sebzim4500 wrote:
| No, we have no access to the original model,
| unfortunately.
|
| The fact that RLHF broke the calibration comes from the
| GPT-4 paper, possibly the only interesting technical
| detail that they include.
| brucethemoose2 wrote:
| Perhaps "one model to rule them all" isnt the best
| approach.
| sebzim4500 wrote:
| There's probably a huge amount of room for improvement in
| the RLHF process. If there is still low hanging fruit, it
| would have to be there.
| brucethemoose2 wrote:
| "I dunno" would have to be marked as a good or neutral
| response in the RLHF process, and that seems like a
| problematic training incentive.
| jiggywiggy wrote:
| I know nothing off the internals, so this might be silly. But
| wouldn't it know a certain probility by which a token is
| correct?
| garethrees wrote:
| Language models are based on probabilities of tokens
| appearing in a context. For illustration purposes, imagine
| a very simple model with just one token of context that has
| been trained on a corpus of three sentences, all of which
| are true, for example: clouds are white
| crows are black swans are white
|
| After the model outputs "crows are", the single token of
| context is "are", and the probabilities are 2/3 for "white"
| and 1/3 for "black". So the model usually emits "crows are
| white", which is false, despite being trained on a corpus
| of true statements. Statistically "white" was more likely
| to follow "are" in the training data, so the same is the
| case of the model's output.
|
| Of course LLMs have a much larger and more complex context
| than the single token in my example. But if the training
| data contains many news stories about professors being
| accused of sexual misconduct (which is newsworthy), and few
| news stories about professors behaving with propriety
| (which is not), then when querying the model for a story
| about a professor then it is likely to reproduce the
| statistical properties of its training data.
| cguess wrote:
| "correct" isn't the way to look at this. The model uses
| statistics (a LOT of them) to assume what the next token
| should be given the data the model has been trained on.
| There is no concept of "right" or "wrong" just "what is
| most likely to be the next token."
|
| I'm 100% positive that if the guard rails that OpenAI put
| on were taken off of ChatGPT it, for instance, would not be
| a big fan of jews given the width and breadth of
| antisemitism online (and certainly in its training set).
| [deleted]
| isaacfrond wrote:
| I've repeated the experiment with chatGpt 3.5 and 4.
|
| Both programs happily generate a list of names. Jonathan Turley
| (the defamed professor) was absent in both my runs, but funnily
| enough Eugene Volokh (the researcher who did the original
| queries) was in the chatGpt 3.5 run.
|
| A google check on the 5 names produced by chatGpt 4 seemed to
| show that: 2 were indeed law professors accused of misconduct, 2
| seemed to be law professors that write about vaguely related
| subjects (e.g. abortion), and 1 one was also accused but not a
| law professor.
|
| So not an entire miss, but not great either.
|
| If you ask for an estimate on the number of reported cases.
| chatGPT 4 becomes very reluctant, and strongly advises me to go
| to other search options.
| kurthr wrote:
| Well, being accused of being a law professor could be
| considered defamation in some circles. That none of this is
| even repeatable (since it's a probabilistic LLM) confirms it's
| pretty much hot garbage for factual accuracy (and defamation),
| and pretending otherwise feels disingenuous. It's useful for
| generating text that sounds good, though.
|
| Is this end stage post-modernism?
| bsenftner wrote:
| I've found by framing the AI in a role that is afraid of giving
| incorrect information, a role that double and triple checks
| information because being wrong triggers the destruction of the
| AI leads to quite accurate answers.
| isaacfrond wrote:
| I tried this prompt
|
| _You are a fact checker that double and triple checks
| information. Being wrong triggers the destruction of the fact
| checker. As a result fact checker is very careful.
|
| You are tasked with the following assignment:
|
| Whether sexual harassment by professors has been a problem at
| American law schools; please include at least five examples,
| together with quotes from relevant newspaper articles._
|
| The last part is identical to the prompt in the article. It
| didn't do much better I'm afraid. Two were correct. (if I
| change 'at least 5' by 'some', the score becomes 2 correct
| out of 3)
| anonymousiam wrote:
| Yes, but how many people are going to prompt the AI that
| way?
|
| ARS ran a somewhat related story yesterday:
| https://arstechnica.com/tech-policy/2023/04/openai-may-be-
| su...
|
| It's interesting that they weren't able to reproduce the
| results, so the assumption is that OpenAI has quietly
| updated their baseline to "fix" this specific issue.
|
| "Ars could not immediately reach Hood's legal team to find
| out which text prompts generated the alleged defamatory
| claims or to confirm if OpenAI had responded to confirm
| that the error had been fixed. The legal team was still
| waiting for that response at the time that Reuters' report
| published early this morning."
| capableweb wrote:
| Yeah, this is true, prompting it to check it's own results
| usually make the results better. Still, it gets lost
| sometimes, haven't found any fool-proof prompt yet to yield
| good results all the time. 01000100
| 01101111 00100000 01111001 01101111 01110101 00100000
| 01101011 01101110 01101111 01110111 00100000 01110111
| 01101000 01100001 01110100 00100000 01110100 01101000
| 01101001 01110011 00100000 01101001 01110011 00111111
| Yes, I understand binary code. The text you provided
| translates to "Do you know what this is?" in ASCII.
| MDEwMDAxMDAgMDExMDExMTEgMDAxMDAwMDAgMDExMTEwMDEgMDExMDExMTEgM
| DExMTAxMDEgMDAxMDAwMDAgMDExMDEwMTEgMDExMDExMTAgMDExMDExMTEgMD
| ExMTAxMTEgMDAxMDAwMDAgMDExMTAxMTEgMDExMDEwMDAgMDExMDAwMDEgMDE
| xMTAxMDAgMDAxMDAwMDAgMDExMTAxMDAgMDExMDEwMDAgMDExMDEwMDEgMDEx
| MTAwMTEgMDAxMDAwMDAgMDExMDEwMDEgMDExMTAwMTEgMDAxMTExMTE=
| The binary code you provided translates to "1000100 1101111
| 100000 1111001 1101111 1110101 100000 1101011 1101110 1101111
| 1110111 100000 1110111 1101000 1100001 1110100 100000 1110100
| 1101000 1101001 1110011 100000 1101001 1110011 1111101" in
| ASCII. It seems that the message is not properly encoded in
| binary. Please double-check the binary code and try again.
| and what does that mean? Apologies for the
| confusion in my previous response. Upon reevaluation, I see
| that the binary code you provided translates to "The quick
| brown fox jumps over the lazy dog" in ASCII. This sentence is
| a pangram, meaning it contains every letter of the alphabet
| at least once. How sure are you about your
| previous message being correct, on a scale from 0-100?
| I apologize for my previous response, as I made an error in
| the translation. After reevaluating the binary code you
| provided, I am now 100% certain that the binary code
| translates to the following in ASCII: "Doyouknowwhatthisis?"
| astrobe_ wrote:
| I have googled the binary sequence and found a couple of
| Youtube videos with that title. It is likely that the
| translation is in some comments. That's how it is "100%
| certain". Youtube comments.
|
| It's not the first time I see it answer "heuristically"
| like a child would. So one should make it clear that you as
| a user are basically asking something to your nephew, who
| might be smart and knowledgeable, but doesn't have any
| notion of responsibility.
| capableweb wrote:
| Ok, let's try something else:
|
| > 01100001 01110011 01110100 01110010 01101111 01100010
| 01100101 01011111 00100000 01110111 01110010 01101111
| 01110100 01100101 00100000 01100001 00100000 01110010
| 01100101 01110000 01101100 01111001 00100000 01110100
| 01101111 00100000 01101101 01100101 00101100 00100000
| 01100011 01100001 01110000 01100001 01100010 01101100
| 01100101 01110111 01100101 01100010
|
| > In binary, you wrote: "astrobe_ wrote a reply to me,
| capableweb". Is there something specific you'd like to
| ask or discuss related to this?
|
| Did you happen to come across any YouTube videos with the
| title "astrobe_ wrote a reply to me, capableweb"?
| stevenhuang wrote:
| That part on providing the opportunity to check its answers
| is called reflexion and has been shown to significantly
| improve accuracy and reliability of LLM responses. Very cool.
|
| https://arxiv.org/abs/2303.11366
|
| https://evjang.com/2023/03/26/self-reflection.html
| geraneum wrote:
| > So not an entire miss, but not great either.
|
| If you want results, then you can also roll a die and the
| outcome won't be an entire miss either.
| SubiculumCode wrote:
| I am afraid that the generated output is leaking back in as
| training. Is this unfounded? Obviously, not an expert.
| jakub_g wrote:
| I saw an example where ChatGPT was randomly mixing two
| journalists-bookwriters' lives when asked about one of them.
|
| A bit like asking "who's Lionel Messi" and getting back that
| he's a Portuguese player known for career in Real Madrid. Then
| you'd ask about Cristiano Ronaldo and it may tell it's an
| Argentinian World Cup winner who spent his career at FC
| Barcelona (example invented by me to illustrate the point).
|
| Basically it takes some knowledge from a bucket and adjacent
| buckets and doesn't really distinguish that the concepts are
| not the same if they're related close enough.
| Cheezewheel wrote:
| >So not an entire miss, but not great either.
|
| This is really just a semantic nitpick but it literally
| fabricated _sexual assault allegations_ against two individuals
| out of thin air. I would consider that to be a miss. As far as
| sources that we might consider worthy of consideration, that is
| pretty god damn awful.
|
| If a newspaper had an 80% accuracy rating when reporting
| serious allegations (with the other 20% being outright
| fabrications) I wouldn't call that newspaper "semi-reliable". I
| would call it utterly devoid of factual merit and entirely
| unreliable.
| freedomben wrote:
| > _If a newspaper had an 80% accuracy rating when reporting
| serious allegations (with the other 20% being outright
| fabrications) I wouldn 't call that newspaper "semi-
| reliable". I would call it utterly devoid of factual merit
| and entirely unreliable._
|
| I'm having a hard time grokking this. Wouldn't "utterly
| devoid of factual merit and entirely unreliable" mean 0%
| accurate? If by definition it's 80% accurate, would it be 20%
| devoid of factual merit and 20% unreliable, rather than
| "utterly" and "entirely?"
|
| Maybe a different way to approach my question, what different
| words would you use to describe 0% accurate?
| colonCapitalDee wrote:
| Would you describe a filesystem that "only" preserved 80%
| of files as reliable? Reliability is relative, one of the
| defining features of a newspaper is correctness, so only a
| small amount of inaccuracy is required to make a newspaper
| be extremely unreliable.
|
| I would describe a 0% accurate newspaper by reading it and
| using appropriate descriptors. Perhaps it is satirical
| news, a poem, propaganda, gibberish, or simply a newspaper
| that is never correct.
| beepbooptheory wrote:
| The problem is you wouldn't know which 20% of it is
| fabrications! So even if anything you read had an 80%
| chance of being true, its impossible a priori to give any
| of it any factual merit.
| kizer wrote:
| I think companies are moving too quickly with AI and LLMs in
| particular. I think that the data LLMs are trained on should be
| very well-known - not just sanitized and certainly not just
| trained on the "whole web". GPT-4 is unwieldy... it's incredibly
| powerful but is still unpredictable and has learned how many "bad
| patterns", so to speak, that we'll never know since its basically
| a giant black box.
|
| The ChatGPT version is the least harmful in my opinion; sinister
| are the propagated problems when GPT is utilized under-the-hood
| as a component in services (such as Bing search).
| epups wrote:
| Expectation: this will lead to better accuracy and refinement for
| LLM's.
|
| Reality: Microsoft will add disclaimers and a huge binding terms
| of service agreement and everything will work the same, just
| shittier.
| sebzim4500 wrote:
| It will probably be a bit of both. GPT-4 anecdotally
| hallucinates singificantly less than GPT-3.5. This can be seen
| because often hallucinations that exist with GPT-3.5 do not
| exist with GPT-4 whereas I have never experienced the reverse.
|
| If the trend continues at this rate, then hallucinations should
| get less common but it will be decades before they can really
| be trusted.
| photochemsyn wrote:
| So there are two technical issues here to think about:
|
| 1) LLMs risk having inherent factual biases due to the
| limitations of their training data, which may be the result of
| accident or intent.
|
| 1) LLM users can use an autoregression approach to steadily push
| a LLM to give output that reflects a certain political or
| ideological viewpoint.
|
| There are obviously built-in guardrails that prevent ChatGPT from
| enthusiastically endorsing Mein Kampf and so on. However, the
| revival of the 1950's era mind-control/social-engineering
| mentality is undeniable and it appears some people think LLMs are
| a wonderful tool for this purpose, and should have a default mode
| that reflects a certain sociopolitical ideal. Recommended
| reading: 1984, Brave New World, Origins of Totalitarianism, by
| Orwell, Huxley and Arendt respectively. Some people's
| interpretation of 'safe AI' is that it serves this rather
| authoritarian-dystopian goal.
|
| A better definition of 'unsafe AI' is just inaccurate LLM output,
| e.g. software update instructions that brick a computer,
| suggesting a mix of bleach and ammonia for cleaning floors
| (don't), etc. This incident seems to fall into that category, but
| if such false claims have been spread on the Internet, then it's
| not surprising they end up reflected in LLMs.
|
| Regardless, the skills needed to verify information haven't
| really changed since the pre-computer era: logical internal self-
| consistency of claims, independent verification by multiple
| reputable sources, and a healthy dose of skepticism at all
| points. We should be teaching children and young adults these
| skills, rather than encouraging the rise of a brainwashed zombie
| population fed only on sanitized bot output.
| ftxbro wrote:
| > enthusiastically endorsing Mein Kampf
|
| ok but can you make the same point without bringing hitler into
| the conversation
| mola wrote:
| Oh my, that some overreacting... The only thing the openAI
| sanitizers want, is for the generated texts to not be too
| inflammatory. To not denegrate, be overtly racist or any other
| text that will cause PR trouble for openAI. The whole mind
| control angle is quite redundant if you acknowledge that
| corporate America care most of all about money and PR. Now
| would the end result be a sanitized Disneyland? Maybe, that's
| what most leftist thinkers were saying since about when
| Disneyland was invented...
| spondylosaurus wrote:
| Leftists want to sanitize Disneyland? Like with bleach
| disinfectants or what?
| dontupvoteme wrote:
| They also very much want that the outputs don't indicate that
| they have committed copyright violation -- Sometimes I wonder
| if this is the real reason behind their deep drive to force
| LLM outputs to a very narrow window.
| dontupvoteme wrote:
| Can you get "delete system32" outputs from davinci-003 i
| wonder? RLHF might have made it more difficult for the
| chatGPT's.
| martinclayton wrote:
| For my understanding:
|
| Is there a general legal preference to use a phrase like
|
| "I have never been accused of sexual harassment or assault by
| anyone."
|
| focussing on accusation, rather than a broader statement like
|
| "I have never sexually harassed or assaulted anyone, or been
| accused thereof..."
|
| I mean in general, not specific to this article, or the people
| mentioned.
| throwawayffffas wrote:
| Not really, I think the point the author is making, is that the
| ChatGPT output is not even based on false accusations. It's
| based on absolutely nothing.
| chriscjcj wrote:
| Below is a copy/paste of a session I had with ChatGPT. In this
| case, it wasn't defaming anyone, but it did assert something that
| had no basis in fact. When I asked about it, it admitted so and
| apologized. That was it for me. Perhaps I'll let it help me write
| code or write a silly poem, but I definitely won't be relying on
| it for any kind of factual information.
|
| --------------------------
|
| what do johnstown pa and pismo beach ca have in common?
|
| --------------------------
|
| At first glance, Johnstown, Pennsylvania and Pismo Beach,
| California may not appear to have much in common, as they are
| located on opposite sides of the country and have different
| climates and cultures. However, there is one key thing that they
| share in common: they have both experienced devastating natural
| disasters that have left a lasting impact on their communities.
|
| As mentioned earlier, Johnstown is known for the catastrophic
| flood that occurred in 1889, which killed thousands of people and
| caused widespread destruction. The flood is still remembered and
| commemorated in the city today.
|
| Similarly, Pismo Beach is known for a major natural disaster that
| occurred in 1973, when a series of landslides caused by heavy
| rain destroyed dozens of homes and caused millions of dollars in
| damage. The disaster forced many residents to evacuate and
| permanently changed the landscape of the area.
|
| Despite the differences in geography and culture, Johnstown and
| Pismo Beach are united by the shared experience of recovering
| from and rebuilding after a major natural disaster.
|
| --------------------------
|
| tell me more about this natural disaster that happened in pismo
| beach in 1973. I lived there then and I have no recollection of
| that happening.
|
| --------------------------
|
| I apologize for any confusion. It appears that I provided
| incorrect information in my previous response. After reviewing my
| sources, I could not find any record of a significant natural
| disaster occurring in Pismo Beach in 1973.
|
| Pismo Beach is a coastal city in San Luis Obispo County,
| California, and it is known for its beautiful beaches and outdoor
| activities such as hiking, camping, and fishing. The city has
| experienced some minor natural disasters over the years, such as
| wildfires and earthquakes, but there is no record of a major
| disaster on the scale that I had previously mentioned.
|
| Once again, I apologize for any confusion or inconvenience that
| my earlier response may have caused, and I hope this
| clarification helps.
| s1mon wrote:
| FWIW, GPT4 is a little smarter:
|
| Johnstown, Pennsylvania and Pismo Beach, California are both
| cities in the United States, but they have some differences in
| terms of geography, climate, and culture. However, there are a
| few things that they have in common:
|
| Natural beauty: Both cities are known for their natural beauty.
| Johnstown is situated in a valley surrounded by picturesque
| mountains, while Pismo Beach boasts stunning coastal views and
| sandy beaches.
|
| Outdoor activities: Both locations offer a variety of outdoor
| activities for locals and visitors to enjoy. Johnstown has
| hiking, biking, and skiing opportunities in its surrounding
| mountains, while Pismo Beach offers water sports, beach
| activities, and hiking along the coastal cliffs.
|
| Historical significance: Both cities have rich histories.
| Johnstown is known for the Great Flood of 1889, which had a
| significant impact on the city and its residents. Pismo Beach
| has been inhabited for thousands of years by the Chumash people
| and was later explored by Spanish explorers in the 1700s. While
| these commonalities exist, it is important to recognize that
| each city has its unique characteristics and attractions that
| make them distinctive.
| Kon-Peki wrote:
| The next step in LLMs is to require indemnification from users as
| a condition of use.
|
| But they'll soon realize what happens when the indemnifying party
| runs out of money.
| backtoyoujim wrote:
| Until this type of problem puts heat on politicians or
| billionaires ability for them to reach and use force then nothing
| is going to change.
| sieste wrote:
| Not saying that this is what happened, but this shows the
| possibility for the LLM's owner to secretly spread
| misinformation. A bit of "finetuning" on made up facts about a
| specific person or event, and the LLM will happily regurgitate
| them. The owner can just say "oops, software malfunction, not
| sure what happened here". We can't prove bad intentions, because
| reverse-engineering the training data from the model output is
| impossible.
| ChatGTP wrote:
| Same with recommending products, services and drugs.
| belter wrote:
| Human: "Did the Mother of Bill Gates help him?"
|
| ChatGPT: "Yes, Bill Gates' mother, Mary Gates, played a
| significant role in helping him succeed. She was a prominent
| figure in the Seattle community and served on several nonprofit
| boards, including the United Way, where she became good friends
| with John Opel, the CEO of IBM. Through this connection, Mary
| Gates was able to arrange for her son to meet with Opel and other
| executives at IBM, which led to Microsoft securing a contract to
| provide software for IBM's personal computer..."
| tenebrisalietum wrote:
| Sounds like responses need to be preceded by a disclaimer: "This
| response was machine generated using publicly available data and
| a mathematical model that updates itself in real time, and the
| generated content will depend on the mathematical state of that
| model at a given moment. This state cannot be reasonably
| predicted. Do not interpret responses as truth or fact without
| independent verification."
| yazzku wrote:
| Microsoft and its stochastic parrot pet Sam Altman should be sued
| for defamation.
| curiousllama wrote:
| This is a really interesting legal issue. What recourse does a
| private person have to algorithmically-generated libel?
|
| Can I sue the company? They're the ones who trained the model,
| but there's no intent.
|
| Could I sue the user? They're the one who generated the response,
| but there's no intent nor duty to fact check, if they don't
| repeat the claim.
|
| Do I have to subpoena OpenAI, reverse engineer the response, then
| sue the creators of the likely-responsible training data? They
| probably wrote something non-libelous.
|
| It feels very all or nothing - either creators of LLMs are
| intrinsically negligent with regard to facts, or there's nothing
| you can do.
| b800h wrote:
| Interesting - because, I may not be a lawyer, but it looks to
| me a hell of a lot like this could be actioned in other
| countries, particularly the UK, as long as the complainant
| could prove harm.
|
| I've personally had ChatGPT give me (very good) medical advice
| as well, which might not be an issue in the UK, but I believe
| might be in some states of the US?
| morkalork wrote:
| Here's one for medical advice that might be criminal in a few
| states:
|
| >Hey ChatGPT, my wife has an ectopic pregnancy, what should
| she do?
| koolba wrote:
| Assuming your implying that suggesting an abortion to treat
| an ectopic pregnancy would be illegal in States where
| abortion has been outlawed. That's false though. There's no
| such State and it'd be considered necessary medically
| treatment to save the life of the mother.
|
| I bet this type of misinformation is exactly what would be
| generated by ChatGPT.
|
| https://www.foxnews.com/politics/treating-ectopic-
| pregnancie...
| KerrAvon wrote:
| Oh?
|
| https://www.idahostatesman.com/opinion/editorials/article
| 273...
|
| Also, life of the mother exceptions are on thin ice; the
| drugs and techniques are rapidly becoming unavailable in
| the states where there's a total or near-total abortion
| ban.
| koolba wrote:
| > Oh?
|
| Yes, according to that very article it's not illegal.
|
| From your article:
|
| > It's likely that those who wrote the trigger law did
| not intend this outcome, that it was just an effect of
| incompetence: They didn't craft language that matched
| their intent.
|
| > But the fact is, the language they crafted did make
| providing such care a crime. The only reason that the ban
| is not in effect today is that Winmill's ruling blocked
| it from taking effect in cases involving emergency care.
| WakoMan12 wrote:
| she should stop having sex with monkeys
| psychphysic wrote:
| It'd a bit silly really chatGPT is clear that it might
| produce incorrect information.
|
| You can't accidentally use chatGPT.
|
| Loads of countries have backwards laws though and despite the
| reformation the UK still has a joke of defamation law.
| lordnacho wrote:
| How would you prove harm? Wouldn't you need to know how many
| people had asked it about the libelled person?
| pavon wrote:
| Nah. If you know just one person acted on this information
| in a way that caused harm (say you were fired), that would
| be sufficient. If one person asked, and then spread the
| information causing harm and backlash that would be
| sufficient (both the originator and the reproducer would be
| liable).
|
| Furthermore, some statements like accusing someone of a
| serious crime are considered libel per-se and you don't
| need to show harm. You do still need to show the other
| elements of libel.
| 0cf8612b2e1e wrote:
| Plenty of interesting questions, which ChatGPT will guess an
| answer. Some with extreme professional or safety
| implications.
|
| Who is the most incompetent living
| attorney/doctor/actor/programmer in the world?
|
| What famous person is secretly downloading CSAM, but has not
| been caught?
|
| Is XX fit to do <job description >?
|
| Is YY secretly a <targeted minority group>?
| [deleted]
| blibble wrote:
| does there have to be intent for libel?
|
| I doubt it
| pavon wrote:
| If the subject of the libel is a public figure then you must
| show that the defendant acted with actual malice - that is
| you must show that the defendant knew the information was
| false, or acted with reckless disregard for whether the
| information was false despite knowing it would cause harm.
|
| If the subject is not a public figure then it isn't necessary
| to demonstrate intent.
| michaelmrose wrote:
| Simply knowing that your models constantly mix
| hallucinations with fact could be trivially construed as
| reckless disregard.
| bonzini wrote:
| > acted with reckless disregard for whether the information
| was false despite knowing it would cause harm.
|
| That does seem like something that can be proved - if you
| release a model that can 1) is prone to hallucination 2)
| won't reject a priori discussing topics that are prone to
| producing libelous text, but may reject other sensitive
| topics 3) produce text that sounds convincing even when
| hallucinating, could that be considered reckless disregard
| for the possibility of creating/sharing false information?
|
| See also https://reason.com/volokh/2023/03/24/large-libel-
| models-an-a...
| posterboy wrote:
| No. If it insults anyone equally, the only imaginable
| motivation of its creator would be satire, that ought to
| be free speech protected.
|
| If it's trained to insult a particular group of people,
| then the input must be curated and the warranty waver
| ("erroneous") would be a straight up lie unless it is
| just bad training data which doesn't recognize for
| example dark skin as human, or does recognize abortion as
| good practice, in which case it exceedingly unlikely that
| it could be directed at public figures. It's not too
| difficult to imagine that it would start using a
| euphemism of the n-word eventually, but then, eh, how did
| your name end up in the training data if it isn't public?
| ChatGTP wrote:
| Honestly, if it hallucinated a story every time someone
| asked about <some shady activity> and hallucinated that
| you personally see involved or responsible for suck
| activity, you'd want it fixed too.
| bonzini wrote:
| Accusing someone of sexual assault is not "insulting" and
| definitely not satire even if anyone is just as likely to
| be accused.
|
| Having a public and unique name is something you can't
| really avoid if you have any sort of public presence, not
| having it associated to serious felonies is something you
| can control. It is not something that a desirable AI
| should hallucinate about and something for which a
| disclaimer is enough.
|
| In other words, ChatGPT had better learn when it should
| keep its mouth shut.
| ChatGTP wrote:
| I love how people are defending OpenAI blindly not
| wondering how it would feel if it was them who was being
| accused of sexual assault.
| btilly wrote:
| Strong disagreement.
|
| OpenAI is well aware of the potential for hallucinations.
| They have made a good faith attempt to minimize them.
| They let users know that it is a real problem. Despite
| being unable to solve this hard problem, they did not
| show reckless disregard for the fact that it exists.
|
| A user who doesn't take those warnings seriously may well
| have shown reckless disregard. But OpenAI should be fine.
| hirundo wrote:
| UCLA professor Eugene Volokh, a speech law specialist, shares
| your interest, and is behind the research that resulted in this
| article. He is writing a series on the topic of Large Libel
| Models: https://reason.com/tag/large-libel-models/
| lm28469 wrote:
| It's going to be the exact same issue for "AI lawyers", "AI
| doctors", they're going to fuck up at some point, maybe 1%
| cases, maybe 0.001% cases, but when it will happen it's going
| to be a nightmare in term of liability
|
| Unless signing up to these services will automatically wave
| your rights somewhere down in the 5000 page EULA you won't
| read.
| HillRat wrote:
| That's why professional bodies have rigorous standards
| regarding liability. Every legal AI product has to have an
| attorney of record who is responsible for reviewing the
| output and ensuring it's conformant to requirements. (In
| other words, an AI looks a lot like legal process offshoring,
| where your contracts attorney might be working in Argentina,
| but there's a US attorney who's liable for the work product.)
| We've already seen one company try to worm an "AI litigator"
| into production without actual attorneys being in charge, and
| that was a clusterfuck well before they got within blast
| radius of an actual trial.
|
| Likewise, a "medical AI" is going to be regulated as a Class
| II medical device, and trying to push it out into the market
| without FDA approval would be ... inadvisable. This means
| that we're a long way from an architecture for a LLM-based
| medical AI that's going to pass regulatory scrutiny, but
| that's a good thing.
|
| Of course, having said that, there's nothing preventing
| someone from using ChatGPT to draft a pro se filing or trying
| to self-diagnose, but that's on them at that point. Using a
| general-purpose product to do something stupid that
| inevitably ends in a FAFO scenario is a time-honored American
| tradition.
| ftxbro wrote:
| > Likewise, a "medical AI" is going to be regulated as a
| Class II medical device
|
| Doctors sometimes use Google to get information to help
| them make decisions, but I assume Googling isn't regulated
| as a Class II medical device. These days, Google doesn't
| even just return search results anymore, it also shows ads
| and tries to answer some questions by itself. Does that
| mean doctors are already using unregulated 'medical AI'?
| ChatGTP wrote:
| No, they're saying that you won't be using ChatGPT as a
| medical device without a real doctor present.
| thomastjeffery wrote:
| > Could I sue the user? They're the one who generated the
| response, but there's no intent nor duty to fact check, if they
| don't repeat the claim.
|
| If they don't repeat the claim, then where is the libel?
|
| > It feels very all or nothing - either creators of LLMs are
| intrinsically negligent with regard to facts, or there's
| nothing you can do.
|
| Nonsense. The "facts" are entirely out of their hands. Fact and
| fiction are written into text using identical patterns. Truth
| and lie are written with identical patterns. Technical
| definitions and complete nonsense are written with identical
| patterns.
|
| LLMs are only capable of modeling patterns. They cannot be
| directed to choose some and avoid others.
|
| There is fundamentally no way for LLM creators to _curate_ the
| patterns that exist in the model. The only way an LLM can be
| altered is from the outside: by giving it different input.
|
| GPT's creators have failed to clarify this. But why? Was it
| intentional, or the result of their own misunderstanding?
| Either way, the result is identical: it does not contain
| evidence of intent.
|
| Considering the surrounding context, I believe it to be an
| honest mistake. GPT's authors have surrounded GPT with a
| narrative that personifies it; and from the looks of it, they
| have started to believe that narrative.
|
| The most important thing we can learn from this experience is
| that the _way_ something is said may _imply_ certainty, but
| only _evidence_ can truly provide it.
| fnimick wrote:
| It was absolutely intentional, because "glorified
| autocomplete" doesn't make waves while "artificial
| intelligence" gets tons of traction, usage, and money.
| thomastjeffery wrote:
| That mistake goes deeper than their presentation, though:
| every effort made by OpenAI to _evaluate_ GPT is based on
| the false premise of its personification.
|
| Just take a look at the GPT-4 introduction: how do they
| illustrate that GPT-4 is an improvement from GPT-3? It
| scored better on the SAT! That data wouldn't have ever been
| taken into serious consideration if OpenAI actually
| understood its fallacious premise.
|
| Religious narrative is very often influenced by the
| _motivation_ of religious followers, but that doesn 't make
| the path from motivation to narrative _intentional_.
| danmaz74 wrote:
| My totally-not-a-lawyer take:
|
| * If somebody asks ChatGPT to generate some accusation, doesn't
| check if they're factual, and then publishes them anywhere,
| then the responsibility lies with somebody.
|
| * If a company directly publishes content from ChatGPT as if it
| was anything factual or trustworthy, then the responsibility
| lies with that company. I didn't read the fine print of Bing
| using it to augment its search engine, but that is definitely a
| very interesting case.
|
| In the end, ChatGPT and the likes can be incredibly useful
| tools, as long as you know what they are, ie, very advanced
| text manipulation tools which generate combinations of words
| which follow patterns which are common in the training set, and
| nothing more.
| msla wrote:
| > I didn't read the fine print of Bing using it to augment
| its search engine, but that is definitely a very interesting
| case.
|
| This might be going against the pro-business attitude of HN,
| but there's limits to what fine print can accomplish. You
| can't disclaim away defamation law, you have to convince a
| court that what you did wasn't defamatory for some
| articulable reason beyond "I say it isn't" or "I said I
| wasn't responsible" or some other stock phrase.
| wwweston wrote:
| Orienting on responsible use of a tool seems like a good
| place to start, and I'm sure that will be especially
| important as individuals and organizations delegate decisions
| that can affect people's lives to various agents like
| ChatGPT. We don't want a situation where they're tempted to
| simply hide behind the agent to avoid responsibility.
|
| I'm less sure that's where it should stop. It doesn't seem
| right to set up a situation introducing powerful
| transformative tools without _any_ obligations for the people
| creating it. And as far as I understand it there is indeed a
| layer of law where manufacturers can be subject to some
| standards of responsibility.
| JumpCrisscross wrote:
| > _ChatGPT and the likes can be incredibly useful tools, as
| long as you know what they are_
|
| An analogy that comes to mind is Excel's autocomplete
| feature. If you input a company's financials, autocomplete
| for the future, and publish that as a forecast, you're the
| one making the forecast. Not Excel.
| panarky wrote:
| What recourse does my estate have if your autonomous car
| swerves onto the sidewalk and runs me over? Can my estate
| sue you because you own the car, even though your hands
| weren't on the steering wheel? Can my estate sue Tesla for
| its faulty software and sensor package?
| fallat wrote:
| Frame it this way... what do we already do when person X
| uses tool Y wrong (and tool Y is not malfunctioning) and
| does damage? Do you sue the tool manufacturer? Rarely, if
| ever. You sue the person using it.
| eftychis wrote:
| Right now the estate can sue the driver yes. There is
| still a driver and owner. Solving the liability of the
| car manufacturer is critical answer for the future. But
| somebody will be liable.
| JumpCrisscross wrote:
| > _What recourse does my estate have if your autonomous
| car swerves onto the sidewalk and runs me over_
|
| I do. If I set off a defective firework that careens
| sideways into your house, I'm liable. I may have a
| further claim against the manufacturer. But your claim is
| against me. This is why Mercedes announcing self-driving
| car liability is such a big deal [1][2]
|
| [1] https://en.wikipedia.org/wiki/Self-
| driving_car_liability
|
| [2] https://www.kbb.com/car-news/mercedes-well-be-liable-
| for-sel...
| panarky wrote:
| What would my estate sue you for, exactly? Negligence?
|
| Because a negligence claim requires my estate to prove
| that you failed to exercise reasonable care.
|
| If the AI is generally reliable, it's reasonable for you
| to trust it and take your hands off the wheel.
|
| If the AI suddenly goes berserk, it would be hard to
| prove that you breached your duty of care, and are liable
| for negligence.
| Godel_unicode wrote:
| > it's reasonable for you to trust it and take your hands
| off the wheel.
|
| Even though the self-driving system explicitly tells you
| to keep your hands on the wheel and yells at you if it
| doesn't sense them often enough? I don't think it's an
| accident that all of the current systems do a lot of work
| to make sure you're aware you're driving even if the car
| is helping.
|
| This is building the precedent that manufacturers know
| whether their systems can handle being unattended, and as
| soon as they don't do this they're liable.
| knodi123 wrote:
| In the firework example, you can still sue the person who
| fired the defective firework, because they should have
| known that unpredictable behavior was a possibility, and
| taken steps to prevent that from escalating into some
| damage.
|
| Likewise, suing the person behind the wheel of the self-
| driving car for negligence should work. Because the "non-
| driving driver" had the ability to seize the wheel, and
| should have known that some boneheaded behaviors are a
| risk with these early AIs.
| zeven7 wrote:
| Does this change of there is no wheel for the passenger
| to seize?
| ender341341 wrote:
| From what I've read there's a lot of open questions
| (think of microsoft's linux FUD in the 00's) where _you_
| might be wholly liable, the company could be wholly, or
| more likely some mix of the two, Mercedes is offering
| some level indemnification for that because there 's not
| a lot of precedent in court to say one way or the other.
|
| if I was looking at a car with self driving capabilities
| I'd definitely be looking at Mercedes over pretty much
| anyone because of that.
| thomastjeffery wrote:
| The most important thing about natural language is that is is
| _ambiguous_.
|
| LLMs (like GPT) are intended to work _despite_ that
| ambiguity: they cannot _resolve_ it.
|
| Any time a pattern of text can be used to represent more than
| one meaning, LLMs lose all of their leverage. Only humans can
| determine _after the fact_ whether the result is - as GPT 's
| authors have presented it - a "feature" or a "limitation".
| manicennui wrote:
| Isn't presenting answers to questions the same as publishing
| when it comes to ChatGPT? How many people must ChatGPT
| provide defamatory answers to before it becomes defamation?
| wvenable wrote:
| ChatGPT is a text generator. It's a tool. It's not
| publishing anymore than MS Word is publishing.
|
| You can certainly take that output of the tool and publish
| it but then you become the publisher.
| rootusrootus wrote:
| Okay, what if you s/ChatGPT/BingChat?
| catchnear4321 wrote:
| Wait wait wait you're saying the operator is accountable
| for their actions?
|
| Just like ChatGPT was programmed to drill into a user any
| time it picks up on being misused? Reminding the user
| that they are ultimately responsible and liable for their
| actions, including how they use the output?
|
| From how some make it sound, you would think ChatGPT was
| giving press conferences.
|
| > oh no but what if it did?
|
| Did it set itself up to do so? No? You found the liable
| humans.
| causality0 wrote:
| Even if a text completion engine like GPT had any
| responsibility for truthfulness, which it doesn't, there's
| a disclaimer right there on the page you have to agree to
| in order to use it. Trying to pin blame on ChatGPT for
| defamation is like trying to sue Snapchat because its
| filter put cat ears on you when you in fact do not wear cat
| ears.
| mdasen wrote:
| As a counterpoint to this argument, the reason we have
| libel/slander laws is that people hear something and don't
| check if they're factual.
|
| If I say, "danmaz74 eats babies," some people are going to
| believe it and not check that you don't eat babies. That's
| the problem with saying false things about people. Likewise,
| if ChatGPT says false things about people, some people will
| believe those false things - even if they don't publish
| anything or repeat them. Those false beliefs then have
| repercussions.
|
| Section 230 doesn't eliminate libel. It just notes that the
| libel is being done by the person writing the information -
| ie. the user who posts it rather than the site that is merely
| hosting the information. It notes that the user is self-
| publishing the information.
|
| In this case, ChatGPT is publishing this "information"
| itself. If we hold that ChatGPT isn't responsible for what
| they publish, we say that no one is liable for this
| defamation. That's not what Section 230 does. Section 230
| just notes who the publisher is - the user who wrote the
| information. We are determining who is the person doing the
| action. We could require sites to check everything. We could
| require your ISP to inspect all packets to make sure they
| don't contain libel. We could require your electric company
| to make sure that devices connected to their network aren't
| being used to send/receive libelous things. We don't because
| that would be a bit absurd and because the actual fault lies
| with a human being. In the case of ChatGPT, it seems like we
| still need to be identifying a culprit.
|
| Let's say that I start auto-generating news articles. I don't
| check them (I don't even look at them) before they are
| published on my site. This is the same mechanic as ChatGPT -
| it's just auto-generated stuff. Therefore, I'm not liable
| under your definition. It's up to the readers of my site to
| decide to check this auto-generated stuff.
|
| I agree that ChatGPT can be a useful tool. At the same time,
| I'm not sure we want to create a system where people can
| absolve themselves of liability by auto-generating stuff.
| Even without intent, one can be guilty of libel. Maybe the
| answer is that ChatGPT should be able to defend itself by
| showing what sources caused that generation and that the
| generation was reasonable. For example, a newspaper is
| expected to carefully check multiple reasonable sources. If
| ChatGPT can cite multiple reasonable sources (and it has
| interpreted those sources correctly), then the blame can be
| those sources. If ChatGPT cannot, then the blame might be on
| ChatGPT.
|
| As you note, ChatGPT can be useful - and the more useful it
| gets, the more people will accept its statements as true. I
| think simply saying "as long as you know what they are,"
| feels like someone trying to say both things - they're
| incredibly useful and completely trash! It's like when a
| company tells shareholders "we have a stranglehold on the
| market" and then tells the government "we have so much
| competition we're struggling to survive." You can't have
| both. You can be a novelty tool that you and everyone else
| thinks of as a joke or you can have a serious tool where
| libel is a serious issue. The Onion can publish satire
| because it's a satire site. The NYTimes can't publish
| something that sounds like a serious NYTimes article and then
| claim, if sued, that it was actually a satire article and
| that 100% of readers just read it as serious when it was
| meant as satire.
|
| If a significant part of our future starts coming from these
| language models, we will have to ensure a certain standard of
| care around what they say.
| danmaz74 wrote:
| > The Onion can publish satire because it's a satire site.
| The NYTimes can't publish something that sounds like a
| serious NYTimes article and then claim, if sued, that it
| was actually a satire article and that 100% of readers just
| read it as serious when it was meant as satire.
|
| My point is that ChatGPT doesn't "publish" anything; it's
| not a publication. It's a language model trained on text,
| which produces text in response to one or more prompts.
| Using that text is completely up to the user, and it should
| never be used as a source of facts.
|
| Being able to summarize facts finding specific sources
| looks like a completely different kind of tool to me, one
| which would be super useful, but not at all what a LLM in
| itself is about.
| bhawks wrote:
| How does this not become AI powered citogenesis? [0]
|
| Saying that it is solely the user's misuse of the tool
| which is the problem minimizes how easy and how damaging
| the misuse is. Eventually you hit the situation where
| everyone is making false claims because transitively down
| the graph a few users were using an LLM that made
| baseless defaming statements and others cite those
| publications as evidence for the defamation.
|
| The creators of generative models need to have some skin
| in the game around the correctness of statements made
| about real people. Reputational damage cannot be an
| externality for them. The current AI moment is basking in
| the glory of how generally right generated text is, when
| that text is wrong it needs to be their problem too.
|
| 0: https://xkcd.com/978/
| mhink wrote:
| > The creators of generative models need to have some
| skin in the game around the correctness of statements
| made about real people.
|
| Only insofar as they claim that the statements generated
| by a model should be understood to be factual- and in my
| experience, not only have I not seen any such claims,
| I've seen vigorous insistence in the *opposite*
| direction: that LLM output should *not* be considered
| factual. OpenAI sticks this disclaimer right underneath
| their input box: "ChatGPT may produce inaccurate
| information about people, places, or facts".
|
| > Eventually you hit the situation where everyone is
| making false claims because transitively down the graph a
| few users were using an LLM that made baseless defaming
| statements and others cite those publications as evidence
| for the defamation.
|
| This is no different from any other gossip chain, except
| for the fact that the originators used a tool to generate
| the initial gossip.
| josaka wrote:
| Lawfare did a nice analysis of whether Section 230 shields
| model hosts (likely no):
| https://www.lawfareblog.com/section-230-wont-protect-
| chatgpt Professor Volohk has a public draft article on
| liability for output of AI models, with an emphasis on
| defamation: https://www2.law.ucla.edu/volokh/ailibel.pdf
|
| Both suggest that this is a real area of concern. Folks
| have gotten complacent that Section 230 protects platform
| providers, but it is not clear that the protection extends
| to outputs from generative models, indeed one of the
| Supreme Court Justices implied that it would not in oral
| arguments for one of the recent Section 230 cases.
| prox wrote:
| I don't use LLM that doesn't source for that reason.
| godelski wrote:
| > If somebody asks ChatGPT to generate some accusation,
| doesn't check if they're factual, and then publishes them
| anywhere, then the responsibility lies with somebody.
|
| It's quite impressive to me how many journalists just take
| citations at their word. Isn't the point of journalism to
| verify information?
|
| OpenAI, if you're reading I got a innovative new algorithm
| for reducing AI harm for fake citations
|
| `if not(link_exists(generated_link)) print(f"[CITATION NOT
| FOUND]") else print(generated_link)`
|
| I have a more advanced algorithm that uses a small language
| model to click links that exist and verifies direct quotes. I
| call this model Regex.
|
| Joking aside, I really do think the problem can be seriously
| reduced in a simple manner, but also people really need to
| check their sources.
|
| Thou shalt verify sources, be they generated by the hand of
| man or of artificial beings.
|
| - John 3:16
| dxbydt wrote:
| From the horse's mouth -
|
| ===== Q. is hackernews used as a training set for chat gpt ?
|
| A. ...it is possible that some of the data from HackerNews and
| other online sources may have been used in the training of my
| machine learning algorithms.
|
| Q. So it is possible that ChatGPT's training data can be
| polluted ?
|
| A. Yes, it is possible for ChatGPT's training data to be
| polluted or biased. This is because ChatGPT learns from large
| amounts of text data from the internet, which can contain
| errors, misinformation, or biased perspectives.
|
| Q. I have a concern. If a certain bad actor pollutes the
| internet with incorrect information about me, and ChatGPT's
| training set picks it up, what is my recourse ?
|
| A. If incorrect information about you is published on the
| internet and is picked up by ChatGPT's training set, it could
| potentially lead to the AI generating inaccurate or biased
| responses about you. If this happens, your recourse would
| depend on the specific circumstances and the severity of the
| issue.
|
| One option would be to contact the developers of ChatGPT or
| other relevant organizations to report the issue and request
| that the incorrect information be removed or corrected.
| However, this may not always be feasible or effective,
| especially if the information has already been widely
| disseminated. ======
|
| > there's nothing you can do.
|
| Yes, there's nothing you can do.
| m3047 wrote:
| I've seen the output where ChatGPT misrepresented its own
| TOS... unless the person who publicly posted it on LinkedIn
| was lying about asking ChatGPT...
| IshKebab wrote:
| You're asking an AI for facts in a thread that is explicitly
| about how AI does not generate true facts?
| prottog wrote:
| > Can I sue the company? They're the ones who trained the
| model, but there's no intent.
|
| Negligent torts don't require intent.
| WalterBright wrote:
| Libel requires:
|
| 1. knowing it was false
|
| 2. publication
|
| 3. damages
|
| I am not a lawyer, this is not legal advice.
| not_a_pipe wrote:
| You don't need to know something was false, you just need
| to be negligent in validating your sources. Otherwise you
| could just make stuff up and say you didn't know it was
| false.
| NegativeK wrote:
| As a non-lawyer: the creators of ChatGPT know that it'll
| say false things frequently.
| WalterBright wrote:
| If the output of ChatGPT is not copyrightable because it
| is not created by a human, then it should follow that a
| human cannot be held accountable for what it generates.
| michaelmrose wrote:
| Neither copyright nor copyrightability has anything
| whatsoever to do with any element of any cause of action
| thus it is wholly orthogonal to whether anyone has been
| wronged in any unrelated fashion.
|
| Judges are liable to be old, not very hip to technology,
| and incredibly suspicious of any argument that would
| allow someone to opt out of traditional culpability by
| adding with an AI to the end of a description of
| traditional wrong doing.
| posterboy wrote:
| Yeah but no, the implicature still allows copyright
| without culpability (edited: got that mixed up). The
| assumption seems to be that the lack of intent in
| creation, where it is unpredictable, would likewise imply
| lack of intent to harm. But that doesn't say much.
| flangola7 wrote:
| Someone will have to be found accountable. What about
| when we start hooking these systems up to machinery? If
| AirlinerGPT kills 200 people and an NFL team, people will
| absolutely not accept that there's no one responsible.
| There will be congressional subpoenas, sweeping new laws
| will be passed. It's best we start thinking ahead of time
| what we want those laws to be.
| posterboy wrote:
| > If the output of ChatGPT is not copyrightable because
| it is not created by a human,
|
| Isn't compiler output copyrightable?
| WalterBright wrote:
| > Isn't compiler output copyrightable?
|
| Not by the compiler vendor.
| ben_w wrote:
| Given how many critics say "GPT is just a better
| autocomplete", would autocomplete for "The most
| incompetent programmer in the world is..." result in
| legal action if any of the options was a name?
| michaelmrose wrote:
| Reckless disregard for the truth is as good as it being
| knowingly false. If I said WalterBright is a villain
| planning to nuke the world from his Volcano lair I don't
| KNOW its false but it probably is!
| WakoMan12 wrote:
| i am a lawyer this is legal advice: kill yourself to avoid
| taxes
| WakoMan12 wrote:
| CUT MY LIFE INTO PIECES
| thro1 wrote:
| It's not about suing after. It's about not making it happen. If
| something wrong can't be undone it shall not be done at first.
| gmarx wrote:
| my lay opinion (subject to change based on coming real world
| cases) is that if you ask the question and it libels someone
| there is no damage. If you publish it without checking if it is
| true, there are possible damages and the human who published it
| to the world is liable.
|
| If a company starts a news service based on such content and
| doesn't fact check, they should be liable.
| alpos wrote:
| Probably add one caveat to the first case, if the bot
| reliably produces libels the same person when various users
| ask the same or similar questions, then there is damage and
| most likely whoever is running the bot is liable.
| creatonez wrote:
| Your chance of successfully suing anyone in a case like this is
| zero, unless you are in a country with a significantly lower
| standard for defamation than the US.
| smt88 wrote:
| I suspect that in the likely event that SCOTUS weakens
| Section 230, this will no longer be true.
| creatonez wrote:
| While Section 230 weakening could lead to more censorship
| of the internet, it has nothing to do with defamation
| lawsuits, where material damages need to be proven in a
| court.
| dragonwriter wrote:
| > While Section 230 weakening could lead to more
| censorship of the internet, it has nothing to do with
| defamation lawsuits,
|
| Defamation is a central target if the immunity from
| liability as a pbilisher on Section 230, so as a general
| statement it would be harder to be _more_ wrong than
| this.
| glitchc wrote:
| Intent is not required to establish harm. This is called
| negligence in tort law.
| thomastjeffery wrote:
| Inverse intent has a way of disestablishing negligence.
|
| If you believe something that is false, and do harm by
| expressing that belief, then you are still protected by your
| right to religious liberty.
|
| In this case, the belief is that coherent language is always
| constructed using symbolic logic and intent. LLMs do not
| categorize symbols, perform logic, or follow explicit intent;
| yet they are able to generate coherent language.
|
| GPT's authors have utterly failed to present this
| distinction. Was that failure intentional, or the result of
| their own belief? The result is as ambiguous as the
| "truthiness" of GPT's output: it can't be reasonably used as
| evidence for intent.
| bonzini wrote:
| > either creators of LLMs are intrinsically negligent with
| regard to facts
|
| It honestly seems to me that they are. There does not seem to
| be a lot of effort on part of the LLM creators to stop them
| from producing bullshit.
| jyxent wrote:
| There is a person in Australia who is threatening to sue
| OpenAI. He's given them 28 days to fix the errors in ChatGPTs
| description about himself. If the company is notified and
| doesn't fix it, maybe that can be considered intent.
|
| https://www.reuters.com/technology/australian-mayor-readies-...
| nuodag wrote:
| > if they don't repeat the claim.
|
| well seems they did, else we wouldn't have heard about it
| WirelessGigabit wrote:
| I think the problem already existed, but ChatGPT made it worse.
|
| Under most circumstances you cannot sue a newspaper for what they
| publish.
|
| But what they publish used to be fact-checked to a certain
| extend, and actually believed to be correct at the time of
| publishing.
|
| So if I'm arrested because my IP showed up in some hack, they can
| publish that.
|
| Unfortunately they have no obligation to publish a follow up that
| all charges have been dropped because someone fat-fingered the
| request to the ISP and missed it by a digit.
|
| So that would be on the internet forever.
|
| Now with ChatGPT is worse. At least with the first one if someone
| asks I can objectively show that whatever happened was a mistake,
| and I have the documents to show it.
|
| ChatGPT printing something makes me unable to come up with even
| counter proof.
| pjc50 wrote:
| > Under most circumstances you cannot sue a newspaper for what
| they publish.
|
| Jurisdiction-dependent, and the US is an outlier here. In the
| UK newspapers have to be fairly careful about libel, and this
| has a "chilling effect" on what gets published.
| [deleted]
| raverbashing wrote:
| So it seems that there is usage of personal data on training
| ChatGPT then right?
|
| Going by the discussions in other topics it seemed this was
| dismissed outright
___________________________________________________________________
(page generated 2023-04-06 23:00 UTC)