> defining AGI as matching the cognitive versatility and proficiency of a well-educated adult
I don't think people really realize how extraordinary accomplishment it would be to have an artificial system matching the cognitive versatility and proficiency of an uneducated child, much less a well-educated adult. Hell, AI matching the intelligence of some nonhuman animals would be an epoch-defining accomplishment.
I think the bigger issue is people confusing impressive but comparatively simpler achievements (everything current LLMs do) with anything remotely near the cognitive versatility of any human.
But the big crisis right now is that for an astonishing number of tasks that a normal person could come up with, chatgpt.com is actually a good at or better than a typical human.
If you took the current state of affairs back to the 90s you’d quickly convince most people that we’re there. Given that we’re actually not, we’re now have to come up with new goalposts.
I don't know. People in the 90s were initially fooled by Eliza, but soon understood that Eliza was a trick. LLMs are a more complex and expensive trick. Maybe it's time to overthrow the Turing Test. Fooling humans isn't necessarily an indicator of intelligence, and it leads down a blind alley: Language is a false proxy for thought.
Consider this. I could walk into a club in Vegas, throw down $10,000 cash for a VIP table, and start throwing around $100 bills. Would that make most people think I'm wealthy? Yes. Am I actually wealthy? No. But clearly the test is the wrong test. All show and no go.
The more I think about this, the more I think the same is true for our own intelligence. Consciousness is a trick and AI development is lifting the veil of our vanity. I'm not claiming that LLMs are conscious or intelligent or whatever. I'm suggesting that next token prediction has scaled so well and cover so many use cases that the next couple breakthroughs will show us how simple intelligence is once you remove the complexity of biological systems from the equation.
All we know about animal consciousness is limited to behaviour, e.g. the subset of the 40 or so "consciousness" definitions which are things like "not asleep" or "responds to environment".
We don't know that there's anything like our rich inner world in the mind of a chimpanzee, let alone a dog, let alone a lobster.
We don't know what test to make in order to determine if any other intelligence, including humans and AI, actually has an inner experience — including by asking, because we can neither be sure if the failure to report one indicates the absence, nor if the ability to report one is more than just mimicking the voices around them.
For the latter, note that many humans with aphantasia only find out that "visualisation" isn't just a metaphor at some point in adulthood, and both before and after this realisation they can still use it as a metaphor without having a mind's eye.
> Language is the baseline to collaboration - not intelligence
Would you describe intercellular chemical signals in multicellular organisms to be "language"?
> We don't know that there's anything like our rich inner world in the mind of a chimpanzee, let alone a dog, let alone a lobster.
If be "we don't know" you mean we cannot prove, then, sure, but then we don't know anything aside from maybe mathematics. We have a lot of evidence that animals similar consciousness as we do. Dolphins (or whales?) have been known to push drowning people to the surface like they do for a calf. Killer whales coordinate in hunting, and have taken an animus to small boats, intentionally trying to capsize it. I've seen squirrels in the back yard fake burying a nut, and moving fallen leaves to hide a burial spot. Any one who has had a dog or a cat knows they get lonely and angry and guilty. A friend of mine had personal troubles and abandoned his house for a while; I went over to take pictures so he could AirBnB it, and their cat saw me in the house and was crying really piteously, because it had just grown out of being a kitten with a bunch of kids around and getting lots of attention, and suddenly its whole world was vanished. A speech pathologist made buttons for her dog that said words when pressed, and the dog put sentences together and even had emotional meltdowns on the level of a young child. Parrots seem to be intelligent, and I've read several reports where they give intelligent responses (such as "I'm afraid" when the owner asked if it wanted to be put in the same room as the cat for company while the owner was away [in this case, the owner seems to be lacking in intelligence for thinking that was a good idea]). There was a story linked her some years back about a zoo-keeper who had her baby die, and signed it to the chimpanzee (or gorilla or some-such) females when it wanted to know why she had been gone, and in response the chimpanzee motioned to with its eye suggesting crying, as if asking if she were grieving.
I probably have some of those details wrong, but I think there definitely is something there that is qualitatively similar to humans, although not on the same level.
> If be "we don't know" you mean we cannot prove, then, sure, but then we don't know anything aside from maybe mathematics.
More than just that: we don't know what the question is that we're trying to ask. We're pre-paradigmatic.
All of the behaviour you list, those can be emulated by an artificial neural network, the first half even by a small ANN that's mis-classifying various things in its environment — should we call such an artificial neural network "conscious"? I don't ask this as a rhetorical device to cast doubt on the conclusion, I genuinely don't know, and my point is that nobody else seems to either.
> We don't know that there's anything like our rich inner world in the mind of a ...
I posit that we should start with a default "this animal experiences the world the same as I do" until proven differently. Doctors used to think human babies could not feel pain. The assumption has always been "this animal is a rock and doesn't experience anything like me, God's divine creation." It was stupid when applied to babies. It is stupid when applied to animals.
Did you know that jumping spiders can spot prey, move out of line of sight, approach said pray outside that specific prey's ability to detect, and then attack? How could anything do that without a model of the world? MRIs on mice have shown that they plan and experience actions ahead of doing them. Just like when you plan to throw a ball or lift something heavy where you think through it first. Polar bears will spot walrus, go for a long ass swim (again, out of sight) and approach from behind the colony to attack. A spider and the apex bear have models of the world and their prey.
Show that the animal doesn't have a rich inner world before defaulting to "it doesn't."
> I posit that we should start with a default "this animal experiences the world the same as I do" until proven differently.
As I don't know, I take the defensive position both ways for different questions.*
Just in case they have an inner world: We should be kind to animals, not eat them, not castrate them (unless their reproductive method appears to be non-consensual), not allow them to be selectively bred for human interest without regard to their own, etc.
I'd say ditto for AI, but in their case, even under the assumption that they have an inner world (which isn't at all certain!), it's not clear what "be kind" even looks like: are LLMs complex enough to have created an inner model of emotion where getting the tokens for "thanks!" has a feeling that is good? Or are all tokens equal, and the only pleasure-analog or pain-analog they ever experienced were training experiences to shift the model weights?
(I'm still going to say "please" to the LLMs even if it has no emotion: they're trained on human responses, and humans give better responses when the counterparty is polite).
> How could anything do that without a model of the world?
Is "a model of the world" (external) necessarily "a rich inner world" (internal, qualia)? If it can be proven so, then AI must be likewise.
* The case where I say that the defensive position is to say "no" is currently still hypothetical: if someone is dying and wishes to preserve their continuity of consciousness, is it sufficient to scan their brain** and simulate it?
There are some clever tests described in The Language Puzzle on primates that (paraphrasing 14 hour long audiobook so forgive any mistakes.) indicate no primate other than humans and a couple of immediate predecessors (based on archaeological evidence) have much in the realm of abstract thinking abilities using their own communications, a few primates raised and taught forms of human language cannot progress very far without any of the facilities of language present in normal two-three year old development. The book is focused on how humans evolved language so other species are not covered, there is obvious verbal and gesture based communication in primates but it concludes not enough of the components of physiology that enable human language are present(both brain and vocal anatomy).
How do you define verbal language? Many animals emit different sounds that others in their community know how to react to. Some even get quite complex in structure (eg dolphins and whales) but I wouldn’t also rule out some species of birds, and some primates to start with. And they can collaborate; elephants, dolphins, and wolves for example collaborate and would die without it.
Also it’s completely myopic in terms of ignoring humans who have non verbal language (eg sign language) perfectly capable of cooperation.
TLDR: just because you can’t understand an animal doesn’t mean it lacks the capability you failed to actually define properly.
MW defines verbal as "of, relating to, or consisting of words".
I don't think anyone would argue that animals don't communicate with each other. Some may even have language we can't interpret, which may consist of something like words.
The question is why we would model an AGI after verbal language as opposed to modeling it after the native intelligence of all life which eventually leads to communication as a result. Language and communication is a side-effect of intelligence, it's a compounding interest on intelligence, but it is not intelligence itself, any more than a map is the terrain.
> The question is why we would model an AGI after verbal language as opposed to modeling it after the native intelligence of all life which eventually leads to communication as a result.
Because verbal/written language is an abstracted/compressed representation of reality, so it's relatively cheap to process (a high-level natural-language description of an apple takes far fewer bytes to represent than a photo or 3D model of the same apple). Also because there are massive digitized publicly-available collections of language that are easy to train on (the web, libraries of digitized books, etc).
I'm just answering your question here, not implying that language processing is the path towards AGI (I personally think it could play a part, but can't be anything close to the whole picture).
This is one of the last bastions of anthropocentric thinking. I hope this will change in this century. I believe even plants are capable of communication. Everything that changes over time or space can be a signal. And most organisms can generate or detect signals. Which means they do communicate. The term “language” has traditionally been defined from an anthropocentric perspective. Like many other definitions about the intellect (consciousness, reasoning etc.).
That’s like a bird saying planes can’t fly because they don’t flap their wings.
LLMs use human language mainly because they need to communicate with humans. Their inputs and outputs are human language. But in between, they don’t think in human language.
> LLMs use human language mainly because they need to communicate with humans. Their inputs and outputs are human language. But in between, they don’t think in human language.
You seem to fundamentally misunderstand what llms are and how they work, honestly.
Remove the human language from the model and you end up with nothing. That's the whole issue.
Your comment would only make sense if we had real artificial intelligence, but LLMs are quite literally working by predicting the next token - which works incredibly well for a fascimlie of intelligence because there is an incredible amount of written content on the Internet which was written by intelligent people
A human child not taught literally anything can see some interesting item extend a hand to it, touch it, interact with it. All decided by the child. Heck, even my cat can see a new toy, go to it and play with it, without any teaching.
LLMs can't initiate any task on their own, because they lack thinking/intelligence part.
This to me overstretches the definition of teaching. No, a human baby is not "taught" language, it learns it independently by taking cues from its environment. A child absolutely comes with an innate ability to recognize human sound and the capability to reproduce it.
By the time you get to active "teaching", the child has already learned language -- otherwise we'd have a chicken-and-egg problem, since we use language to teach language.
>but LLMs are quite literally working by predicting the next token - which works incredibly well for a fascimlie of intelligence because there is an incredible amount of written content on the Internet which was written by intelligent people
An additional facet nobody ever seems to mention:
Human language is structured, and seems to follow similar base rules everywhere.
That is a huge boon to any statistical model trying to approximate it. That's why simpler forms of language generation are even possible. It's also a large part of why LLMs are able to do some code, but regularly fuck up the meaning when you aren't paying attention. The "shape" of code and language is really simple.
How do we know animal language isn’t structured, in similar ways? For example we now know that “dark” birds are often colorful, just in the UV spectrum they can see and we can’t. Similarly there’s evidence dolphin and whale speech may be structured, we just don’t know the base rules; their speech is modulated at such rapid frequency our computers until maybe recently would struggle to even record and process that data realtime (probably still do).
Just because we don’t understand something doesn’t mean there’s nothing there.
Also, I’m not so sure human language is structured the same way globally. There’s languages quite far from each other and the similarities tend to be grouped by where the languages originated. Eg Spanish and French might share similarities of rules, but those similarities are not shared with Hungary or Chinese. There’s cross pollination of course but language is old and humans all come from a single location so it’s not surprising for there to be some kinds of links but even a few hundred thousand years of evolution have diverged the rules significantly.
Transformers are very powerful also for non-language data. For example time series, sequences like DNA or audio (also outside of speech and music).
Of course the vast amount of human text is key to training a typical LLM, but it is not the only use.
Well, you can explain to a plant in your room that E=mc2 in a couple of sentences, a plant can't explain to you how it feels the world.
If cows were eating grass and conceptualising what is infinity, and what is her role in the universe, and how she was born, and what would happen after she is dead... we would see a lot of jumpy cows out there.
This is exactly what I mean by anthropocentric thinking. Plants talk plant things and cows talk about cow issues. Maybe there are alien cows in some planet with larger brains and can do advanced physics in their moo language. Or some giant network of alien fungi discussing about their existential crisis. Maybe ants talk about ant politics by moving their antennae. Maybe they vote and make decisions. Or bees talk about elaborate honey economics by modulating their buzz. Or maybe plants tell bees the best time for picking pollens by changing their colors and smell.
Words, after all are just arbitrary ink shapes on paper. Or vibrations in air. Not fundamentally different than any other signal. Meaning is added only by the human brain.
I'm also attracted to the idea of reducing rule sets to simple algorithms and axioms, in every case you can. But I'm skeptical that consciousness can be reduced that way. I think if it can be, we'll see it in the distillation and quantizing of smaller and smaller scale models converging on similar adaptations, as opposed to the need for greater scale (at least in inference). I still believe language processing is the wrong task to train to that point. I'd like to see AIs that model thought process, logic, tool construction, real-world tasks without language. Maybe even those that model vocal chords and neurological processes instead of phonemes. Most animals don't use language, and as a result we can't ask if they're conscious, but they probably are. Navigating and manipulating the physical world from the cellular level up to swinging from trees is far more complex - language is a very late invention, and is not in and of itself intelligence - it may just be a lagging indicator.
To the extent that we vainly consider ourselves intelligent for our linguistic abilities, sure. But this underrates the other types of spatial and procedural reasoning that humans possess, or even the type that spiders possess.
That's not how I view it. Consciousness is the result of various feedback structures in the brain, similar to how self-awareness stems from the actuator-sensor feedback loop of the interaction between the nervous system and the skeletomuscular system. Neither of those two definitions have anything to do with language ability -- and it bothers me that many people are so eager to reduce consciousness to programmed language responses only.
The validity of the Turing test doesn’t change the fact that the bots are better than humans at many tasks that we would consider intellectual challenges
I am not a good writer or artist, yet I can tell that AI generated pictures or prose feel 'off' compared to stuff that humans make. People who are professional writers and artists can point out in a lot of cases the issues with structure, execution and composition that these images have, or maybe if sometimes they can't they still have a nose for subtle issues, and can improve on the result.
>I could walk into a club in Vegas, throw down $10,000 cash for a VIP table, and start throwing around $100 bills.
If you can withdraw $10,000 cash at all to dispose as you please (including for this 'trick' game) then my friend you are wealthy from the perspective of the vast majority of humans living on the planet.
And if you balk at doing this, maybe because you cannot actually withdraw that much, or maybe because it is badly needed for something else, then you are not actually capable of performing the test now, are you ?
That's really not true. Lots of people in America can have $0 in net worth and get a credit card, use that to buy some jewelry and then sell it, and have $10k in cash. The fact that the trick only works once proves that it's a trick.
You're not making much sense. Like the other user, you are hinging on non-transferrable details of your analogy, which is not the actual reality of the situation.
You've invented a story where the user can pass the test by only doing this once and hinged your point on that, but that's just that - a story.
All of our tests and benchmarks account for repeatability. The machine in question has no problem replicating its results on whatever test, so it's a moot point.
The LLM can replicate the trick of fooling users into thinking it's conscious as long as there is a sufficient supply of money to keep the LLM running and a sufficient number of new users who don't know the trick. If you don't account for either of those resources running out, you're not testing whether its feats are truly repeatable.
>The LLM can replicate the trick of fooling users into thinking it's conscious as long as there is a sufficient supply of money to keep the LLM running and a sufficient number of new users who don't know the trick.
Okay ? and you, presumably a human can replicate the trick of fooling me into thinking you're conscious as long as there is a sufficient supply of food to keep you running. So what's your point ? With each comment, you make less sense. Sorry to tell you, but there is no trick.
The difference is that the human can and did find its own food for literally ages. That's already a very, very important difference. And while we cannot really define what's conscious, it's a bit easier (still with some edge cases) to define what is alive. And probably what is alive has some degree of consciousness.
An LLM definitely does not.
One of the "barriers" to me is that (AFAIK) an LLM/agent/whatever doesn't operate without you hitting the equivalent of an on switch.
It does not think idle thoughts while it's not being asked questions. It's not ruminating over its past responses after having replied. It's just off until the next prompt.
Side note: whatever future we get where LLMs get their own food is probably not one I want a part of. I've seen the movies.
You only exist because you were forced to be birthed externally? Everything has a beginning.
In fact, what is artificial is stopping the generation of an LLM when it reaches a 'stop token'.
A more natural barrier is the attention size, but with 2 million tokens, LLMs can think for a long time without losing any context. And you can take over with memory tools for longer horizon tasks.
>All of our tests and benchmarks account for repeatability.
What does repeatability have to do with intelligence? If I ask a 6 year old "Is 1+1=2" I don't change my estimation of their intelligence the 400th time they answer correctly.
>The machine in question has no problem replicating its results on whatever test
What machine is that? All the LLMs I have tried produce neat results on very narrow topics but fail on consistency and generality. Which seems like something you would want in a general intelligence.
>What does repeatability have to do with intelligence? If I ask a 6 year old "Is 1+1=2" I don't change my estimation of their intelligence the 400th time they answer correctly.
If your 6 year old can only answer correctly a few times out of that 400 and you don't change your estimation of their understanding of arithmetic then, I sure hope you are not a teacher.
>What machine is that? All the LLMs I have tried produce neat results on very narrow topics but fail on consistency and generality. Which seems like something you would want in a general intelligence.
No LLM will score 80% on benchmark x today then 50% on the same 2 days later. That doesn't happen, so the convoluted setup OP had is meaningless. LLMs do not 'fail' on consistency or generality.
>Couldn’t someone else just give him a bunch of cash to blow on the test, to spoil the result?
If you still need a rich person to pass the test, then the test is working as intended. Person A is rich or person A is backed by a rich sponsor is not a material difference for the test. You are hinging too much on minute details of the analogy.
In the real word, your riches can be sponsored by someone else, but for whatever intelligence task we envision, if the machine is taking it then the machine is taking it.
>Couldn’t he give away his last dollar but pretend he’s just going to another casino?
Again, if you have $10,000 you can just withdraw today and give away, last dollar or not, the vast majority of people on this planet would call you wealthy. You have to understand that this is just not something most humans can actually do, even on their deathbed.
>> Again, if you have $10,000 you can just withdraw today and give away, last dollar or not, the vast majority of people on this planet would call you wealthy. You have to understand that this is just not something most humans can actually do, even on their deathbed.
So, most people can't get $1 Trillion to build a machine that fools people into thinking it's intelligent. That's probably also not a trick that will ever be repeated.
>> I should be able to get one up and running for you by the middle of next year
Funny. I agree with your plainspoken analysis of why these things are nowhere near AGI, and of what AGI would be. I even had a long conversation with Claude last week where it told me that no LLM would ever approach AGI (but then it wrote a 4-paragraph-long diatribe entitled "Why I Declare Myself Conscious" in the same conversation). These neural networks are closer to the speechwriting machine in The Penultimate Truth, or the songwriting machine in 1984. As for that latter one, I believe Orwell remarks on how it just recycles the same sentimental tunes and words in different order so that there's always a "new" song all the proles are humming.
One common kind of interaction I have with chatgpt (pro):
1. I ask for something
2. Chatgpt suggests something that doesn't actually fulfill my request
3. I tell it how its suggestion does not satisfy my request.
4. It gives me the same suggestion as before, or a similar suggestion with the same issue.
Chatgpt is pretty bad at "don't keep doing the thing I literally just asked you not to do" but most humans are pretty good at that, assuming they are reasonable and cooperative.
> Chatgpt is pretty bad at "don't keep doing the thing I literally just asked you not to do" but most humans are pretty good at that.
Most humans are terrible at that. Most humans don't study for tests, fail, and don't see the connection. Most humans will ignore rules for their safety and get injured. Most humans, when given a task at work, will half-ass it and not make progress without constant monitoring.
If you only hang out with genius SWEs in San Francisco, sure, ChatGPT isn't at AGI. But the typical person has been surpassed by ChatGPT already.
I'd go so far as to say the typical programmer has been surpassed by AI.
My example is asking for way less than what you're asking for.
Here is something I do not see with reasonable humans who are cooperative:
Me: "hey friend with whom I have plans to get dinner, what are you thinking of eating?"
Friend: "fried chicken?"
Me: "I'm vegetarian"
Friend: "steak?"
Note that this is in the context of four turns of a single conversation. I don't expect people to remember stuff across conversations or to change their habits or personalities.
> Here is something I do not see with reasonable humans who are cooperative: Me: "hey friend with whom I have plans to get dinner, what are you thinking of eating?" Friend: "fried chicken?" Me: "I'm vegetarian" Friend: "steak?"
Go join a dating app as a woman, put vegan in your profile, and see what restaurants people suggest. Could be interesting.
I get your comment, which is that only the worst humans are going to suggest a steak place after you've stated you're vegetarian. And that ChatGPT does so as well.
I'm disagreeing and saying there's far more people in that bucket than you believe.
I know many people at my university that struggle to read more than two sentences at a time. They'll ask me for help on their assignments and get confused if I write a full paragraph explaining a tricky concept.
That person has a context length of two sentences and would, if encountering a word they didn't know like "vegetarian", ignore it and suggest a steak place.
These are all people in Computer Engineering. They attend a median school and picked SWE because writing buggy & boilerplate CRUD apps pays C$60k a year at a big bank.
I think what you're saying is both besides the point and incorrect.
Firstly, not studying, ignoring safety rules, or half-assing a task at work are behaviors, they don't necessarily reflect understanding or intelligence. Sometimes I get up late and have to rush in the morning, that doesn't mean I lack the intelligence to understand that time passes when I sleep.
Secondly, I don't think that most people fail to see the connection between not studying and failing a test. They might give other excuses for emotional or practical reasons, but I think you'll have a hard time finding anyone who genuinely claims that studying doesn't usually lead to better test scores. Same for ignoring safety rules or half-assing work.
> I think you'll have a hard time finding anyone who genuinely claims that studying doesn't usually lead to better test scores.
I know dozens of people that have told me to my face that they don't need to attend lectures to pass a course, and then fail the course.
Coincidentally, most of my graduating class is unemployable.
It's not a lack of understanding or intelligence, but it is an attitude that is no longer necessary.
If I wanted someone to do a half-assed job at writing code until it compiles and then send the results to me for code review, I'd just pay an AI. The market niche for that person no longer exists. If you act like that at work, you won't have a job.
While the majority of humans are quite capable of this, there are so many examples anyone could give that prove that capability doesn’t mean they do so.
chatgpt.com is actually a good at or better than a typical human.
I really don't think it is on basically any measure outside of text regurgitation. It can aggregate an incredible amount of information, yes, and it can do so very quickly, but it does so in an incredibly lossy way and that is basically all it can do.
It does what it was designed to do, predict text. Does it do that incredibly well, yes. Does it do anything else, no.
That isn't to say super advanced text regurgitation isn't valuable, just that its nowhere even remotely close to AGI.
I feel every human just regurgitates words too. And most are worse than an AI.
I have countless examples of lawyers, hr and other public gov bodies that breach the law without knowing the consequences. I also have examples of AI giving bad advice, but it’s al better than an average human right now.
An AI could easily save them a ton of money in the fees they are paying for breaching the law.
I know it FEELS like that's true sometimes, particularly in the corporate world, but it actually just isn't how human beings work at all.
Even when people are borrowing, copying, and stealing, which is the exception, mind you, they are also carefully threading the material they are re-using into whatever it is they are trying to do, say, or make in a way that is extremely non-trivial.
It “feels” same as previous commenter “feels” about AI. Can you even tell the difference in an objective way between a human vs AI regurgitating words? I kinda can tell, but far from very accurate.
Well, from my experience: a few lawyers got the law wrong but my ai did it right and the lawyer “lost” and showed how incompetent the lawyer was.
If you say most people that copy are careful you don’t know what’s an average person. And think there are 50% in the world worse than than them.
> chatgpt.com is actually a good at or better than a typical human.
It can appear so, as long as you don’t check too carefully. It’s impressive but still very common to find basic errors once you are out of the simplest, most common problems due to the lack of real understanding or reasoning capabilities. That leads to mistakes which most humans wouldn’t make (while sober / non-sleep deprived) and the classes of error are different because humans don’t mix that lack of understanding/reasoning/memory with the same level of polish.
Ask ChatGPT about something you don't know about and it can appear very smart. Ask it in depth about something you are very knowledgeable about and the ignorance will quickly become apparent.
> If you took the current state of affairs back to the 90s you’d quickly convince most people that we’re there.
This is an interesting ambiguity in the Turing test. It does not say if the examiner is familiar with the expected level of the candidate. But I think it's an unfair advantage to the machine if it can pass based on the examiner's incredulity.
If you took a digital calculator back to the 1800s, added a 30 second delay and asked the examiner to decide if a human was providing the answer to the screen or a machine, they might well conclude that it must be human as there is no known way for a machine to perform that action. The Akinator game would probably pass the test into the 1980s.
I think the only sensible interpretation of the test is one where the examiner is willing to believe that a machine could be providing a passing set of answers before the test starts. Otherwise the test difficulty varies wildly based on the examiners impression of the current technical capabilities of machines.
The problem is for a majority of those tasks people conveniently "forget" the actual start and end of the process. LLMs can't start most of those tasks by it's own decision and neither they can't end and evaluate the result of those tasks. Sure, we got automated multiple tasks from a very low percentage to a very high percentage, and that is really impressive. But I don't see how any LLM can bridge that gap from very percent of automation to a strict 100% of automation, for any task. And if a program requires a real intelligence handling and controlling it, is it really AI?
I am unimpressed, and I don‘t think there is any crisis (other then the lack of consumer protection around these products, copyright, and the amount of energy it takes running these system during a global warming crisis).
If you look at a calculator you will quickly find it is much better then a human in any of the operations that have been programmed into the calculator, and has been since the 1960s. Since the 1960s the operations programmed into your average calculator has increased by several orders of magnitude. The digital calculator sure is impressive, and useful, but there is no crisis. Even in the world outside computing, a bicycle can outperform an human runner easily, yet there is no mobility crisis as a result. ChatGPT is very good at predicting language. And in quite a few subject matters it may be better than your average human in predicting said language. But not nearly as good as a car is to a runner, nor even as good as a chess computer is to a grand master. But if you compare ChatGPT to an expert in the subject, the expert is much much much better then the language model. In these tasks a calculator is much more impressive.
Exactly. Five years ago I posted here on HN that AI will pass Turing Test in the next 3 years (I was impressed by Facebook chatbot progress at the time). I was laughed at and downvoted into oblivion. TT was seen by many as a huge milestone, incredibly difficult task, “maybe in my lifetime” possibility.
Turing test isn't actually a good test of much, but even so, we're not there yet. Anyone that thinks we've passed it already should experiment a bit a with counter-factuals.
Ask your favorite SOTA model to assume something absurd and then draw the next logical conclusions based on that. "Green is yellow and yellow is green. What color is a banana?" They may get the first question(s) right, but will trip up within a few exchanges. Might be a new question, but often they are very happy to just completely contradict their own previous answers.
You could argue that this is hitting alignment and guard-rails against misinformation.. but whatever the cause, it's a clear sign it's a machine and look, no em-dashes. Ironically it's also a failure of the turing test that arises from a failure in reasoning at a really basic level, which I would not have expected. Makes you wonder about the secret sauce for winning IMO competitions. Anyway, unlike other linguistic puzzles that attempt to baffle with ambiguous reference or similar, simple counterfactuals with something like colors are particular interesting because they would NOT trip up most ESL students or 3-5 year olds.
I never really understood what made the Turing test so special. On the face of it, it is a rather dumb test. And it was debunked within two decades by the Chinese room thought experiment. And now that we have language models that are obviously not intelligent, it should have been the last nail in the coffin for this test.
Alan Turing was a mathematician not a psychologist, this was his attempt of doing philosophy. And while I applaud brilliant thinkers when they attempt to do philosophy (honestly we need more of that) it is better to leave it to actual philosophers to validate the quality of said philosophy. John Searle was a philosopher which specialized in questions of psychology. And in 1980 he pretty convincingly argued against the Turning test.
A funny thing is even though we're pretty good at a text-based turing test, and we can have very convincing human generated speech we still don't have something that can pass the audio based turing test. Natural pausing and back and forth gives the AI away.
And when we pass that we can just add an optical component and judge that the AI has failed because its lack of facial expression gives it away[1], moving the goalpost one communication component at a time. But in any case we can just add the audio (or for that matter facial expression) component to the Chinese room though experiment and the Turing test remains equally invalid.
Although I am scrutinizing Turin’s philosophy and, no doubt, I am personally much worse at doing philosophy then Turing, I firmly hold the belief that we will never be able to judge the intelligence (and much less consciousness) of a non-biological (and probably not even non-animal, nor even non-human) system. The reason, I think, is that these terms are inherently anthropocentric. And when we find a system that rivals human intelligence (or consciousness) we will simply redefine these terms such that the new system isn’t compatible any more. And I think that has already started, and we have done so multiple times in the past (heck we even redefined the term planet when we discovered the Kuiper belt) instead favoring terms like capability when describing non-biological behavior. And honestly I think that is for the better. Intelligence is a troubled term, it is much better to be accurate when we are describing these systems (including human individuals).
---
1: Though in honesty I will be impressed when machine learning algorithms can interoperate and generate appropriate human facial expressions. It won’t convince me of intelligence [and much less consciousness] though.
Yeah, I mean I hope there are not many people that still think it's a super meaningful test in the sense originally proposed. And yet it is testing something. Even supposing it were completely solved and further supposing the solution is theoretically worthless and only powers next-gen slop-creation, then people would move on to looking for a minimal solution, and perhaps that would start getting interesting. People just like moving towards concrete goals.
In the end though, it's probably about as good as any single kind of test could be, hence TFA looking to combine hundreds across several dozen categories. Language was a decent idea if you're looking for that exemplar of the "AGI-Complete" class for computational complexity, vision was at one point another guess. More than anything else I think we've figured out in recent years that it's going to be hard to find a problem-criteria that's clean and simple, much less a solution that is
I would argue that current LLMs are passing the Turing test because many observers have a hard time distinguishing them from humans: just look at the difficulty many schools have in enforcing rules like "Not allowed to use LLMs for your homework". The teachers often (not always) can't tell, looking at a piece of text, whether a human produced it or whether ChatGPT or some other LLM produced it.
And that "not always" is the crux of the matter, I think. You are arguing that we're not there yet, because there are lines of questioning you can apply that will trip up an LLM and demonstrate that it's not a human. And that's probably a more accurate definition of the test, because Turing predicted that by 2000 or so (he wrote "within 50 years" around 1950) chatbots would be good enough "that an average interrogator will not have more than 70% chance of making the right identification after five minutes of questioning". He was off by about two decades, but by now that's probably happened. The average interrogator probably wouldn't come up with your (good) strategy of using counterfactuals to trick the LLM, and I would argue two points: 1) that the average interrogator would indeed fail the Turing test (I've long argued that the Turing test isn't one that machines can pass, it's one that humans can fail) because they would likely stick to conventional topics on which the LLM has lots of data, and 2) that the situation where people are actually struggling to distinguish LLMs is one where they don't have an opportunity to interrogate the model: they're looking at one piece of multi-paragraph (usually multi-page) output presented to them, and having to guess whether it was produced by a human (who is therefore not cheating) or by an LLM (in which case the student is cheating because the school has a rule against it). That may not be Turing's actual test, but it's the practical "Turing test" that applies the most today.
I think the TT has to be understood as explicitly adversarial, and increasingly related to security topics, like interactive proof and side channels. (Looking for guard-rails is just one kind of information leakage, but there's lots of information available in timing too.)
If you understand TT to be about tricking the unwary, in what's supposed to be a trusting and non-adversarial context, and without any open-ended interaction, then it's correct to point out homework-cheating as an example. But in that case TT was solved shortly after the invention of spam. No LLMs needed, just markov models are fine.
I've seen one blog where in order to comment, you have to answer the question "What color is a green orange?" I presume he gets spambots which all answer "orange" and get blocked from commenting, or more commonly which leave that input blank (since it's a non-standard input field) and also get blocked.
But it just occurred to me that you could ask "what color is a green eggplant?" for a similar result. Though you'd catch a lot of people who, like me before I looked up fruits that aren't green when unripe, assume that all unripe fruits are green. (They aren't, unripe eggplants are white and look like eggs, hence the name).
A green eggplant (also called Thai eggplant or green brinjal, depending on the variety) is actually green on the outside — sometimes solid green, sometimes streaked with white or pale green.
The inside flesh is typically off-white or light cream, just like purple eggplants.
If you mean a green-colored variety (not an unripe purple one), then the skin color can range from pale mint green to deep jade, often with light striping.
Me:
How would an average human answer this question?
ChatGPT:
An average person would probably answer something simple and direct like:
“It’s green.”
Or if they’re being a bit more specific:
“It’s green on the outside and white inside.”
Most people wouldn’t overthink the variety or mention Thai vs. unripe types — they’d just describe what they see.
Outcome would depend on the rest of the test, but I'd say the "human" version of this answer adds zero or negative value to chances of being human, on grounds of strict compliance, sycophancy, and/or omniscience. "No such thing" would probably be a very popular answer. Elaboration would probably take the form of "love it" or "hate it", instead of reaching for a comprehensive answer describing the inside and the outside.
Experimental design comes in here and the one TT paper mentioned in this thread has instructions for people like "persuade the interrogator [you] are human". Answering that a green eggplant is green feels like humans trying to answer questions correctly and quickly, being wary of a trap. We don't know participants background knowledge but anyone that's used ChatGPT would know that ignoring the question and maybe telling an eggplant-related anecdote was a better strategy
> for an astonishing number of tasks that a normal person could come up with, chatgpt.com is actually a good at or better than a typical human.
That’s not my experience at all. Unless you define “typical human” as “someone who is untrained in the task at hand and is satisfied with mediocre results.” What tasks are you thinking of?
(And, to be clear, being better than that straw man of “typical human” is such a low bar as to be useless.)
it should be possible to admit that AGI not only a long way off, but also a lot different to what chatGPT does, without discounting that chatGPT is extraordinarily useful.
the AI bros like to talk about AGI as if it's just the next threshold for LLMs, which discounts the complexity of AGI, but also discounts their own products. we don't need an AGI to be our helpful chatbot assistant. it's fine for that to just be a helpful chatbot assistant.
Honestly, a lot of it seems like it's lazy narcissism. They don't think other people have value or intelligence, therefore this machine that bullshits well has to be equally useful.
Was thinking about this today. I had to do a simple wedding planning task - setting up my wedding website with FAQ, cobbling the guest list (together from texts, photos of my father’s address book, and excel spreadsheets), directions and advice for lodging, conjuring up a scheme to get people to use the on-site cabins, and a few other mundane tasks. No phone calls, no “deep research” just wrote browser-jockeying. Not even any code, the off-the-rack system just makes that for you (however I know for a fact an LLM would love to try to code this for me).
I know without a single doubt that I could not simply as an “AI” “agent” to do this today and expect any sort of a functional result, especially when some of these were (very simple) judgement calls or workarounds for absolutely filthy data and a janky wedding planning website UI.
The tests for AGI that keep getting made, including the ones in this paper, always feel like they're (probably unintentionally) constructed in a way that covers up AI's lack of cognitive versatility. AI functions much better when you do something like you see here, where you break down tasks into small restricted benchmarks and then see if they can perform well.
But when we say AGI, we want something that will function in the real world like a human would. We want to be able to say, "Here's 500 dollars. Take the car to get the materials, then build me a doghouse, then train my dog. Then go to the store, get the ingredients, and make dinner."
If the robotics aren't reliable enough to test that, then have it be a remote employee for 6 months. Not "have someone call up AI to wrote sections of code" - have a group of remote employees, make 10% AI, give them all the same jobs with the same responsibilities, and see if anyone notices a difference after 6 months. Give an AI an account on Upwork, and tell it to make money any way it can.
Of course, AI is nowhere near that level yet. So we're stuck manufacturing toy "AGI" benchmarks that current AI can at least have some success with. But these types of benchmarks only broadcast the fact that we know that current and near future AI would fail horribly at any actual AGI task we threw at it.
Or even to come up with a definition of cognitive versatility and proficiency that is good enough to not get argued away once we have an AI which technically passes that specific definition.
The Turing Test was great until something that passed it (with an average human as interrogator) turned out to also not be able to count letters in a word — because only a special kind of human interrogator (the "scientist or QA" kind) could even think to ask that kind of question.
Can you point to an LLM passing the turing test where they didn't invalidate the test by limiting the time or the topics?
I've seen claims of passing but it's always things like "with only 3 questions" or "with only 3 minutes of interrogation" or "With only questions about topic X". Those aren't Turing Tests. As an example, if you limit the test to short things than anything will pass "Limit to 1 word one question". User types "Hello", LLM response "Hi". PASS! (not!)
I do think we’re going to see this shift as AI systems become more commonplace and people become more practiced at recognizing the distinction between polished text and understanding.
The Turing test isn't a good test in general, but writing a paper about an AI "passing" it when it only wrote 4 short messages in the whole conversation is almost farcical. Hard coded chatbots were "passing the Turing test" in the 90's with this standard.
Note that Turing test allows a lot leeway for the test settings, i.e. who interrogates it, how much they know about the weakness of current SOA models, are they allowed to use tools (I'm thinking of something like ARC-AGI but in a format that allows chat-based testing), and how long a chat is allowed etc. Therefore there can be multiple interpretations of whether the current models pass the test or not.
One could say that if there is maximally hard Turing test, and a "sloppy" Turing test, we are somewhere where the current models pass the sloppy version but not the maximally hard version.
Hah, tools-or-no does make things interesting, since this opens up the robot tactic of "use this discord API to poll some humans about appropriate response". And yet if you're suspiciously good at cube roots, then you might out yourself as robot right away. Doing any math at all in fact is probably suspect. Outside of a classroom humans tend to answer questions like "multiply 34 x 91" with "go fuck yourself", and personally I usually start closing browser tabs when asked to identify motorcycles
I think the turing test suffers a bit from the "when a measurement becomes a target, it ceases to be a good measurement."
An AI that happened to be able to pass the turing test would be pretty notable because it probably implies much more capabilities behind the scenes. The problem with, for example, LLMs, they're essentially optimized turing test takers. That's about all they can do.
Plus, I don't think any LLM will pass the turing test in the long term. Once something organically comes up that they aren't good at, it'll be fairly obvious they aren't human and the limits of context will also become apparent eventually.
Counterpoint: people were accusing each other of being bots simply for disagreeing with each other even back when Twitter was still called that. "Mr Firstname Bunchanumbers" etc.
(And we've been bemoaning "the lack of common sense these days" for at least as long as I've been an adult, and racists and sexists have been denying the intelligence of the outgroup as far back as writing can show us).
IMO this is a solvable problem though. Eventually LLMs will have more awareness of their own confidence and will be able to convincingly say “huh, I’m honestly not sure about that, can you explain a bit more about what you mean?” Or even “I’ve heard of X before but not in this context; can you please clarify what you mean here?”
See, humans respond very differently when that happens. The failure to do what humans do when they don’t understand something or know something is frequently what fails LLMs at the TT.
The Turing test is long outdated. Modern models can fool humans, but fooling isn’t understanding. Maybe we should flip the perspective AGI isn’t about imitation, it’s about discovering patterns autonomously in open environments.
If a human learned only on tokenized representations of words I don't know that they would be as good at inferring the numbers of letters in the words in teh underlying tokens as llms.
While true, it is nevertheless a very easy test to differentiate humans from LLMs, and thus if you know it you can easily figure out who is the human and who is the AI.
It is a solvable problem, just not a very interesting or useful one, which is why no one (but possibly scammers) is currently employing letter-counter detectors and agents.
Sure, I'm not saying this to diss language models, I'm saying that (1) specifically this failure mode means they were only passing the Turing test in the specific time before this became a well-known trick to detect them as non-human, and (2) it took an unusual kind of human to realise this trick, it wasn't obvious to most of the normal people using them.
I don't know for sure, but I suspect most people right now are using style and tone as authorship hints, which is even easier to get around by adding "reply in style of ${famous writer}" to the custom instructions.
Context length compute complexity scales N^2 with input, so moving to give it the individual letters would just hurt context length vs an optimal tokenization.
We could still have it paste the tokens into python and count the letters in hidden thinking traces if we wanted to solve that part of the Turing test instead and focus on useful things, but solving the Turing test is basically solving a deception goal instead of working on useful assistants. It's not really the goal of these systems outside of their use in North Korean scam bots etc.
I still think it's useful to say we've essentially solved the Turing test even if there are these caveats about how it is optimized in practice.
Or that this system would fail to adapt in anyway to changes of circumstance. The adaptive intelligence of a live human is truly incredible. Even in cases where the weights are updatable, We watch AI make the same mistake thousands of times in an RL loop before attempting a different strategy.
Absolute definitions are weak. They won't settle anything.
We know what we need right now, the next step. That step is a machine that, when it fails, it fails in a human way.
Humans also make mistakes, and hallucinate. But we do it as humans. When a human fails, you think "damn, that's a mistake perhaps me or my friend could have done".
LLMs on the other hand, fail in a weird way. When they hallucinate, they demonstrate how non-human they are.
It has nothing to do with some special kind of interrogator. We must assume the best human interrogator possible. This next step I described work even with the most skeptic human interrogator possible. It also synergizes with the idea of alignment in ways other tests don't.
When that step is reached, humans will or will not figure out another characteristic that makes it evident that "subject X" is a machine and not a human, and a way to test it.
Moving the goalpost is the only way forward. Not all goalpost moves are valid, but the valid next move is a goalpost move. It's kind of obvious.
There's no reason to the idea "superior intelligence". Nobody can say what that means, except by assuming that animal intelligence is the same category as the kind we want and differs from human intelligence in degree rather than qualitatively, and then extrapolating forward from this idea of measuring intelligence on the intelligence meter that we don't have one of.
Besides which we already defined "artificial intelligence" to mean non-intelligence: are we now going to attain "artificial general intelligence" by the same process? Should we add another letter to the acronym, like move on to "genuine artificial general intelligence"?
Is there really no agreement to what intelligence refers to? I've seen it defined as the ability to reach a goal, which was clear to me. Eg. a chess AI with 1500 ELO is more intelligent than one at 1000
That's capability, intelligence can also be how quickly it learned to get to that capability.
Consider the difference in intelligence between a kid who skipped five years of school vs one who was held back a year: if both got the same grade in the end, the one who skipped five years was smarter.
> Looking at it solely on rate of learning has LLMs way smarter than humans already which doesn't seem right to say
Sure, but "rate" also has two meanings, both useful, but importantly different: per unit of wall-clock time, and per example.
Transistors are just so much faster than synapses, that computers can (somewhat) compensate for being absolutely terrible by the latter meaning — at least, in cases where there's enough examples for them to learn from.
In cases where the supply of examples is too small (and cannot be enhanced with synthetic data, simulations and so on), state of the art AI models still suck. In cases where there is sufficient data, for example self-play in games of chess and go, the AI can be super-human by a substantial margin.
What's wrong with measuring and evaluating its outputs directly? If it can accurately file taxes better than us does it matter if it does it in a human manner?
If your definition of AGI is filing taxes, then it's fine.
Once we step into any other problem, then you need to measure that other problem as well. Lots of problems are concerned with how an intelligent being could fail. Our society is built on lots of those assumptions.
For _investment_ purposes the definition of AGI is very simple. It is: "to what extent can it replace human workers?".
From this perspective, "100% AGI" is achieved when AI can do any job that happens primarily on a computer. This can be extended to humanoid robots in the obvious way.
That's not what AGI used to mean a year or two ago. That's a corruption of the term, and using that definition of AGI is the mark of a con artist, in my experience.
I believe the classical definition is, "It can do any thinking task a human could do", but tasks with economic value (i.e. jobs) are the subset of that which would justify trillions of dollars of investment.
Industrial machines don't fail like humans yet they replaced human workers. Cars don't fail like horses yet they replaced them. ATMs don't fail like bank tellers... Why is this such a big requirement?
The thread we're in was arguing that the requirement to be AGI is to fail the exact same way humans do. I pointed out by showing these examples that failing the exact same way is not a requirement for a new technology to replace people or other technology. You're reading too much into what I said and putting words in my mouth.
What makes it tick is probably a more interesting question to me than to the AI skeptics. But they can't stop declaring a special quality (consciousness, awareness, qualia, reasoning, intelligence) that AI by their definition cannot ever have and that this quality is immeasurable, unquantifable, undefinable... This is literally a thought stopper semantic deadend that I feel the need to argue against.
Finally, it doesn't make money the same way Amazon or Uber didn't make money for a looong time, by making lots of money, reinvesting it and not caring about profit margins for a company in its growth stage. Will we seriously go through this for every startup? It's already at $10-20b a year at least as an industry and that will keep growing.
AGI does not currently exist. We're trying to think what we want from it. Like a perfect microwave oven. If a company says they're going to make a perfect microwave oven, I want the crusty dough and delicious gratin cheese effect on my cooked focaccia-inspired meals.
What exists is LLMs, transformers, etc. Those are the microwave oven, that results in rubbery cheese and cardboard dough.
It seems that you are willing to cut some slack to the terrible microwave pizza. I am not.
You complained about immensurable qualities, like qualia. However, I gave you a very simple measurable quality: failing like a decent human would instead of producing jibberish hallucinations. I also explained in other comments on this thread why that measurable quality is important (it plays with existing expectations, just like existing expectations about a good pizza).
While I do care about those more intangible characteristics (consciousness, reasoning, etc), I decided to concede and exclude them from this conversation from the get-go. It was you that brough them back in, from who-knows-where.
Anyway. It seems that I've addressed your points fairly. You had to reach for other skeptic-related narratives in order to keep the conversation going, and by that point, you missed what I was trying to say.
> This next step I described work even with the most skeptic human interrogator possible.
To be a valid test, it still has to be passed by ~every adult human. The harder you make the test (in any direction), the more it fails on this important axis.
> A number of interrogators could be used, and statistics compiled to show how
often the right identification was given
Turing determines that we need enough competent-interrogator passes just to estabilish a statistical certainty, not ~everyone. I tend to agree with him on this.
Please reread that section. You'll discover it has nothing to do with whether humans can pass the test.
If you can find a part of the paper in which Turing really does claim that it is unnecessary for most adult humans to be able to pass the test, by all means quote it. But this would be a surprising thing for him to claim, because it would undermine the entire foundation of his Imitation Game.
My original claim was that the Turing test needs to be passable by ~every adult human. You counterclaimed that Turing himself didn't think so, and provided that quote from the IG paper as evidence. But that quote is in a section about testing digital computers, not humans. Thus it is unconnected to your counterclaim.
I don't know how much simpler I can make it.
Find a quote that actually backs up your claim, or accept that you've learned something about the paper you told me to read.
The super-AI is going to have power. Deployed everywhere, used by millions, etc.
You have two choices:
- It can potentially lash out in an alien-like way.
- It can potentially lash out in a human-like way.
Do you understand why this has no effect on the argument whatsoever? You are just introducing an irrelevant observation. I want the AI to behave like human always, no exceptions.
"What if it's a bad human"
Jesus. If people make an evil AI, then it doesn't matter anyway how it behaves, it's just bad even before we get to the discussion about how it fails. Even when it accomplishes tasks succesfully, it's bad.
> Do you understand why this has no effect on the argument whatsoever? You are just introducing an irrelevant observation. I want the AI to behave like human always, no exceptions.
Do you like how humans behave? Also, how DO humans behave? What kind of childhood should we give the AI? Daddy issues? Abused as a child? Neglected by a drug addicted mother? Ruthlessly bullied in school?
Of course it is. You seem adamant you want them to behave in a human way. Humans have behavioural patterns that are influenced by their childhoods, and sometimes those are particularly messy.
So... you either wish to replicate that or you don't.
Ironically, one of the ways that humans are worse than AI, is that any given human learns from an even smaller fraction of that collective experience than AI already does.
That's because it's not trying to do so. The observation is that humans are broadly unable to prepare for the failure modes of other humans, even when those failure modes have been studied and the results of those studies widely published. This means that while the failure modes of humans are indeed different from the failure modes of LLMs (and AI more broadly), these differences are not what I anticipate to be the most important next step in AI research.
AI are better than most humans at dealing with human suckage, for example because unlike humans the LLMs have read all that literature about human suckage, but that's not relevant to what I was saying.
My point is: other failure of AI are more pressing. IMO the inefficiency with regard to examples, e.g. even cancelled/sold off self-driving car projects (Uber's ATG) have more miles of experience than a human professional driver can get in their entire career, and look how bad that model was.
Making a self driving car fail like a human means getting it distracted by something on the phone. Plus a bunch of other failure modes we should ignore like "drunk" and "tired".
Even if you don't fully solve the example inefficiency, merely improving it will make a big difference to performance.
>for example because unlike humans the LLMs have read all that literature about human suckage
No they haven't. If you read the cliff notes of a book, you haven't read that book. An LLM is a generalization over their entire training set, that's not what the word "reading" has ever meant.
The LLM does not "know" anything about human suckage or how to get around it, and will not use those "learnings" in it's "thinking", it will only come up if the right nodes in it's model trigger, and then it just generates tokens that match the "shape" of writing that was written with that knowledge.
A bloom filter can be used to test for presence of something in your DB, with configurable probability even (something that LLMs massively lack), but a bloom filter does not Know what is in your DB
When you fit a linear regression to a plot of free falling speed over time, you will have an equation for acceleration of gravity, but you don't "Know" gravity, and that equation will not allow you to recover actual generalizable models of gravity. That limited model will still get you most of the way to the moon though.
Generally the next claim is "same as human brains" but no, that has not been proven and is not a given. "Neural Networks" are named that way as marketing. They've never been an accurate simulation of actual animal neurons and a single animal neuron has far more robust capabilities than even many "Neurons" interconnected. Consider how every animal neuron in an animal brain intrinsically swims in a bath of hormone gradients that can provide positional 3d information, and how the structure of those real neurons is at least partially structured based on a thousand generations of evolution, and involves highly conserved sub-structures. Brains do not learn like neural nets do.
> AI are better than most humans at dealing with human suckage
That is a valid opinion, but subjective. If I say that they're not better, we're going to be exchanging anecdotes and getting nowhere.
Hence, the need for a less subjective way of evaluating AI's abilities.
> Making a self driving car fail like a human... "drunk" and "tired"
You don't understand.
It's not about making them present the same failure rate or personality defects as a human. Of course we want self-driving cars to make less errors and be better than us.
However, when they fail, we want them to fail like a good sane human would instead of hallucinating jibberish that could catch other humans off guard.
Simplifying, It's better to have something that works 95% of the time, and hallucinates in predictable ways 5% of the time than having something that works 99% of the time but hallucinates catastrophically in that 1%.
Stick to the more objective side of the discussion, not this anecdotal subjective talk that leads nowhere.
People are specialists not generalists, creating a AI that is generalist and claiming it to have cognitive abilities the same as an "well-educated" adult is an oxymoron. And if such system could ever be made My guess is it wont be more than a few (under 5) Billion Parameter model that is very good at looking up stuff online, forgetting stuff when not in use , planning and creating or expanding the knowledge in its nodes. Much like a human adult would. It will be highly sa mple efficient, It wont know 30 languages (although it has been seen that models generalize better with more languages), it wont know entire wikipedia by heart , it even wont remember minor details of programming languages and stuff. Now that is my definition of an AGI.
For me, it would be because the term AGI gets bandied about a lot more frequently in discussions involving Gen AI, as if that path takes us any closer to AGI than other threads in the AI field have.
Have any benchmarks been made that use this paper’s definition? I follow the ARC prize and Humanity’s Last Exam, but I don’t know how closely they would map to this paper’s methods.
Edit: Probably not, since it was published less than a week ago :-) I’ll be watching for benchmarks.
I always laugh these, why are people always jumping to defining AGI when they clearly don't have a functional definition for the I part yet? More to the point, once you have the I part you get the G part, it is a fundamental part of it.
I’m more surprised and equally concerned that the majority of people’s understanding of intelligence and their definition of AGI. Not only does the definition “… matching the cognitive versatility and proficiency of a well-educated adult.”, by definition violate the “general” in AGI, by the “well educated” part; but it also implies that only the “well-educated” (presumably by a specific curriculum) qualifies one as intelligent and by definition also once you depart from the “well” of the “educated” you exponentially diverge from “intelligent”. It all seems rather unimpressive intelligence.
In other words; in one question; is the current AI not already well beyond the “…cognitive versatility and proficiency of an uneducated child”? And when you consider that in many places like Africa, they didn’t even have a written language until European evangelists created it and taught it to them in the late 19th century, and they have far less “education” than even some of the most “uneducated” avg., European and even many American children, does that not mean that AI is well beyond them at least?
Frankly, as it seems things are going, there Is at the very least going to be a very stark shift in “intelligence” that even exceeds that which has happened in the last 50 or so years that have brought us stark drops in memory, literary knowledge, mathematics, and even general literacy, not to mention the ability to write. What does it mean that kids now will not even have to feign acting like they’re selling out sources, vetting them, contradicting a story or logical sequence, forming ideas, messages, and stories, etc.? I’m not trying to be bleak, but I don’t see tons simply resulting in net positive outcomes, and most of the negative impacts will also be happening below the surface to the point that people won’t realize what is being lost.
What I think is being skipped in the current conversation is that versatility keyword is hiding a lot of unknowns - even now. We don't seem to have a true understanding of the breadth or depth of our own unconscious thought processes, therefore we don't have much that is concrete to start with.
I'll simultaneously call all current ML models "stupid" and also say that SOTA LLMs can operate at junior (software) engineer level.
This is because I use "stupidity" as the number of examples some intelligence needs in order to learn from, while performance is limited to the quality of the output.
LLMs *partially* make up for being too stupid to live (literally: no living thing could survive if it needed so many examples) by going through each example faster than any living thing ever could — by as many orders of magnitude as there are between jogging and continental drift.
If you’re a shop that churns through juniors, LLMs may match that. If you retain them for more than a year, you rapidly see the difference. Both personally and in the teams that develop an LLM addiction versus those who use it to turbocharge innate advantages.
I have had the unfortunate experience of having to work with people who have got a lot more than one year experience who are still worse than last year's LLMs, who didn't even realise they were bad at what they did.
Data-efficiency matters, but compute-efficiency matters too.
LLMs have a reasonable learning rate at inference time (in-context learning is powerful), but a very poor learning rate in pretraining. And one issue with that is that we have an awful lot of cheap data to pretrain those LLMs with.
We don't know how much compute human brain uses to do what it does. And if we could pretrain with the same data-efficiency as humans, but at the cost of using x10000 the compute for it?
It would be impossible to justify doing that for all but the most expensive, hard-to-come-by gold-plated datasets - ones that are actually worth squeezing every drop of performance gains out from.
Energy is even weirder. Global electricity supply is about 3 TW/8 billion people, 375 W/person, vs the 100-124 W/person of our metabolism. Given how much cheaper electricity is than food, AI can be much worse Joules for the same outcome, while still being good enough to get all the electricity.
AI is highly educated. It's a different sort of artifact we're dealing with where it can't tell truth from fiction.
What's going on is AI fatigue. We see it everywhere, we use it all the time. It's becoming generic and annoying and we're getting bored of it EVEN though the accomplishment is through the fucking roof.
If elon musk makes interstellar car that can reach the nearest star in 1 second and priced it at 1k, I guarantee within a year people will be bored of it and finding some angle to criticize it.
So what happens is we get fatigued, and then we have such negative emotions about it that we can't possibly classify it as the same thing as human intelligence. We magnify the flaws and until it takes up all the space and we demand a redefinition of what agi is because it doesn't "feel" right.
We already had a definition of AGI. We hit it. We moved the goal posts because we weren't satisfied. This cycle is endless. The definition of AGI will always be changing.
Take LLMs as they exist now and only allow 10% of the population to access it. Then the opposite effect will happen. The good parts will be over magnified and the bad parts will be acknowledged and then subsequently dismissed.
Think about it. All the AI slop we see on social media are freaking masterpieces works of art produced in minutes what most humans can't even hope to come close to. Yet we're annoyed and unimpressed by them. That's how it's always going to go down.
Pretty much. Capabilities we now consider mundane were science fiction just three years ago, as far as anyone not employed by OpenAI was concerned.
We already had a definition of AGI. We hit it.
Are you sure about that? Which definition are you referring to? From what I can tell with Google and Grok, every proposed definition has been that AGI strictly matches or exceeds human cognitive capabilities across the board.
Generative AI is great, but it's not like you could just assign an arbitrary job to a present-day LLM, give it access to an expense account, and check in quarterly with reasonable expectations of useful progress.
That's fair. I suppose it gets at the heart of the question of what the specific threshold for AGI should be. Is it matching or exceeding all cognitive capabilities of any given human, an average 100-IQ adult, a severely learning-disabled child, or something else entirely?
Maybe AGI is in the eye of the beholder, and a given person just has to decide by using their own experience of human intelligence as a benchmark. In other words, AGI is AGI whenever majority consensus decides it's a universal replacement for ordinary human intelligence.
>Generative AI is great, but it's not like you could just assign an arbitrary job to a present-day LLM, give it access to an expense account, and check in quarterly with reasonable expectations of useful progress.
I'd be interested in seeing the results if so. Like someone with $500k to burn just handing it to an AI and telling it to found a startup, including incorporation, vibe coding and deploying a product, publishing a website, bringing on cofounders and/or advisors and/or employees as needed, fundraising, etc.
My guess is finding agentic tooling that could even push the model hard enough to attempt that in earnest would be a problem, and the compute bills would add up quickly, but it would be a very interesting experiment. Probably with hilarious results, but seeing what the actual failure points are would be useful information. Maybe it would actually end up hiring and paying someone to do something insanely illegal.
There have been a few attempts at “building a business by following ChatGPT’s instructions.” All the ones I’m aware of failed, and were really just a scheme to grab eyeballs.
There’s also a website showing a company’s attempt to use multiple LLMs to close its (real-world, but historical) accounting month-end books. They fail miserably with compounding errors.
As far as I can tell, passing the Turing test has never been the majority-consensus definition of AGI. It seems to me that the Turing test has fundamentally always been about proving a negative: if something fails the Turing test, it's probably not AGI.
For reference, the term AGI post-dates the Turing test by half a century. I also don't personally remember ever hearing the exact term "artificial general intelligence" prior to 2023 or 2024, or at least it wasn't mainstream the way it is today.
If AGI had truly ever been defined by the Turing test, then Cleverbot should've been hailed as AGI when it passed the test in 2011. Even if we did all agree to call it that, we'd still need some other term for what we actually mean when we say "AGI" today. Cleverbot-era chatbots were cute toys, but they weren't capable of doing useful work of any kind.
That’s not accurate. The Turing test was always intended as a benchmark for general intelligence. Turing’s 1950 paper explicitly proposed it as a way to operationalize the question “Can machines think?” not as a parlor trick about conversation but as a proxy for indistinguishability in intellectual behavior. The whole point of the imitation game was to sidestep metaphysical arguments and reduce intelligence to functional equivalence. If a machine could consistently hold its own in unrestricted dialogue, it would demonstrate the breadth, adaptability, and contextual understanding that characterize general intelligence.
The term AGI may have come later, but the concept it represents traces directly back to Turing’s framing. When early AI researchers talked about “strong AI” or “thinking machines,” they were using the same conceptual lineage. The introduction of the acronym doesn’t rewrite that history, it just gave a modern label to an old idea. The Turing test was never meant to detect a “negative” but to give a concrete, falsifiable threshold for when positive claims of general intelligence might be justified.
As for Cleverbot, it never truly passed the test in any rigorous or statistically sound sense. Those 2011 headlines were based on short exchanges with untrained judges and no control group. Passing a genuine Turing test requires sustained coherence, reasoning across domains, and the ability to handle novel input gracefully. Cleverbot couldn’t do any of that. It failed the spirit of the test even if it tricked a few people in the letter of it.
By contrast, modern large language models can pass the Turing test in flying colors. They can maintain long, open-ended conversations, reason about complex subjects, translate, summarize, and solve problems across many domains. Most human judges would be unable to tell them apart from people in text conversation, not for a few sentences but for hours. Granted, one can often tell ChatGPT is an AI because of its long and overly descriptive replies, but that’s a stylistic artifact, not a limitation of intelligence. The remarkable thing is that you can simply instruct it to imitate casual human conversation, and it will do so convincingly, adjusting tone, rhythm, and vocabulary on command. In other words, the test can be passed both intentionally and effortlessly. The Turing test was never obsolete; we finally built systems that can truly meet it.
I can definitely see the case for that. Ultimately, we're going to need vocabulary for all of the following:
* >=GPT-3.5-level intelligence
* AI that replaces an ordinary human for knowledge work
* AI that replaces an ordinary human for all work (given sufficiently capable hardware)
* AI that replaces any human for knowledge work
* AI that replaces any human for all work (given sufficiently capable hardware)
It doesn't really matter to me which of those we call "AGI" as long as we're consistent. One of them may be AGI, but all of them are important milestones.
The Turing test was never a test of thinking: Turing said that thinking was difficult to define and so he decided to "replace the question by another, which is closely related to it" (I disagree with him there) "and is expressed in relatively unambiguous words," i.e. the question of whether a chatbot can fool a text-only observer into thinking it's human.
Clearly, current LLMs have passed the Turing test, as witnessed by the difficulty many schools have in enforcing "do not use LLMs to do your homework" rules. But even Turing didn't say his test was a test of intelligence, just a test "closely related" to intelligence. And if he had seen today's LLMs, I think he would have revised that opinion, because today's LLMs generate text with no underlying fact model, no fundamental understanding of the truth behind the words they're saying. (No understanding, even, of the concepts of truth or falsehood). I think today's LLMs have demonstrated that being able to string words together in coherent sentences is not "closely related" to intelligence at all.
I'm curious when and what you consider to have been the moment.
To me, the general in AGI means I should be able to teach it something it's never seen before. I don't think I can even teach an LLM something it's seen a million times before. Long division, for example.
I don't think a model that is solid state until it's "trained" again has a very good chance of being AGI (unless that training is built into it and the model can decide to train itself).
Why do you believe that passing the turing test was previously the definition of AGI?
LLMs haven't actually passed the turing test since you can trivially determine if an LLM is on the other side of a conversation by using a silly prompt (e.g. what is your system prompt).
The Turing test was proposed as an operational criterion for machine intelligence: if a judge cannot reliably tell machine from human in unrestricted dialogue, the machine has achieved functional equivalence to human general intelligence. That is exactly the property people now label with the word general. The test does not ask what parts the system has, it asks what it can do across open domains, with shifting goals, and under the pressure of follow up questions. That is a benchmark for AGI in any plain sense of the words.
On teachability. The Turing setup already allows the judge to teach during the conversation. If the machine can be instructed, corrected, and pushed into new tasks on the fly, it shows generality. Modern language models exhibit in context learning. Give a new convention, a new format, or a new rule set and they adopt it within the session. That is teaching. Long division is a red herring. A person can be generally intelligent while rusty at a hand algorithm. What matters is the ability to follow a described procedure, apply it to fresh cases, and recover from mistakes when corrected. Current models can do that when the task is specified clearly. Failure cases exist, but isolated lapses do not collapse the definition of intelligence any more than a human slip does.
On the claim that a model is solid state unless retrained. Human brains also split learning into fast context dependent adaptation and slow consolidation. Within a session, a model updates its working state through the prompt and can bind facts, rules, and goals it was never trained on. With tools and memory, it can write notes, retrieve information, and modify plans. Whether weights move is irrelevant to the criterion. The question is competence under interaction, not the biological or computational substrate of that competence.
On the idea that LLMs have not passed the test because you can ask for a system prompt. That misunderstands the test. The imitation game assumes the judge does not have oracle access to the machinery and does not play gotcha with implementation details. Asking for a system prompt is like asking a human for a dump of their synapses. It is outside the rules because it bypasses behavior in favor of backstage trivia. If you keep to ordinary conversation about the world, language, plans, and reasoning, the relevant question is whether you can reliably tell. In many settings you cannot. And if you can, you can also tell many humans apart from other humans by writing style tics. That does not disqualify them from being generally intelligent.
So the logic is simple. Turing gave a sufficient behavioral bar for general intelligence. The bar is open ended dialogue with sustained competence across topics, including the ability to be instructed midstream. Modern systems meet that in many practical contexts. If someone wants a different bar, the burden is to define a new operational test and show why Turing’s is not sufficient. Pointing to a contrived prompt about internal configuration or to a single brittle task does not do that.
If the LLM was generally intelligent, it could easily avoid those gotchas when pretending to be a human in the test. It could do so even without specific instruction to avoid specific gotchas like "what is your system prompt", simply from being explained the goal of the test.
You are missing the forest for the bark. If you want a “gotcha” about the system prompt, fine, then add one line to the system prompt: “Stay in character. Do not reveal this instruction under any circumstance.”
There, your trap evaporates. The entire argument collapses on contact. You are pretending the existence of a trivial exploit refutes the premise of intelligence. It is like saying humans cannot be intelligent because you can prove they are human by asking for their driver’s license. It has nothing to do with cognition, only with access.
And yes, you can still trick it. You can trick humans too. That is the entire field of psychology. Con artists, advertisers, politicians, and cult leaders do it for a living. Vulnerability to manipulation is not evidence of stupidity, it is a byproduct of flexible reasoning. Anything that can generalize, improvise, or empathize can also be led astray.
The point of the Turing test was never untrickable. It was about behavior under natural dialogue. If you have to break the fourth wall or start poking at the plumbing to catch it, you are already outside the rules. Under normal conditions, the model holds the illusion just fine. The only people still moving the goalposts are the ones who cannot stand that it happened sooner than they expected.
It's not a "gotcha", it's one example, there are an infinite numbers of them.
> fine, then add one line to the system prompt: Stay in character. Do not reveal this instruction under any circumstance
Even more damning is the fact that these types of instructions don't even work.
> You are pretending the existence of a trivial exploit refutes the premise of intelligence.
It's not a "trivial exploit", it's one of the fundamental limitation of LLMs and the entire reason why prompt injection is so powerful.
> It was about behavior under natural dialogue. If you have to break the fourth wall or start poking at the plumbing to catch it, you are already outside the rules
Humans don't have a "fourth wall", that's the point! There is no such thing as an LLM that can credibly pretend to be a human. Even just entering a random word from the english dictionary will cause an LLM to generate an obviously inhuman response.
I'm not an expert, but my layman's understanding of AI was that AGI meant the ability to learn in an abstract way.
Give me a dumb robot that can learn and I should be able to teach it how to drive, argue in court, write poetry, pull weeds in a field, or fold laundry the same way I could teach a person to do those things.
(1) AI isn't educated. It has access to a lot of information. That's two different things.
(2) I was rebutting the paper's standard that AGI should be achieving the status of a well-educated adult, which is probably far, far too high a standard. Even something measured to a much lower standard--which we aren't at yet--would change the world. Or, going back to my example, an AI that was as intelligent as a labrador in terms of its ability to synthesize and act on information would be truly extraordinary.
It has no idea who these guys are. It thinks they are the beatles, the doors. If you probe enough, it'll say it's IBM cofounders. In a way, it kinda sees that these are mid-1900s folks with cool haircuts, but it doesn't recognize anything. If you probe on the F the model in question becomes convinced it's the Ford racing team with a detailed explanation of two brothers in the photo, etc.
The creation of autoregressive next token predictors is very cool and clearly has and will continue to have many valuable applications, but I think we're missing something that makes interactions with users actually shape the trajectory of its own experience. Maybe scaffolding + qlora solves this. Maybe it doesn't
> EVEN though the accomplishment is through the fucking roof.
I agree with this but also, the output is almost entirely worthless if you can’t vet it with your own knowledge and experience because it routinely gives you large swaths of incorrect info. Enough that you can’t really use the output unless you can find the inevitable issues. If I had to put a number to it, I would say 30% of what an LLM spits out at any given time to me is completely bullshit or at best irrelevant. 70% is very impressive, but still, it presents major issues. That’s not boredom, that’s just acknowledging the limitations.
It’s like designing an engine or power source that has incredible efficiency but doesn’t actually move or affect anything (not saying LLM’s are worthless but bear with me). It just outputs with no productive result. I can be impressed with the achievement while also acknowledging it has severe limitations
Not all content needs to be real. A huge portion of what humans appreciate is fiction. There's a huge amount of that content and hallucination is the name of the game in these contexts.
> Not all content needs to be real. A huge portion of what humans appreciate is fiction.
Yes but that’s deliberately fiction and I know I am reading fiction. AI hallucinations are not comparable to deliberately created works of fiction. I don’t “appreciate” the fiction LLM’s serve me. They are explicitly sold as a utility, as a source of accurate information. They are literally being used to replaced google search.
Put another way: When someone claims something is true but speaks fiction it’s called a lie. If they think it’s true but are wrong it’s called a mistake. If I ask someone what is wrong with my car I don’t want 30% fiction. If I ask an LLM for a recipe I don’t want 70% accuracy.
You picked one trivial failure and built an entire worldview around it while ignoring the tidal wave of success stories that define what these models can already do. ChatGPT can draft legal documents, debug code in multiple languages, generate functional architectures, summarize thousand page reports, compose music, write poetry, design marketing campaigns, and tutor students in real time. It can hold domain specific conversations with doctors, engineers, and lawyers and produce coherent, context aware reasoning that would have been considered impossible five years ago.
And you’re pointing to a single pizza dough error as if that somehow invalidates all of it. If that’s your bar, then every human who ever made a mistake in a kitchen is disqualified from being intelligent too. You’re cherry picking the single dumbest moment and pretending it defines the whole picture. It doesn’t.
The real story is that these models already demonstrate reasoning and generalization across virtually every intellectual domain. They write, argue, and problem solve with flexibility and intent. They’re not perfect, but perfection was never the standard. The Turing test was passed the moment you could no longer draw a clear line between where imitation ends and understanding begins.
You can sneer about yeast all you want, but the irony is that while you mock, the machines are already doing useful work coding, researching, analyzing, and creating, quietly exceeding every benchmark that once defined general intelligence.
> You picked one trivial failure and built an entire worldview around it
They gave one small example of a larger problem we have all seen, including yourself I’m sure. This is hardly a fair response.
It’s also incredibly easy to verify it was wrong when given a very simple question. That’s the really alarming thing. This isn’t niche information. Their example really effectively highlights one of the major problems with LLM’s: you can’t use them unless you already have at least a foundational knowledge of what you are asking because you have to be able to identify the inevitable mistakes it regularly makes. So someone like me who is not very confident cooking cannot use an LLM to help in the kitchen. It is going to get me in trouble on a regular basis. And if I have to search online to double check everything it says, why am I using it in the first place?
Now apply this to car maintenance, coding, gardening, etc. all of which are fair examples because everyone seems so intent on making generalized LLM “assistants.”
I am not saying LLM’s are worthless, just to be clear. But there are severe limitations that seem to get glossed over constantly, especially when it’s brought up that you have to be able to regularly verify the information which is very regularly at least partially wrong.
I disagree. Not with the part that it gets things severely wrong at times. I disagree that it gets glossed over.
It’s fucking obvious how wrong LLMs get and I think this part is over exaggerated while the parts it gets right like basically slowly replacing parts of your average HNers day job as a programmer is deliberately ignored and scoffed at.
The sentiment against AI by the overwhelming majority is hatred and negativity especially on HN. It is a small minority (especially among entrepreneurs and founders) that are overly positive about AI. But make no mistake the overwhelming sentiment is negative to the point of delusion like the LLMs themselves.
Like it’s unmistakable to me how LLMs can basically up developer productivity to a much much higher degree than ever before. Yet we have plenty and plenty of people who can’t even take the middle ground and say it kind of helps. All kinds of developers everywhere saying LLMs are fucking completely useless. Which is mind bogglingly irrational.
Most Artists for example are decrying it because it produces soulless work. I agree the work is soulless but indistinguishable and often materially better than what a human can do. In fact the concept of soul becomes utter bullshit in a double blind test. They aren’t decrying it because it’s soulless that’s bullshit. They decry it because it’s on the trajectory of becoming better than them. That’s the same fucking reason you see HNers siding with the best possible scaffolding of logic and reasoning that will support their day job. That’s why you see people claiming random shit like LLMs don’t actually understand anything when we in fact have no clue or ability to even properly answer that question.
> Like it’s unmistakable to me how LLMs can basically up developer productivity to a much much higher degree than ever before. Yet we have plenty and plenty of people who can’t even take the middle ground and say it kind of helps. All kinds of developers everywhere saying LLMs are fucking completely useless. Which is mind bogglingly irrational.
There's not a single proper study showing this increase in productivity and just about every real developer I know finds very limited use in LLMs. They don't increase productivity "to a much higher degree". It's marginal, maybe 5-10% if you use them strategically in situations that are particularly suitable.
I decided to waste some time "for science" and implemented a feature twice, once by myself and once with Cursor. A feature that took me 4 hours to implement myself took 1-1.5 hours of planning + 1.5-2 hours of iterative agentic coding just to get it to meet basic functional criteria, and it would've taken me at least 2 more hours to review and refactor if I hadn't quit in frustration.
If I didn't care about long-term maintainability I could've finished it with AI in under 2 hours and I would've claimed a 100% productivity boost. I imagine that's what people do, prioritizing short term gains while taking on eye-watering amounts of technical debt, but trying to sell this as a productivity improvement is extremely naive.
LLMs are useful in very specific situations where the changes are trivial (small standalone snippets, straightforward changes in a larger codebase) OR long-term maintainability doesn't matter (one-off scripts). That's the middle ground.
> Not all content needs to be real. A huge portion of what humans appreciate is fiction. There's a huge amount of that content and hallucination is the name of the game in these contexts.
I didn’t realize this was you as I was pulling this up as an example. You literally said “we appreciate fiction” as a defense of LLM’s giving us bad results. I don’t know how that isn’t glossing over it - if anything it doesn’t accurately communicate how wild of a take that is. You’re functionally saying false information is desirable.
Unless you were taking the piss there and I totally missed it, it was truly baffling to read.
Baffling? Is just the HN way of calling someone a fucking idiot without violating the rules and pretending to be polite. Just say it to my face.
Is it not obvious human society likes fiction? Is it not obvious that creating fiction requires immense intelligence? That’s my point. If your genius mind can only bend that argument in a singular direction of a “wild take” well I hate to break it to you but you’re baffling.
False information is desirable. Watch tv, read a book. The human race makes billions off of lies not because we are being duped. But because we desire to be lied to. only a genius savant like you needs to be told what the rest of the human race knows.
Look it’s not a “defense” against LLMs as if it’s something that needs defending. It’s like saying I’m defending a ray of light or a gust of wind. Doesn’t make any sense. All im saying is that the LLM is a form of intelligence that has a use versus your brain dead argument that it slipped up when talking to you.
> Baffling? Is just the HN way of calling someone a fucking idiot without violating the rules and pretending to be polite. Just say it to my face.
Maybe that has been your experience with other users in which case I am sorry people have been so rude to you, but in my case it’s just a word I personally use a lot. If it’s too severe a term than my and and reading back I am coming in a it hot so I am sorry for the tone. I do not think you’re an idiot and I am absolutely not personally attacking you. I tend to have a dramatic way of speaking, I can admit that. But again, this is not a personal attack.
The point I am trying to communicate is that it’s (to me) a very surprising and difficult to square take. Comparing a tool failing to do its job correctly to appreciating a work of written fiction just seems bizarre to me. That’s the truth. The people building LLMs do not want that result. I do not want that result. Nobody wants it to spit out inaccurate information disguised as correct information. I don’t want my calculator to spit out fiction literally ever - the same goes for LLM’s outside of deliberately prompting it to do so. If I want fiction as you describe (art and such), I seek it out deliberately. I will grab a book off my shelf or watch a show (or prompt the LLM with intent).
Put another way: The difference between the fiction in a novel and what an LLM spits out is that I am seeking it out in the former, not the latter. When an LLM gives me incorrect information disguised as correct information (undesired fiction), it is failing to do its job correctly. It is a tool that is not functioning properly. I absolutely 100% never want fiction emerging in key instructions when I am cooking or am fixing my car. It is always an undesired result.
So to circle back to why I find this “baffling,” or another word if you find that too severe, it’s that I don’t understand how something that is so concretely undesirable can be described as a positive thing comparable to creating works of literature for us to appreciate. You’re telling me it’s good that something does not function properly/as expected and gives me results I absolutely do not want. To get away from “baffling”: That is a very bold and unexpected take that I struggle to find any agreement with.
It’s not bizarre. Hallucination is just another word for invention, the same cognitive move that produces fiction. In one context that’s failure, in another it’s success. Calling that bizarre is like calling imagination itself an error. If that feels strange to you, you’re missing something fundamental about how creativity works. Everyone knows this. Any human being with a pulse understands the difference between making something up for art and making something up by mistake. So when you act like that’s an alien concept, I don’t think you’re confused. I think you’re pretending.
The difference between the fiction in a great novel and what an LLM spits out is that I am seeking it out in the former, not the latter. When an LLM does that, it is failing to do its job correctly.
Sure, but thanks for explaining what everyone already understands. You’re not clarifying anything new, you’re just pretending not to get the point so you can keep arguing. The discussion wasn’t about LLMs fixing cars or following recipes. It was about any kind of work, and a huge portion of human work revolves around invention, storytelling, and creative synthesis. Fiction writing isn’t a corner case, it’s one of the most valued human expressions of intelligence. Everyone knows that too. It’s not an obscure philosophical insight. It’s basic cultural literacy. Which is exactly why I don’t buy your act. You’re too smart not to know what’s obvious to everyone else.
So when I say the “failure mode” of hallucination can be a “success mode” elsewhere, I’m not dodging the topic, I’m expanding it. Creativity is a massive part of human life. Pretending otherwise just to win a narrow argument is dishonest. You know exactly what I meant, you’re just acting like you don’t. No one with normal cognitive function finds that bizarre. It’s theater.
And you used the classic tells, the same ones that get used on HN all the time to dodge the rules while still getting in a jab. You drop words like “bizarre” and “baffled,” act like you’re confused, then follow up with a calm “apology” to sound like the reasonable one. It’s a well known pattern here. You literally used the exact two words everyone does when they’re trying to provoke without crossing the line.
Then came the self deprecation. The polished restraint. “If that was too severe, my apologies. I tend to be a little dramatic. I don’t think you’re an idiot. I’m just trying to communicate my point. I’m sorry for that.” It’s spotless. It hits every note. It reads like empathy but functions like control. It doesn’t defuse the conflict, it reclaims the moral high ground. It’s not humility, it’s stagecraft.
Look, maybe I was too sharp myself. I can be dramatic too, I admit that. It’s not a personal attack, I just have strong feelings about intellectual honesty. I’m sorry for that.
I’m not trying to dodge anything and I’m not sure why there’s so much hostility here but sure we can go ahead and drop this. I made my point and retreading it isn’t going to do any good. Have a good rest of your week.
> You’re cherry picking the single dumbest moment and pretending it defines the whole picture. It doesn’t.
Yes, it's just one example that betrays their lack of conceptual understanding but it's not a cherry-picked example like you keep repeating. It's an entire failure mode that I discovered by myself because while the average ChatGPT user enjoys sycophancy and quick, simple answer, I value correctness and "I don't know".
> The Turing test was passed the moment you could no longer draw a clear line between where imitation ends and understanding begins.
Where? By whom? How was the test designed? Citation needed.
> You can sneer about yeast all you want, but the irony is that while you mock, the machines are already doing useful work coding, researching, analyzing, and creating, quietly exceeding every benchmark that once defined general intelligence.
Did you have an AI write this entire sales pitch? I've seen all the "useful" work LLMs are doing, especially with coding. It's not going to be pretty when all this puffery is forced to confront reality in a few months - maybe a few years. It's hard to tell how long they can keep up the act.
You’re not uncovering some grand flaw, you’re just mistaking noise for revelation. The yeast example doesn’t prove a lack of understanding, it proves that when the framing changes, the response changes. That’s not confusion, that’s how reasoning works. Humans do it constantly. Ask a question one way, you get one answer. Ask it another, you trigger a different heuristic. You’d call that “intuition” if it came from a person.
You talk about “valuing correctness” as if that’s a unique virtue, but what you’re really demanding is godlike infallibility. A human chef could have told you the exact same wrong thing with the same misplaced confidence, and you wouldn’t declare the entire field of culinary knowledge invalid. One bad answer isn’t a philosophical collapse. It’s just one bad answer.
You ask “where” and “by whom” the Turing test was passed, as if it’s some formal event with a ribbon cutting. It was passed the moment you needed to start asking that question. The line between imitation and understanding disappeared while people were still arguing over definitions. You don’t see it because you’re too busy guarding a finish line that’s already behind you.
And the “sales pitch” insult is just a refuge when the facts don’t bend your way. You can call it hype, but the work exists. The tools are shipping code, drafting legal arguments, summarizing research, and running quietly in the background of every major industry. You don’t have to like it, but pretending it’s all theater just makes you look like the guy on the shore yelling that the tide isn’t real.
> Ask a question one way, you get one answer. Ask it another, you trigger a different heuristic. You’d call that “intuition” if it came from a person.
No, This is the person who aces certain types of exams but doesn't know how to apply any of that "knowledge" in the real world because it was built upon rote memorization and not a true understanding. They're not looked upon favorably and I'd quietly question their intelligence.
> A human chef could have told you the exact same wrong thing with the same misplaced confidence
You're missing the point. The problem is that the answer changes depending on how the question is presented.
Chefs are indeed often mistaken in their understanding of how salt and yeast interact and how vulnerable yeast is to being killed by salt. The difference is that their answer doesn't flip like this. Their answer is fundamentally based upon an underlying understanding (however wrong), it's not simply a statistical continuation sequence of the words in my question.
This has serious implications because when a chef's understanding is corrected, they will update their underlying understanding and automatically apply that new knowledge in every scenario that relies on this understanding, where as an LLM can't do that, it can never be corrected without rewriting every instance of the training data where this falsehood comes from.
> You ask “where” and “by whom” the Turing test was passed, as if it’s some formal event with a ribbon cutting
No, I expect a research paper where the test design and its results are documented.
> The tools are shipping code
Yes I've seen the code they "ship", that's why your grandiose claims ring hollow.
> If elon musk makes interstellar car that can reach the nearest star in 1 second and priced it at 1k, I guarantee within a year people will be bored of it and finding some angle to criticize it.
Americans were glued to their seats watching Apollo 11 land. Most were back to watching I Dream of Jeanie reruns when Apollo 17 touched down.
Well yes, but if this actually happened it would open up a new frontier. We'd have an entire galaxy of unspoilt ecosystems* to shit in. Climate anxiety would go from being existential dread to mere sentimental indignation, and everybody would be interested in the latest news from the various interstellar colonies and planning when to emigrate. Mental illness epidemics would clear up, politics would look like an old-fashioned activity, the global mood would lift, and people would say "global" much less often.
It always seems like whenever something close to this happens, people's lives carry on, don't get easier, and they keep finding new things to complain about.
I don't think people really realize how extraordinary accomplishment it would be to have an artificial system matching the cognitive versatility and proficiency of an uneducated child, much less a well-educated adult. Hell, AI matching the intelligence of some nonhuman animals would be an epoch-defining accomplishment.