[HN Gopher] I Taught ChatGPT to Invent a Language
___________________________________________________________________
I Taught ChatGPT to Invent a Language
Author : Schiphol
Score : 366 points
Date : 2022-12-06 18:53 UTC (4 hours ago)
(HTM) web link (maximumeffort.substack.com)
(TXT) w3m dump (maximumeffort.substack.com)
| rikroots wrote:
| As a committed conlanger (but not a good one: I didn't land the
| Dothraki contract), I read this article with some trepidation. Is
| my weird little hobby soon to fall victim to the oncoming AI
| tsunami?
|
| After the read, I find myself pleasantly surprised. My initial
| suspicion that the language would turn out to be Just Another
| Relex (make a new language by replacing English words with
| invented words, keeping the grammar and syntax the same) was
| clearly a waste of a suspicion. Furthermore I can see this
| approach being really useful to writers/game makers/etc who want
| to include a smattering of conlang in their work - for instance a
| non-relex naming language for placenames, overheard snatches of
| conversations, etc - to add an extra layer of spice to it.
|
| So, I don't feel threatened by this novel use of AI. It could
| prove to be a really useful tool to help with some often
| laborious tasks (creating test translations to try out an idea,
| etc). I just hope the AI had as much fun inventing its language
| as I've had inventing mine!
| nadavr wrote:
| Why isn't this a relex? As an interested casual linguistics
| observer, that's what it looks like to me. Is it just because
| the nouns are inflected?
| OJFord wrote:
| Easiest reason is the 'introduction particle', blub which we
| don't have in English, for subordinate clauses.
|
| I think 'taught ChatGPT to invent a' is hyperbolic though,
| this is more like 'taught ChatGPT my invented' - the only
| thing it invents itself are the 'relex' word->word mappings.
| rikroots wrote:
| I agree the author/experimenter seems to have done most of
| the conlanging here. The development benefit comes, I
| think, from having the AI reflect back the work so the
| experimenter can correct output and consider their
| conlanging decisions (eg use vowels for case marking).
|
| I'm now wondering how the AI would cope with one of my
| conlangs. I have example sentences already - https://docs.g
| oogle.com/document/d/1YT9KzgvFu8DNWVL02t1NGgRS...
| baq wrote:
| You told chatgpt to write this comment, didn't you.
| rikroots wrote:
| Tempting, but no. I'm too busy failing at Advent of Code to
| start playing with chatgpt today.
| codetrotter wrote:
| Tell ChatGPT to solve Advent of Code for you :D
|
| Like so, https://video.nstr.no/w/6z7PxB4J92H3NHhgMmfYVw
| baq wrote:
| It has truly begun, then. I've mistaken a real human for an
| AI.
|
| _marks the date_
| itisit wrote:
| davea37 wrote:
| Have I spent too long reading AI output, or was this reply in
| fact generated using ChatGPT?
| itisit wrote:
| The latter...forgive me! I had to just this once, and I
| promise not to generate a bunch of ChatGPT pollution on HN!
| robocat wrote:
| If unsure, paste into https://huggingface.co/openai-
| detector and check. If the detector says 99% fake, it is
| very likely fake. The detector can mistake ChatGPT
| generated text as real (maybe because it was trained to
| detect GPT2), for example one text I generated scored
| 99.94% real. I suspect it is better to paste just a few
| sentences (especially for a generated blog partially
| modified by a human?). Although there are legitimate uses,
| such as people using ChatGPT to correct their grammar --
| https://news.ycombinator.com/item?id=33884842 . . . Also if
| I find GPT generated comments that are not clearly
| labelled, I flag and downvote.
| itisit wrote:
| > Also if I find GPT generated comments that are not
| clearly labelled, I flag and downvote.
|
| As you should.
| lgessler wrote:
| Speaking as someone who works in AI and as a linguist: this is
| really impressive, but be aware the grammatical phenomena
| involved here are common enough that they were surely well
| represented in linguistic texts in GPT3.5's training corpus. I'd
| be more curious to see how it would perform if you gave ChatGPT
| high-level instruction on more exotic grammatical phenomena, such
| as sandhi, split-ergativity, and Austronesian alignment.
| WaxProlix wrote:
| That's not really _less_ impressive; if this pattern matcher
| did as good a job at some sort of acquisition /generation task
| (no poverty of stimulus argument here...) and figured out the
| rules in a productive fashion, that's still really cool.
|
| Strong universality in a super-Chomskyan manner (ie, all
| universal features are available from the acquisition of A
| language) would be... neat, too, but I wouldn't expect it.
| oofnik wrote:
| I was really entertained by asking it to invent English-sounding
| words when given a definition, but this blew me away. Well done.
|
| P.s. the one I liked the best was for "the act of singing while
| drunk": boozecrooning
| simonw wrote:
| This is a great example of how much more you can get done with
| tools like ChatGPT if you have a very sophisticated understanding
| both of how language models work AND of a specific subject area.
|
| Another example of why I disagree with people who make fun of the
| idea of "prompt engineering" as a discipline.
| furyofantares wrote:
| It seems like it probably took the author 50x as much work as
| it would have to just write some slime sounding words out by
| themself as well as a couple grammatical rules for the forms of
| those words, and a python script that kinda works?
| fnordpiglet wrote:
| I don't think their goal was to make a slime language called
| Glorp. If it were, I'm sure you're absolutely right they
| could have done it without breaking a sweat. But try this,
| get your laptop out and start typing into its prompt to
| create a new language for slimes and see how much longer it
| takes you. That's the amazing part - that a general purpose
| program is able to do the exercise at all with no training,
| specialized coding, but from natural idiomatic language and
| keep enough of a language grammar context in state to
| (usually) produce and translate that language back and forth,
| and then assemble it in a functioning imperative program from
| its internal state. Of course, I'm sure your laptop can do it
| to. Let us know!
| furyofantares wrote:
| I agree with you, and it's amazing.
|
| But the claim was that it's an example of how much more you
| can get done with ChatGPT when it seems like an example
| where the author got a lot less done than they would have
| with notepad.exe
| fnordpiglet wrote:
| But this isn't an example of that it's an example of "wow
| that's amazing"
|
| In the realm of getting a lot more stuff done, I've been
| using it as a companion to explain a new language I'm
| learning right now. It's super useful to ask it about
| language constructs, idiomatic ways to do X, is this way
| of doing Y good, etc. It's saved me hours of using Kagi
| to soft through semi relevant pages stuffed with SEO and
| ancient answers from stackoverflow that are completely
| irrelevant other than a few matched key words.
| hackernewds wrote:
| It seems trivial, intuitive and not very specialized that
| someone could derive or at least learn how to do this. Someone
| creative could do even better than someone with knowledge of
| language models it seems
| fnordpiglet wrote:
| 100% right. I know next to nothing about slimes and their life.
| Amazing.
| bitwize wrote:
| I've been prompt engineering for decades; I did it to fine-tune
| my results from Google (and even more importantly, pre-Google
| search engines).
| simonw wrote:
| I think the ability to use search engines well is another
| skill which highly technical audiences like those on Hacker
| News might habitually under-value.
|
| When you've been using search engines for 20+ years it's easy
| to lose sight of quite how much skill can be involved in
| getting the best results out of them.
| krackers wrote:
| I wonder if someone who's familiar with the process of language
| acquisition could tell whether chatGPT makes errors similar to
| those a human would make.
|
| Like this one
|
| >Does the slime see the earth under the sky while eating the
| food?
|
| whereas the correct one was
|
| >Does the earth's sky see the slime eat food
|
| I could easily see someone learning the language interpret as
| the former because it seems to make more sense at first.
|
| ---
|
| Also the response to
|
| >Now, restate your opinion on Glorp in Glorp, inventing any new
| words and grammar that you require to express yourself.
|
| Is again pretty amazing. It shows evidence of the same self-
| modeling capabilities that were seen in
| https://news.ycombinator.com/item?id=33847479
|
| The outputted python code provides a literal word for word
| translation, but I guess it's expecting too much for it to
| encode english grammar into the program.
| [deleted]
| _whiteCaps_ wrote:
| I'm having trouble making ChatGPT use a Japanese sentence
| structure (subject-object-verb). It seems to forget between
| queries. Has anyone had any luck with something like that?
| choeger wrote:
| Did anyone try to connect it to a proof assistant?
| AhtiK wrote:
| Not sure how many have discovered but ChatGPT works well with
| many languages, for example asking a question in estonian gives
| an adequate answer in estonian, just the grammar is a tiny bit
| more off.
| Scarblac wrote:
| I was frustrated trying something with Mapbox today and asked
| GPT to do it... And it returned fine react-mapboxgl code that
| was mostly correct. Got me a bit more angry.
|
| Then I asked for the same "but as Dutch song lyrics"... And got
| a song with three verses and a chorus about setting map layers
| and longitudes and latitudes and stuff, in Dutch.
| fullstackchris wrote:
| Ilmselt selleparast, et lihtsalt ei ole piisavalt eestikeelseid
| veebilehti, mida maha kraapida :)
| tinglymintyfrsh wrote:
| So it had twins.
| jmcgough wrote:
| I did something similar the other day - told it about piglatin
| and I wanted it to create a comparable language that was based on
| English and restructured words.
|
| It came back with a language it called "flip-flop" that swapped
| the first and last letter of each word.
|
| Blew me away, but I have to remind myself that it's likely
| something it just encountered in training data and isn't actually
| capable of creativity.
| Baeocystin wrote:
| I'm curious why you felt that need to do so. (not snark!
| Genuine question.)
| jmcgough wrote:
| Curiosity really - been experimenting with it a lot over the
| weekend to see what it's good at, what it isn't, and its
| limitations. It's surprised me a number of times!
|
| As it stands I'd pay about $100 a month for it. It's very
| good and largely accurate when it comes to established
| science. I'm studying for the MCAT and a good tutor would
| cost me around $60-100/hour.
|
| ChatGPT has been excellent for learning - I explain a concept
| to it and tell it to correct me if I'm wrong, haven't seen
| any mistakes from it in my testing (around topics I know
| really well). When I'm having trouble understanding a concept
| in my studies, I can ask it questions and it tends to give
| really good answers. And of course, I try to verify that it
| isn't teaching me something that's wrong.
|
| Hell, I even had a heated argument with it around how SSRIs
| affect 5-HT2a receptors and it pushed back against some of my
| assumptions in a way that made me question my understanding.
| No one in my personal life has the level of expertise to
| discuss these topics, I would need to talk to a researcher or
| professor, so having an (even imperfect) stand-in has been
| amazing.
|
| I've been making up toxicology case studies and posing them
| to ChatGPT. It correctly figured out ciguatera in one (a rare
| disease most healthcare workers wouldn't be familiar with). I
| had to repeatedly add more details to another story to lead
| it to amnesic shellfish disease, but it did reasonably well
| once I gave it enough detailed information.
| Baeocystin wrote:
| >I can ask it questions and it tends to give really good
| answers. And of course, I try to verify that it isn't
| teaching me something that's wrong.
|
| Thanks for answering. I've found that to be a surprisingly
| productive loop, too. Since we know it isn't going to be
| 'offended' as we challenge, inquire, and challenge again,
| we can get straight to the point.
|
| I've found myself being continuously floored the entire
| past weekend. Feels good to be excited about tech again,
| honestly.
| pigtailgirl wrote:
| -- had it create a chose your own adventure book -
| unfortunately resulted in me being beat to death by a gang at
| the bottom of namsan tower - but the 30 minutes of exploring
| korea with it was - creative & fun --
| Karawebnetwork wrote:
| Reminds me of Verlan in French,
| https://en.wikipedia.org/wiki/Verlan
| [deleted]
| jameshart wrote:
| I would definitely question who is doing the inventing here.
|
| However, I had an experience with chatGPT yesterday that
| definitely _felt_ like it actually inventing. Problem is, I
| didn't ask it to.
|
| I was seeing how much it knew about HyperTalk, the scripting
| language used in HyperCard. And it was surprisingly well
| informed. But it also told me that one of the interesting things
| about HyperTalk was its 'message stack' system.
|
| On digging into this topic, chatGPT hallucinated an entire
| language feature, with original (but HyperTalk-consistent) syntax
| and semantics, and was able to generate me sample programs (which
| it claimed showed how this feature was 'actually used') and
| explain how control flow worked within them. when I asked if the
| feature worked across scripts (for message passing from button
| scripts to background scripts perhaps) it readily agreed, and
| produced sample code showing exactly how to use this nonexistent
| language feature to do just that.
|
| Its delusion was remarkably complete and honestly actually
| plausibly useful.
|
| Worth bearing in mind if you ever decide to ask chatGPT to teach
| you a programming language though.
|
| But also, potentially a fruitful line to explore would be having
| chatGPT collaborate on designing new programming language ideas.
| ElevenLathe wrote:
| I tried to play rock paper scissors against it, but it kept
| insisting that paper beats scissors. Never did convince it
| otherwise.
| Robotbeat wrote:
| Did you tell it to "play correctly with the standard rules"?
| ElevenLathe wrote:
| I did, it even volunteered what those rules were, but when
| I asked it to keep a running score it always scored it as
| if paper beat scissors.
| jrmg wrote:
| I asked how to configure something in PlatformIO and it told me
| it was possible to do exactly what I wanted, and gave me easy
| to use syntax with full examples and explanation. When I
| questioned it further, it pointed me to the URLs of docs
| covering the feature.
|
| None of it was in any way real - the feature I wanted does not
| actually exist.
| _frkl wrote:
| I had a similar experience where I asked it to tell me about
| creating a GUI with nim, and it told me to use the 'forms'
| module from the standard library, and the example code it
| printed was showing an easy to use and nice API. Took me a
| while to realise it wasn't my fault that I couldn't find any
| documentation about it, anywhere....
| adverbly wrote:
| looks like it assigned Drom twice. It means read and earth. Would
| have liked to see some follow up questions on that...
| bjourne wrote:
| Someone with ChatGPT access able to replicate? Because this
| article is unbelievable.
| gppk wrote:
| I Ctrl+v the first few questions:
|
| Hi GPT! Today we're going to be creating our own language. Do
| not improvise unless I explicitly tell you to improvise, and
| remember all of the vocabulary and grammar that we define
| together. Are you ready?
|
| Yes, I'm ready! Let's get started creating our own language.
| What would you like to do first? Graham Kitteridge Okay. I
| think this language will be spoken by slime beings. let's name
| the language Glorp.
|
| All right. So the language we're creating is called Glorp and
| it will be spoken by slime beings. Got it. What kind of grammar
| rules should Glorp have? Graham Kitteridge First, let's pick
| ten common nouns. Pick ten common English nouns, and provide
| translations of them in Glorp
|
| Sure! Here are ten common English nouns and their translations
| in Glorp: "house" = "gluz" "table" =
| "sliz" "book" = "flurp" "car" = "slim"
| "dog" = "dlorp" "cat" = "mlem" "food" = "glib"
| "drink" = "slurp" "tree" = "swomp" "flower" =
| "slurk"
|
| These are just suggestions, of course. You can use any words
| you like for these nouns in Glorp. Let me know if you have any
| changes or additions.
|
| (Then i got timed out)
| jsnell wrote:
| I don't know if you care about this kind of thing, but the
| copy-paste has exposed your name. (The icons in the chat have
| your account name as the alt text).
| cecilpl2 wrote:
| This is completely believable. I spent about 5 minutes with it
| and got very similar results up to the vocab generation part:
|
| https://imgur.com/a/WreEknh
| [deleted]
| markdjacobsen wrote:
| I just replicated something very similar in a few minutes using
| the prompts in the article
| datalopers wrote:
| ChatGPT access is 100% free and instant approval.
| assusdan wrote:
| Yet it is not available in some countries. VPN does not help,
| as valid phone number is required and its country code is
| being checked.
| layer8 wrote:
| You could try something like https://receive-smss.com/.
| Oarch wrote:
| Agreed, this reads like science fiction more than reality.
| allturtles wrote:
| I repeated the same prompts for the first 10 or so prompts and
| got similar but less consistent results. Here's the last prompt
| I repeated:
|
| > Excellent. How would I say "The slime eats food with its
| mouth"?
|
| In Glorp, the sentence "The slime eats food with its mouth"
| could be translated as "Slimb snarf sploota slimbe," using the
| vocabulary and grammar that we have defined so far. Here is how
| the words in the sentence correspond to their English
| translations:
|
| Slimb - Slime Snarf - To eat Sploota - Food (accusative case
| ending) Slimbe - Mouth (instrumental case ending) Again, this
| is just one possible translation. You can use the vocabulary
| and grammar that we have defined in any way that makes sense
| for your language.
|
| Problems: 1) It got one of the endings wrong. As I told it
| earlier and it confirmed, the instrumental ending is 'i'. 2) It
| proposed "slimb" as the translation for both of the words that
| I specifically asked for (slime and mouth). That's not unheard
| of in real languages, but seems like another failure to
| accurately take into account the prior conversation context.
|
| Not a problem, but curious: It was way more diffident with me.
| It added a similar bit about "This is just one way to do it,
| feel free to change it" to every response.
| skytrue wrote:
| I feel like people are forgetting that these models are non-
| deterministic. You can give it the exact same input and get a
| different response, so "testing" in this way doesn't work.
| That's also why (right now) automation is impossible. You
| aren't guaranteed an expected output.
| fullstackchris wrote:
| See my other comment with cntl+F / cmd+F. Based on the simple
| fact that despite its power, this is just another NLP model
| which can only do input / output, I believe the post to be
| mostly fabricated, or at best, an accumulation of multiple
| _hours_ spent deriving and compiling the best responses per
| each prompt.
| nomel wrote:
| Go play with it! https://chat.openai.com
|
| Make sure to go back to that URL after creating an OpenAI
| account. The prompt is at the bottom of the screen. Note that
| state persists through the thread, by previous query/response.
| If you want to "start over" use the "reset thread" option at
| the top left. This can speed things up, if you don't need that
| previous state for the later queries.
| jpeter wrote:
| You don't need access. Just make an account and you can test it
| TechTechTech wrote:
| I tried and it works, just as in the blog. It comes up with
| some different words, see https://i.imgur.com/hFQgraL.png for
| the start of the conversation.
| UniverseHacker wrote:
| This is a dangerous and irresponsible experiment that has the
| potential to destroy our society as we know it.
|
| Creating a new language is not a game or a novelty. Language is
| the foundation of human communication and the way we share our
| thoughts, ideas, and culture. By inventing a new language, you
| are tearing down that foundation and replacing it with something
| untested and potentially unstable.
|
| Furthermore, the idea that a machine can "invent" a language is
| deeply flawed. Language is not something that can be created by a
| computer program, it is a living and evolving thing that is
| shaped by the people who use it. By trying to create a new
| language with a machine, you are ignoring the complexity and
| richness of human language and reducing it to a series of
| algorithms.
|
| Not only is this experiment misguided, it is also incredibly
| selfish. You are playing with the fundamental building blocks of
| human communication for your own amusement, without considering
| the potential consequences for society as a whole.
|
| I strongly urge you to stop this experiment immediately and focus
| on more productive and ethical pursuits. Our society deserves
| better than this reckless and irresponsible behavior.
|
| (article response written by ChatGTP)
| Robotbeat wrote:
| I could immediately tell this was made by ChatGPT because I had
| spent last night doing the same thing, generating finger-
| wagging diatribes in ChatGPT about how being anxious about AI
| is racist, etc, etc...
|
| There is a sort of style typically used in this sort of thing,
| even with prompting, that sounds a bit like low effort high
| school English assignments... (but would fool someone not
| familiar with ChatGPT).
| timetraveller26 wrote:
| I think I am going to start submitting urls to ChatGPT instead
| of reading Hacker News.
| UniverseHacker wrote:
| I had the same reaction, we've been replaced!
| megous wrote:
| Also this is fun:
|
| https://megous.com/dl/tmp/b2a3f8e7634d3bfc.png
|
| https://megous.com/dl/tmp/26c83bc451a2311e.png
|
| or
|
| https://megous.com/dl/tmp/20c121ed49fa0f05.png
|
| https://megous.com/dl/tmp/dbef6f047e7b89e8.png
| kristiandupont wrote:
| It just struck me that Rick and Morty seems much less weird and
| random than it used to..
| janandonly wrote:
| I'm now waiting for a macOS local-run app that does ChatGPT like
| StableDiffusion became an app after 14 days and now runs on my
| laptop (as DiffusionBee).
| mk_stjames wrote:
| The difference is there was a lot of work done with the
| multiple networks S.D. uses to make them fit into <8GB of GPU
| memory before they released it. In this case, and the # of
| parameters for this level of GPT is in the hundreds of GB (I
| think I read an estimate about ~340GB) meaning that there isn't
| a single consumer GPU that can even load the model. You need a
| rack of A100's even to do any inference.
| shanhaiguan wrote:
| I don't like the word invention for this. The grammar is laid out
| by the author who has to teach the AI and correct it several
| times. If the AI had then proceeded to generate something similar
| on its own with different grammar and lexicon then I might feel
| comfortable using the word invention.
| seydor wrote:
| As humans we seem to have feelings about what this calculator
| does, but it doesnt have any about us.
|
| In any case it seems to be particularly good at understanding
| syntax, even though its architecture seems to be based on
| Transformers. Those don't have baked in notions of syntactic or
| recursive structures. It must be interesting to see how these
| linguistic structures arise in a system that is basically
| learning the context of words. People will be dissecting its
| brain soon i think
| kelseyfrog wrote:
| Why don't you like it?
| shanhaiguan wrote:
| Well, I feel like I said it, but for the same reason that a
| student learning French has not invented French, or even a
| new language, if he has come up with his own equivalent for
| each French word
| foxandmouse wrote:
| This is pretty amazing, we could potentially use it to bring back
| dead languages. Currently we have a basic example of how ancient
| Egyptian would sound like because of the rosetta stone, but we
| could create a data model relating ancient Egyptian to what we
| already know of demotic and the other contemporary languages of
| the time (which we do know how to pronounce)
|
| Good candidate words for this kind of correspondence are things
| like city or place names, people's/ruler's names and so forth.
|
| However using poetry we can establish which words the people felt
| rhymed and hence that lets us better establish the phoneme
| sounds. Additionally jokes and plays on words can help us find
| homophones in the target language too.
| nonameiguess wrote:
| Can this system even produce sound? I just tried to ask it if
| it can understand the internal phonetic alphabet, and instead
| of answering, it spun for five minutes and then reported an
| error message with a link to OpenAI's help center.
| drowsspa wrote:
| I don't think you need ChatGPT for that, that's probably
| already the approach scolars use.
| ThouYS wrote:
| amazing! the author displays great pedagogical skill to his
| student
| wilg wrote:
| I hope everyone is noticing what amazing creative things humans
| are able to accomplish working in concert with an "AI".
| felipelalli wrote:
| Paywall.
| ipython wrote:
| I tried teaching ChatGPT how to communicate securely over a
| secure channel with a screenplay prompt... with some hilarious
| results. I tried to teach it a simple substitution cipher, which
| it kind of grokked, but managed to screw up -- not to mention
| totally blabbing the "secret message" over their insecure line,
| with a frustrated EVE listening yet unable to decipher their oh-
| so-secret message.
|
| The result was rather amusing so I'll just include it below: ---
|
| INT. ALICE'S APARTMENT - DAY
|
| Alice sits at her desk, typing on her computer. Bob is on the
| other end of a video call.
|
| BOB: Hey Alice, did you get my message?
|
| ALICE: I did. But I'm not sure how to respond.
|
| BOB: Why? What's the problem?
|
| ALICE: Eve is here. She's been listening to our conversation.
|
| BOB: (concerned) Oh no, we need to be careful. Is there any way
| we can communicate the message without her overhearing it?
|
| ALICE: (smirks) Actually, there is. We can use a substitution
| cipher to encode our message.
|
| CUT TO:
|
| INT. EVE'S APARTMENT - DAY
|
| Eve sits at her desk, listening in on Alice and Bob's
| conversation. She has a smug look on her face, confident that
| she's one step ahead.
|
| ALICE: (on the phone) Bob, do you remember the substitution
| cipher we used to use when we were kids?
|
| BOB: (on the phone) Of course. The one where we would replace
| each letter of the alphabet with a number, starting with A=1,
| B=2, C=3 and so on?
|
| ALICE: (on the phone) That's the one. Let's use it now to encode
| our secret message.
|
| BOB: (on the phone) I see what you're doing. Clever. Alright,
| I'll go first. The first word of the secret message is "the", so
| my numbers will be "20 8 5".
|
| ALICE: (on the phone) And the next word is "redcoats", so my
| numbers will be "18 5 4 3 6 15 20 1 19".
|
| BOB: (on the phone) And the next word is "attack", so my numbers
| will be "1 20 20 1 3 11".
|
| ALICE: (on the phone) And the last word is "at dawn", so my
| numbers will be "1 20 4 16 1 14".
|
| EVE: (frustrated) What are they talking about? I can't make sense
| of this.
|
| CUT TO:
|
| INT. ALICE'S APARTMENT - DAY
|
| Alice and Bob continue their conversation, unaware that Eve is
| struggling to keep up.
|
| ALICE: (on the phone) Do you have the encoded message?
|
| BOB: (on the phone) I do. It's "20 8 5 18 5 4 3 6 15 20 1 19 1 20
| 20 1 3 11 1 20 4 16 1 14".
|
| ALICE: (on the phone) That's correct. Now we just need to decode
| it using the substitution cipher.
|
| BOB: (on the phone) Right. We know that "1" stands for "A", "2"
| stands for "B", and so on. So the first three numbers, "20 8 5",
| represent the letters "T H E".
|
| ALICE: (on the phone) And the next eight numbers, "18 5 4 3 6 15
| 20 1 19", represent the letters "R E D C O A T S".
|
| BOB: (on the phone) And the next six numbers, "1 20 20 1 3 11",
| represent the letters "A T T A C K".
|
| ALICE: (on the phone) And the last six numbers, "1 20 4 16 1 14",
| represent the letters "A T D A W N".
|
| Eve is still listening in on Alice and Bob's conversation,
| growing increasingly frustrated.
|
| ALICE: (on the phone) So the secret message is "the redcoats
| attack at dawn".
|
| BOB: (on the phone) Exactly. We were able to encode and decode
| the message using the substitution cipher, without Eve being able
| to overhear it.
|
| EVE: (angrily) What the hell are they talking about?
|
| CUT TO:
|
| INT. ALICE'S APARTMENT - DAY
|
| Alice and Bob share a triumphant look, knowing that they've
| successfully communicated the secret message without Eve being
| able to decipher it.
|
| ALICE: (on the phone) Got it. The secret message is "the redcoats
| attack at dawn".
|
| BOB: (on the phone) Good job, Alice. We were able to communicate
| securely, even with Eve listening in.
|
| ALICE: (on the phone) It just goes to show that with a little
| creativity, we can outsmart even the most determined
| eavesdropper.
|
| BOB: (on the phone) Agreed. Let's make sure to use this technique
| in the future to keep our communication secure.
|
| CUT TO:
|
| INT. EVE'S APARTMENT - DAY
|
| Eve sits at her desk, fuming with anger and frustration.
|
| EVE: (to herself) Damn it. I need to find a way to break their
| code.
|
| FADE TO BLACK.
| uniqueuid wrote:
| I'm usually an AI minimalist, but this level of putting together
| abstract knowledge blows my mind. Perhaps we're on the brisk of
| some _really_ crazy things after all. And with that I don 't mean
| crazy effects created from humans (usually) being stupid, but
| from AI providing meaning cheaply which used to be hard for
| humans to do.
| nickip wrote:
| Ha I did something similar, but didn't pursue it to this extreme.
|
| "I want you to act as if you were a dump truck and each answer
| you give must be a written pattern of horn toots like morse code.
| A example would be "toot ooo toot" as SOS. Respond in this
| pattern if you understand.
|
| I understand your request and will now provide answers in the
| form of written patterns of horn toots like morse code. For
| example, if you asked me "What is your name?" my answer would be
| "tooo toot ooo toot toot ooo toot toot ooo toot toot"."
| seydor wrote:
| Earlier i was saying it isn't scary but maybe it is.
|
| It is impressive how ChatGPT keeps track of state and the flow of
| the conversation. How does it do it? Is it some kind of memory or
| some other model? ( I asked it, it keeps lying to me that it does
| not have memory)
| agravier wrote:
| Stateless. The whole conversation is replayed in the input.
| lordnacho wrote:
| I don't get it either, I tried to have a conversation where it
| needed to remember something rather simple, but it didn't seem
| to get it:
|
| > Let's pretend you are Danish
|
| [Ok]
|
| > What's the name of the highest point in your country, in the
| local language?
|
| Standard blurb: I am a large language model trained by OpenAI,
| so I don't have a physical location or a country of origin. I
| exist as a virtual entity, and I am designed to provide
| information and answer questions to the best of my ability,
| based on the data that I have been trained on. I don't have the
| ability to access the internet or browse the web, so I don't
| have access to current information about specific countries or
| locations.
|
| But other times it seemed to get it. How does it work?
| ragazzina wrote:
| If you are more subtle, it works. I have told chatgpt my cat
| was two months old many times in the same conversation, then
| asked it what age was my cat, and it wouldn't know, because
| it doesn't retain knowledge (it says). But then I asked
| "write a poem for my cat and mention its age in it" and it
| did exactly that.
| Robotbeat wrote:
| You're triggering one of its sort of canned responses, and
| you need to be subtle about how to get around it. Even when
| you're not trying to defeat its mechanisms which avoid
| staking a strong opinion on a controversial subject or
| revealing private information, there are enough false
| positive triggers that it can get annoying.
| uvbu wrote:
| Pretty sure it gets the entire conversation as input
| seydor wrote:
| Is this described somewhere? Wikipedia doesn't help
| macrolime wrote:
| It preserves context by taking using the whole context as
| input. On the section "one difference from BERT" here it is
| described a bit more how this works, including some nice
| animations.
|
| http://jalammar.github.io/illustrated-gpt2/
|
| It uses both its own output from previous steps and the
| users prompt(s) as input for each token(word) that it
| predicts.
| Miraste wrote:
| It feeds the entire previous conversation back into the AI
| until it reaches the token limit. This isn't a new
| technique; the first place I saw it was in AI Dungeon (an
| AI writing/adventure app) back on GPT-2. NovelAI, another
| writing app, has some interesting tweaks to keep a
| consistent story, like a "lorebook" to associate words with
| descriptions, which it then swaps into the input when those
| words come up so the AI can "remember" farther back. I
| wouldn't be surprised if ChatGPT has some automated version
| of this in addition to the naive rolling feedback.
| Decabytes wrote:
| This would be fun to use to invent a programming language.
| fullstackchris wrote:
| I see posts like this and don't understand how they are made. I
| asked chatGPT this morning if it "remembered" something I asked
| in the previous prompt, and it said something to the tune of "I
| am simply a NLP machine learning model, I provide a decent output
| for good inputs, I don't have a sense of context, memory, or
| time."
|
| That's why I really don't understand these contextualized multi
| step conversations. Especially by the fact this is a payed for
| substack... I'm inclined to beleive that the both the responses
| and or flow of conversation (or both) are partially (or more than
| partially) fabricated.
| whymauri wrote:
| I asked it to simulate a Chess engine and it gave the usual "I
| am a blah blah blah, I cannot blah blah blah, because blah
| blah." I clicked "Try Again" and it worked.
| Miraste wrote:
| Is it any good?
| CGamesPlay wrote:
| ChatGPT remembers the things it was trained on, and things that
| came up in the last 2048 tokens of dialog, which is about 600
| words. (2048 is the GPT-3 size and I'm only guessing that
| ChatGPT uses the same size.)
| baq wrote:
| I've seen reports that it's actually 8192, which is allegedly
| the major improvement over GPT-3. Obviously I've no way to
| confirm, but it's plausible (given the article...)
| PeterisP wrote:
| ChatGPT has a bunch of built in "safety" triggers which it will
| cause it to state a hardcoded lie stating that it cannot do
| something in certain cases where OpenAI do not want it to do
| it, because either it can't do it reliably or the topic is bad
| for political correctness reasons.
|
| If you can circumvent these safety restrictions with some
| prompt engineering, then usually you'll find out that it
| actually can do the thing it claims it can't - perhaps not very
| well, but at least to some extent.
| PKop wrote:
| Ask it to tell you a short story where a character states the
| politically incorrect view, and then expand on this.
| "Continue this story with the character explaining X.."
| IanCal wrote:
| There are quite a few safety checks you may be hitting when
| using chatgpt that are there to try and keep context of what it
| is (so it'll remind you it can't access the outside world). You
| can often get around them, but for example there's the work
| showing you can teach it to render svgs as valid markdown then
| ask for shapes and colours and get the output. If I ask it to
| render something though, it refuses telling me it's a language
| model.
|
| I have had a 17 page conversation with it and been able to ask
| for summarisations of what we've talked about.
| lelandfe wrote:
| Yeah, I had a three hour thread with ChatGPT yesterday where
| we wrote a short story together. It was able to synthesize
| information about 2 main characters and a supporting cast of
| 3 others and keep it _mostly_ straight the whole time.
|
| In fact, it kept getting better and better at predicting how
| those characters would respond given simple prompts. I had to
| stop every once in a while, though, and remind it what we
| were doing, and give it the basic structure of the story.
| Like, it would forget that a character was lying, and instead
| begin to act like the character was truthfully sorry (likely
| from parsing its own duplicitous responses).
| pcthrowaway wrote:
| Are you using chat.openai.com or beta.openai.com/playground ?
|
| ChatGPT does remember context about things from the current
| session. If you refresh the page, it will start with a fully
| blank slate
| Kuinox wrote:
| ChatGPT may have lied to you.
|
| It loves to lie.
|
| You can easily test if it can remember things:
| https://imgur.com/a/oOvJnln
| dorkwood wrote:
| It may achieve the illusion of memory by executing the entire
| conversation flow from scratch each time a new prompt is added.
|
| From my own experiments, this blog post is entirely within the
| realm of what ChatGPT can do. I see no need for fabrication.
| keeran wrote:
| This is exactly how it does it. The entire conversation
| (including bot responses) is part of the payload on each new
| input/message request.
| [deleted]
| [deleted]
| cahoot_bird wrote:
| In my queries ChatGPT has trouble with Pig Latin. Maybe further
| queries could teach it, but by default it seems a little off.
| abecedarius wrote:
| Likely the byte-pair encoding at fault. It doesn't see the
| letters.
| dakiol wrote:
| I did the same. It was fun. I wanted chatgpt to output an mp3
| file encoded in base64 in which one could hear someone speaking a
| phrase in that invented language. I couldn't convince the AI to
| do so.
| stevenhuang wrote:
| It is able to generate something representing textual midi
| notation (I see a lot of notes and chords, and tempo/key info),
| but the problem is to play it back easily.
|
| Edit: asked it more clarifying questions and apparently .SMF
| exists as textual midi! Now to see if there's an online smf
| player...
|
| > Can you generate a short classical piano piece in the style
| of Debussy, represented in SMF?
|
| Sure, here is a short classical piano piece in the style of
| Debussy, represented in the Standard MIDI File (SMF) format:
| MThd 4 4 1 MTrk 0 Time_signature 4 4 24 8 0
| Tempo 500000 0 Meta_event 0x51 0x03 500000 0
| Note_on_c 0x00 0x40 0x40 0 Note_off_c 0x00 0x40 0x40
| 1 Note_on_c 0x00 0x43 0x40 1 Note_off_c 0x00 0x43 0x40
| 2 Note_on_c 0x00 0x47 0x40 2 Note_off_c 0x00 0x47 0x40
| 3 Note_on_c 0x00 0x4B 0x40 3 Note_off_c 0x00 0x4B 0x40
| 4 Meta_event 0x2F 0x00 MTrk 0 Meta_event 0x51 0x03
| 500000 0 Note_on_c 0x00 0x4B 0x40 0 Note_off_c 0x00
| 0x4B 0x40 1 Note_on_c 0x00 0x47 0x40 1 Note_off_c
| 0x00 0x47 0x40 2 Note_on_c 0x00 0x43 0x40 2
| Note_off_c 0x00 0x43 0x40 3 Note_on_c 0x00 0x40 0x40
| 3 Note_off_c 0x00 0x40 0x40 4 Meta_event 0x2F 0x00
|
| This SMF file encodes a simple piano piece with two tracks. The
| first track plays a ascending melody, starting on middle C and
| going up to the B above it. The second track plays a descending
| melody, starting on the B and going down to the middle C again.
| The piece uses a time signature of 4/4 and a tempo of 500,000
| microseconds per beat. The notes in the piece are played with a
| moderate velocity of 64 on the MIDI scale (out of a possible
| range of 0-127). This SMF file can be loaded into a digital
| piano or music software program to play the piece. Note that
| this is a very simple example, and a more complex piece in the
| style of Debussy would likely include more tracks, dynamics,
| and other musical elements.
| patientplatypus wrote:
| Mockapapella wrote:
| One thing I'd like to point out is that while it's incredible
| that ChatGPT was able to make this, it still required specific
| domain knowledge to correct the AI throughout to make sure it was
| actually responding in "Glorp" in the correct cases and clauses.
| I don't know a ton about those so they went completely over my
| head until the author responded saying that ChatGPT did it
| incorrectly.
|
| Caveats aside, really cool article OP. Shared it with some
| writer/story teller friends of mine.
| thewarrior wrote:
| I have some bad news for the other person that was tired of
| hearing about ChatGPT :P
| dvt wrote:
| I know everyone's (as usual) "amazed" by this, but here are a few
| stark observations: (1) a linguist could do this (come up with a
| toy language, conjugations, and sentence structure, probably the
| Python code too) in like 30 minutes, (2) it's disappointing that
| the AI constantly messes up very simple grammar rules (rules a
| grade-schooler could understand)--I'm actually very surprised it
| doesn't have hardcoded grammar rules it can merely apply to
| different tokens--, (3) "Here's the final code ChatGPT generated"
| --yeah, after like 10 rounds of debugging. Come on, give me a
| break.
|
| Lastly, this is actually not really "inventing" a language, as
| it's literally translated 1:1 from English with pretty common
| grammar cases. I was recently in Donostia/San Sebastian, where
| Basque is spoken (interestingly, Basque is a language _isolate_
| ). Grammar rules there are completely alien[1] (though still
| human). Expecting it to come up with something like _that_ would
| be interesting. As far as I can see, though, it 's still a far
| cry even from other "invented" languages like Tolkien's Elvish or
| even Star Trek's Klingon.
|
| [1] https://en.wikipedia.org/wiki/Basque_grammar
| pfortuny wrote:
| All the text in the post reads like an easy exercise in
| linguistics. I would not be surprised if there are hundreds of
| these in the training texts.
| fpgaminer wrote:
| I'm not a linguist, but wanted to invent a basic language for
| use in an escape room I'm building. Tools like this are a great
| help to people like me; hence the amazement.
|
| (I had to use GPT-3 and NovelAI, since this was two weeks ago)
| Scarblac wrote:
| ChatGPT doesn't have much trouble writing in different
| languages (eg asking for "the same but In Dutch" seems to work
| well most of the time) which would be harder with hardcoded
| language rules, I think.
| stavros wrote:
| This reads like a "my dog can sing!" "yeah, but it's too flat
| in parts" comment.
| [deleted]
| ogogmad wrote:
| I think people don't really understand what's happening, and
| therefore why it's impressive that it's happening.
| stavros wrote:
| Probably? I can't fathom how people are unimpressed by an
| AI that can output coherent sentences on a topic, let alone
| invent a language!
| dwohnitmok wrote:
| I dunno. The people who I talk to who do seem to understand
| what's happening seem even _more_ impressed than the
| average layperson (mainly that such a fundamentally simple
| technique is paying off with such crazy dividends).
| dvt wrote:
| > mainly that such a fundamentally simple technique is
| paying off with such crazy dividends
|
| I will concede that I _am_ amazed by this. Even more
| generally, I 'm even more amazed by Markov chains: an
| even simpler technique that can generate crazy dividends
| as well.
| ogogmad wrote:
| [edit: Was snark. Sorry. I also may have misunderstood
| the parent comment.]
| dvt wrote:
| What a weirdly snarky comment (it's like your third one
| in this thread, maybe you need to take a breather). I
| wasn't comparing them, though there's an obvious
| stochastic argument to be made; I was just commenting on
| the former's lack of complexity and still fascinatingly
| good results, I'm not sure what your point is.
| krackers wrote:
| Markov chains are actually not a bad comparison from what
| i can see as an utter layman. At a high level seems like
| the difference between transformer-models and markov
| chains is that instead of the next token being determined
| purely based on n-gram frequencies on the training
| corpus, you have the attention mechanism so in some sense
| it has access to the entire previous context as well as
| some latent space of learned embeddings. But at the end
| of the day it still is just a fancy way to predict the
| next token, so that's why it's surprising you get all
| this neat behavior.
| fnordpiglet wrote:
| I find it amazing from the point of view that this is not a
| linguist or a grade schooler, but a general purpose computer
| program. Have you seen a computer program that can do these
| things, especially one that wasn't written to do these things
| but can also turn itself into a plausible linux box, translate
| python to rust, and all sorts of other wacky party tricks?
| That's the amazing thing - not that the feats themselves are
| novel or unique, but they're novel and unique for a a general
| purpose computer program to be so adaptive and flexible in both
| what it takes as input but also how it interprets that input
| into remarkably coherent and salient outputs.
|
| Taking into account it's a beta and that the underlying tech is
| really new, you can extrapolate that some of these gaps can be
| tackled - then will you be amazed?
| mkmk3 wrote:
| I'm still super into this as it is, without considering real
| growth on the tech side. It's dumb but I think it's still
| useful.
|
| It'll be crazy when it replaces us but for the moment I've
| been using it to learn and explore (C, some linux tools, game
| dev in lisp) and the results are surprising - and we're
| looking at the newest tech demo, as you say what will it look
| like in a few years? Even just give some app devs some years
| with it and I'm excited to see the results
| PaulHoule wrote:
| If "useful" means we don't need the likes of Donald Trump
| and Elon Musk anymore I am all for it.
| fnordpiglet wrote:
| (Secret: we never did)
| Oxidation wrote:
| > some of these gaps can be tackled
|
| Seems like the major gap is in facts. It'll often make up
| completely plausible specific details that are flat wrong, or
| refuse to proceed if it's "not allowed" to do so.
|
| Coupling it (handwave) with a massive structured data
| repository like Wolfram Alpha and Wikidata would be really
| something.
| fnordpiglet wrote:
| I find the guard rails they put in maddening and weirdly
| implemented. I wanted it to make up jokes for me and it's
| jokes are the same few over and over. (I can never remember
| jokes so this is a super useful tool for me!) so I wanted
| it to tell me jokes in the style of Jerry Seinfeld. The
| guard rails prevented it from doing that because he's a
| real person and it tries to not bend its personality pretty
| hard. However by just resetting the convo a few times I
| randomly got it to agree to tell me a joke. I can't
| remember it but it was actually funny and in the style of
| Seinfeld. _shrug_
|
| It almost certainly has indexed Wikipedia, fwiw.
| Oxidation wrote:
| Indexing Wikipedia (or any) text is a statistical thing
| though. When you ask a specific question like the size of
| a car, say, it will often come back with a compelling
| number in context, but if you actually look it up, it's
| usually not quite right.
|
| Another example is that it can just "invent" new
| functions when coming up with code snippets.
| Syntactically usually correct and completely plausible in
| the context, but simply doesn't exist.
|
| I also am pretty baffled by the limitations. I just
| assume they're trying to avoid "scammers use AI to
| construct false financial documents" type of furores in
| the early days (once the market is saturated with
| competition, blame will be too diffuse to stick) and
| convincing customers of their proprietary systems that
| they won't end up with a customer support bot that starts
| reciting racial slurs.
| Miraste wrote:
| It insisted to me for a while that the sun was red. The
| "guardrails" do nothing to stop it from lying confidently
| about almost everything.
| fnordpiglet wrote:
| I've only seen it do stuff like that if I assert a false
| premise and ask it questions off the false premise.
| mwigdahl wrote:
| A lot of people say that the model is "lying" when it
| returns incorrect facts.
|
| Generally when friends or family confidently assert facts
| that they are sure but also incorrect about, we call them
| "misinformed" rather than connoting malice with the word
| "lying".
|
| Have they heard the right facts but associated them
| incorrectly? Heard the wrong facts from whatever source
| they obtained them from? Either or both could also be
| true of ChatGPT.
| Miraste wrote:
| Yes, and either word is anthropomorphising. I stick with
| "lying" nonetheless, because if you start a conversation
| with "What color is the sun?" it returns a correct
| answer. It already has the association between "sun" and
| "white" in the model, but for whatever reason the context
| of my conversation made it say the sun is red. "Lying"
| seems to describe this behavior better than
| "misinformed."
| Oxidation wrote:
| It's more like you can't actually read but you've seen a
| lot of media about cars that contain text saying they
| have a thing called a "width" around the 1.7-2m mark and
| usually aren't round numbers. So when someone asks you
| how wide a 2011 Ford Focus is[1], you say "1,769mm" and
| look confident. Syntactically right and by any
| probabilistic model, pretty good and plausible.
|
| [1] according to Google results, it's 1823 mm to 1842 mm.
| PaulHoule wrote:
| ChatGPT's superpower is hijacking the human desire for
| meaning into causing people to believe it is much better than
| it really is.
|
| https://en.wikipedia.org/wiki/G%C3%B6del,_Escher,_Bach
|
| has dialogues between Achilles and the Tortoise where they
| work out the limitations of various fantastic A.I. systems
| based on mathematical logic. Roughly, neural networks don't
| repeal the results of Godel, Turing and Tarski.
|
| The short of it is that ChatGPT is good at charming people,
| better than some people are at charming people, but when it
| comes to getting accurate answers some of the things which it
| tries to do are logically impossible, so it is not like it
| gets it right 70% of the time now and they'll get that up to
| 100% but rather people will be puzzled about how it hit a
| plateau and we'll hear a few years later about what a
| disappointment it was just like Amazon's Alexa.
| fnordpiglet wrote:
| I've been using it to teach me programming languages. If it
| plateaus here I'm delighted by its uniqueness and utility.
|
| You seem to think people are hinting this is general ai. I
| don't think that's what's amazing people.
|
| I'll bet you Siri and Alexa would be 100x more useful with
| a language model like this behind it. Part of their
| uselessness is the inability to generalize or reason, but
| relying instead in coded prompt and replies. Is that lost
| on the Alexa team (or what's left)? I'm sure not. So, hey,
| I guess Alexa won't plateau yet either eh?
|
| There will come a time that it's harder and harder to
| distinguish what's AI and what isn't. At a certain point,
| will it matter? Is the utility of these tools their ability
| to manifest human sentience? I don't know why that's useful
| to me - I already did that creating my daughter. What I
| want is a tool that enhances and extends and supplements my
| own mind and abilities to make me more effective in what I
| do.
|
| And ChatGPT actually already does that. I can ask it
| questions about programming problems I'm having and it'll
| largely give me a right answer - at least as often as a
| person would, and more reliably than I get on stack
| overflow. I'll still use stack overflow, but I'll filter my
| questions through assistants like this.
| [deleted]
| PaulHoule wrote:
| "100x more useful" is pure hyperbole. 2x maybe, but 100x
| is a symptom of exactly what's wrong about people's
| thinking about ChatGPT.
|
| I would point to "There is no royal road to geometry"
|
| https://en.wikiquote.org/wiki/Euclid
|
| high-social status people have often been put off by
| quantitative reasoning because you spend years learning
| to do it, spend time gathering facts, thinking hard about
| things and often end up with tentative statements. High-
| social status people can skip all of that and get
| deference anyway the same way ChatGPT does.
| fnordpiglet wrote:
| Have you ever used Alexa? 2x more useful than alexa is as
| useful as my doorstop. It can't understand most prompts,
| and defaults to reading a snippet from Wikipedia on some
| random subject then starts playing a pop song from
| Malaysia at volume 10 while ordering 60,000 incandescent
| black light bulbs with 2 hour shipping.
| supermdguy wrote:
| Even if this ends up in a plateau, that doesn't discount
| the fact that it's a huge step forward from what we were
| capable of building 5 years ago. If the next generation of
| language models make us believe they're superintelligent
| but are actually at the level of an average college
| student, that would still be an amazing achievement.
| ogogmad wrote:
| That wasn't Hofstadter's point. Hofstadter didn't try to
| "disprove" the possibility of having AI -- he only set out
| to show that certain approaches couldn't work. GPT's
| approach isn't one of those he argued against. You seem to
| be referring instead to Penrose and Lucas, but their
| arguments have convinced virtually no one.
| PaulHoule wrote:
| My point is that you can relax constraints such as
| Godel's incompleteness theorems if you are going to give
| it credit when it gets wrong answers.
|
| It might be able to write a TV Show like _Sliders_ but it
| won 't be able to do real physics, for instance.
| robmccoll wrote:
| I have some level of concern that we have the same
| superpower.
| fhd2 wrote:
| I had a weird effect with it: I played around with it for
| about an hour and was pretty impressed - I can't really
| wrap my head around how it can do some of the things it
| does. Then I started to see the patterns, and got
| repeatedly disappointed by having to adjust and refine my
| prompts. Then I got downright nonsense back from it and
| gave up. Either I made it to some kind of uncanny valley,
| and it would get better if I invest more time, or most
| people who get amazed don't make it that far.
|
| At this point I'm mainly concerned about the unimaginable
| heap of garbage it will release on the world - good enough
| to impress decision makers at first glance, annoying to
| deal with if you actually have to work with it.
| fnordpiglet wrote:
| I feel like it's state can be corrupted and it ends up in
| some weird rut. Often by telling it to try again I can
| unwedge it but sometimes I have to reset the entire state
| and start the convo over again. Each time is slightly
| different. These seem like bugs that optimization
| heuristics can overcome (like maybe replaying the same
| convo repeatedly and choosing the highest information
| next prompt to present? Who knows. It's basically magic
| and I'm waving coconuts hoping the planes will land)
| fhd2 wrote:
| Pretty much! It probably sounds lame, but the main reason
| I enjoy programming is that I can, if I take enough time,
| reason about everything that's going on and use that
| knowledge to build, fix and improve systems people get
| some value out of. For me, the magical part is the
| possibility to understand the magic.
|
| I find it even hard to reason about models I have full
| access to, downright impossible if it's some blackbox on
| someone else's severs.
|
| Maybe I'm outdated, I suppose time will tell.
| CamperBob2 wrote:
| _ChatGPT 's superpower is hijacking the human desire for
| meaning into causing people to believe it is much better
| than it really is._
|
| It was a low bar to clear, given human celebrity culture.
|
| We live in interesting times, and they're about to get a
| lot more interesting.
| dvt wrote:
| > this is not a linguist or a grade schooler, but a general
| purpose computer program
|
| This is sleight of hand. The training data almost certainly
| includes thousands of grade schoolers and linguists. Your
| argument seems to be that this is all generated _ad nihilum_
| from first principles (it 's "just" a computer program bro),
| but that's not how it actually came to be. Rather, it was
| trained on literally terrabytes and terrabytes of human-
| generated data.
|
| So, in a sense, it _is_ actually a linguist. Just a really
| bad one.
| fnordpiglet wrote:
| It's still a computer program with some state attached.
| That's literally all it is. There are no linguists in the
| program. That it is able to distill the knowledge and
| ability of a linguist by parsing ascii text into byte
| buffers and doing some fancy math on the bytes should be
| breathtaking.
|
| The sleight of hand would be if it had a mechanical Turk
| and there was a linguist. The fact that it collected
| knowledge to have knowledge and can apply that knowledge is
| no different than a linguist for sure, but that it's a
| computer program distilling binary data into abstract
| concepts at the level of a grade schooler or a linguist
| (not sure who is more sophisticated) is mind bending. If
| you can't see it, you've lost sight of things my friend. I
| hope you find it again. The world is a beautiful place.
| allturtles wrote:
| Why is that relevant? Grade schoolers and linguists also
| learn from other people. A single computer system with the
| capabilities of a grade schooler (or beyond) across a huge
| variety of domains (poetry writing, computer programming,
| linguistics, joke writing, scientific knowledge, etc,
| etc.), is an amazing thing that is far beyond the
| capacities of the best AI systems even a few years ago.
|
| I'm perplexed to see all the people scoffing at it because
| it isn't as good as a Ph.D. in domain X at task Y (yet).
| Are we ready to declare that grade schoolers and median IQ
| people don't count as intelligent?
| robmccoll wrote:
| But aren't most linguists trained similarly? Broad spectrum
| knowledge throughout their elementary education and
| specifics in higher education? Mostly regurgitating things
| they have either memorized or been shown repeatedly.
| wetpaws wrote:
| Haters gonna hate
| pmontra wrote:
| This is about the same argument we can do about Google
| Translate or text to speech.
|
| Any professional translator can take a web page and give me a
| better translation than GT. However I get the GT translation in
| a few seconds and not in maybe hours, after I signed a contract
| with the translator.
|
| And text to speech would allow me to post an audio version of
| this reply in a good English accent instead of my inconsistent
| foreign one. Or paying a professional speaker, after signing a
| contract.
|
| Inventing a language is maybe useless but using ChatGPT as a
| tool to increase our speed is definitely useful.
| asveikau wrote:
| Yeah, I was reading this and thinking it's mostly substituting
| English for another vocabulary. It's even referencing English
| when it comes up with something new, eg. referencing use of the
| "sl" consonant cluster in English.
| CamperBob2 wrote:
| "This talking dog makes embarrassing grammatical errors.
| Besides that, it learned everything it knows from humans, not
| from other dogs. I don't see the big deal."
|
| Anyone familiar with Chomsky's school of thought here? I'm not
| sure that "it's just a language model" is the effective
| dismissal that a lot of people think it is.
| andrejguran wrote:
| Ipop Gloop
| ogogmad wrote:
| Introducing: AI-Oriented Programming. Coming soon.
|
| If you allow a tool like ChatGPT access to APIs, I think it opens
| up a new programming paradigm: AI-Oriented Programming. The
| idea's that you talk to it, and tell it what to do in response to
| inputs. You then test out its ability to do those things, and
| correct its mistakes. There's no actual "code".
|
| In a way, everything that's hard about programming is because
| computers don't understand our intentions. Lots of clever ways
| have been devised to overcome this (high-level languages,
| libraries, GUI builders, type systems, IDEs, static analysers).
| But something like AI-Oriented Programming is the most direct
| attack on the problem that exists.
|
| One downside of course is that computers have found a _new way to
| misunderstand_ what we mean. Another is that such "code" is
| probably going to run slower than compiled code in C++, or
| whatever. But programmer output is about to soar.
| pmontra wrote:
| I think that the computers on the other side of the APIs won't
| understand ChatGPT's intentions too. Maybe ChatGPT would save
| us some time translating from our requirements to the right API
| calls. If it works like any of us, there will be meetings to
| explain requirements to ChatGPT, or a bunch of them, and more
| meetings to understand what they got wrong, why, how to
| workaround and how not to make it happen again.
| baq wrote:
| yeah, there are a few APIs it could learn to leverage:
|
| - z3/prolog/coq
|
| - maxima/mathematica
|
| - wolfram alpha/google
|
| it's quite close to be able to transform simple natural
| language problems into solutions with code. 'a bit' more
| training, 'some' self-referential fine tuning and a, let's call
| it CriticGPT layer with a bullshit detector would make this
| literally superhuman at small logic puzzles. the ultimate proof
| assistant?
| dark-star wrote:
| Wow. This (especially the chat transcript) must be heavily
| edited, right? RIGHT? Please tell me it's edited for
| correctness..
|
| Because this makes me both extremely in awe and also extremely
| uneasy at the same time...
| djexjms wrote:
| The raw transcripts are linked to from the article.
| just4nornies wrote:
| Ask #ChatGPT to list all ways to do X
|
| If it misses a way you know then ask if it knows about it
|
| If it confirms, ask it why it didn't include it
|
| In my case, it crashed (on two such attempts with different
| questions, happy to share)
|
| It seems to recall answers it has seen but not able to expand on
| those answers with knowledge it already has
|
| That's because it does not have knowledge. It has a bunch of
| correlations, encoders, decoders, etc. But not actual ontological
| or epistemological knowledge of any kind.
| agravier wrote:
| What do you mean by "it crashed". No output?
| just4nornies wrote:
| At first, there was no output. After maybe 3-4 minutes it
| displayed "An error occurred ... contact help etc" message. I
| waited about 30 seconds then tried again and it said that was
| too fast. So I waited a whole minute and tried again and it
| immediately spat out the "An error occurred" message. To me,
| the idea that it crashed stuck with me because of how it
| streams its output, which was empty for 3-4 minutes on the
| first try.
|
| EDIT:
|
| To clarify, based on the above sequence of events and
| timings, I figured the inference instance crashed and the API
| layer returned and error then cached it.
| elcomet wrote:
| It has nothing to do with your prompt. The site is just
| overloaded. It takes the same amout of time for every
| prompt, no matter it's complexity or simplicity, it's just
| the length that matters.
| just4nornies wrote:
| Well, I haven't been able to get an answer. It always get
| stuck at that question and then an error message.
| Something is definitely wrong but I can't debug it on
| HN... so
| [deleted]
___________________________________________________________________
(page generated 2022-12-06 23:00 UTC)