Gemini 2.5 Pro is certainly a tipping point for me. Previous LLMs have been very impressive, especially on coding tasks (unsurprising as the answers to these have a preponderance of publicly available data). But outside of a coding assistant, LLMs til now felt like an extra helpful and less garbage-filled Google search.
I just used 2.5 Pro to help write a large research proposal (with significant funding on the line). Without going into detail, it felt to me like the only reason it couldn’t write the entire thing itself is because I didn’t ask it to. And by “ask it”, I mean: enter into the laughably small chat box the entire grant solicitation + instructions, a paragraph of general direction for what I want to explore, and a bunch of unstructured artifacts from prior work, and turn it loose. I just wasn’t audacious enough to try that from the start.
But as the deadline approached, I got more and more unconstrained in how far back I would step and let it take the reins - doing essentially what’s described above but on isolated sections. It would do pretty ridiculously complex stuff, like generate project plans and timelines, cross reference that correctly with other sections of text, etc. I can safely say it was a 10x force multiplier, and that’s being conservative.
For scientific questions (ones that should have publicly available data, not ones relying on internal data), I have started going to 2.5 Pro over senior experts on my own team. And I’m convinced at this point if I were to connect our entire research data corpus to Gemini, that balance would shift even further. Why? Because I can trust it to be objective - not inject its own political or career goals into its answers.
I’m at the point where I feel the main thing holding back “AGI” is people’s audacity to push its limits, plus maybe context windows and compute availability. I say this as someone who’s been a major skeptic up until this point.
LLMs at this point are stateless calculators without personal experience, life goals, obligations, etc. Till recently people expected to have a character like Terminator or HAL. Now we have intelligence separate from 'soul'. Can calculator be AGI? It can be Artificial, General, and Intelligence. We may need another word for 'creature' with some features of living being.
The capabilities of AI post gpt3 have become extraordinary and clearly in many cases superhuman.
However (as the article admits) there is still no general agreement of what AGI is, or how we (or even if we can) get there from here.
What there is is a growing and often naïve excitement that anticipates it as coming into view, and unfortunately that will be accompanied by the hype-merchants desperate to be first to "call it".
This article seems reasonable in some ways but unfortunately falls into the latter category with its title and sloganeering.
"AGI" in the title of any article should be seen as a cautionary flag. On HN - if anywhere - we need to be on the alert for this.
I think a reasonable definition of intelligence is the application of reason on knowledge. An example of a system that is highly knowledgeable but has little to no reason would be an encyclopedia. An example of a system that is highly reasonable, but has little knowledge would be a calculator. Intelligent systems demonstrate both.
Systems that have general intelligence are ones that are capable of applying reason to an unbounded domain of knowledge. Examples of such systems include: libraries, wikis, and forums like HN. These systems are not AGI, because the reasoning agents in each of these systems are organic (humans); they are more like a cyborg general intelligence.
Artificial general intelligence are just systems that are fully artificial (ie: computer programs) that can apply reason to an unbounded domain of knowledge. We're here, and we have been for years. AGI sets no minimum as to how great the reasoning must be, but it's obvious to anyone who has used modern generative intelligence systems like LLMs that the technology can be used to reason about an unbounded domain of knowledge.
I think the thing missing would be memory. The knowledge of current models is more or less static save for whatever you can cram into their context window. I think if they had memory and thus the ability to learn - “oh hey, I’ve already tried to solve a bug in these ways maybe I won’t get stuck in loop on them!” Would be the agi push for me. Real time incorporating new knowledge into the model is the missing piece.
It's not: whatever the way you define AGI, you cannot just ignore the key letter of the three letters acronym: G stands for “General”.
You can argue that for the first time in the history we have an AI that deserves its name (unlike Deep blue or AlphaGo which aren't really about intelligence at all) but you cannot call that Artificial GENERAL Intelligence before it overcomes the “jagged intelligence” syndrome.
We don't have this for humans either, other than the vague pseudoscience of IQ. As I've travelled more, and just grown older in general, I've come to accept a lot of humans as barely sentient.
Until you can boot one up, give it access to a VM video and audio feeds and keyboard and mouse interfaces, give it an email and chat account, tell it where the company onboarding docs are and expect them to be a productive team member, they're not AGI. So long as we need special protocols like MCP and A2A, rather than expecting them to figure out how to collaborate like a human, they're not AGI.
The first step, my guess, is going to be the ability to work through github issues like a human, identifying which issues have high value, asking clarifying questions, proposing reasonable alternatives, knowing when to open a PR, responding to code review, merging or abandoning when appropriate. But we're not even very close to that yet. There's some of it, but from what I've seen most instances where this has been successful are low level things like removing old feature flags.
Just because we rely on vision to interface with computer software doesn't mean it's optimal for AI models. Having a specialized interface protocol is orthogonal to capability. Just like you could theoretically write code in a proportional font with notepad and run your tools through windows CMD - having an editor with syntax highlighting and monospaced font helps you read/navigate/edit, having tools/navigation/autocomplete etc. optimized for your flow makes you more productive and expands your capability, etc.
If I forced you to use unnatural interfaces it would severely limit your capabilities as well because you'd have to dedicate more effort towards handling basic editing tasks. As someone who recently swapped to a split 36key keyboard with a new layout I can say this becomes immediately obvious when you try something like this. You take your typing/editing skills for granted - try switching your setup and see how your productivity/problem solving ability tanks in practice.
Agreed, but I also think to be called AGI, they should be capable of working through human interfaces rather than needing to have special interfaces created for them to get around their lack of AGI.
The catch in this though isn't the ability to use these interfaces. I expect that will be easy. The hard part will be, once these interfaces are learned, the scope and search space of what they will be able to do is infinitely larger. And moreover our expectations will change in how we expect an AGI to handle itself when our way of working with it becomes more human.
Right now we're claiming nascent AGI, but really much of what we're asking these systems to do have been laid out for them. A limited set of protocols and interfaces, and a targeted set of tasks to which we normally apply these things. And moreover our expectations are as such. We don't converse with them as with a human. Their search space is much smaller. So while they appear AGI in specific tasks, I think it's because we're subconsciously grading them on a curve. The only way we have to interact with them prejudices us to have a very low bar.
That said, I agree that video feed and mouse is a terrible protocol for AI. But that said, I wouldn't be surprised if that's what we end up settling on. Long term, it's just going to be easier for these bots to learn and adapt to use human interfaces than for us to maintain two sets of interfaces for things, except for specific bot-to-bot cases. It's horribly inefficient, but in my experience efficiency never comes out ahead with each new generation of UIs.
> Just because we rely on vision to interface with computer software doesn't mean it's optimal for AI models
This is true but AGI means "Artificial General Intelligence". Perhaps it would be even more efficient with certain interfaces, but to be general it would have to at least work with the same ones as humans.
Here's some things that I think a true AGI would need to be able to do:
* Control a general purpose robot and use vision to do housework, gardening etc.
* Be able to drive a car - equivalent interfaces to humans might be service motor controlled inputs.
* Use standard computer inputs to do standard computer tasks
And this list could easily be extended.
If we have to be very specific in the choice of interfaces and tasks that we give it, it's not a general AI.
At the same time, we have to be careful at moving the goalposts too much. But current AI are limited to what can be returned in a small number of interfaces (prompt with text/image/video & return text/image/video data). This is amazing, they can sound very intelligent while doing so. But it's important not to lose sight of what they still can't do well which is basically everything else.
Outside of this area, when you do hear of an AI doing something well (self driving, for example) it's usually a separate specialized model rather than a contribution towards AGI.
By this logic disabled people would not class as "Generally Intelligent" because they might have physical "interface" limitations.
Similarly I wouldn't be "Generally Intelligent" by this definition if you sat me at a Cyrillic or Chinese keyboard. For this reason, I see human-centric interface arguments as a red herring.
I think a better candidate definition might be about learning and adapting to new environments (learning from mistakes and predicting outcomes), assuming reasonable interface aids.
> Similarly I wouldn't be "Generally Intelligent" by this definition if you sat me at a Cyrillic or Chinese keyboard
Would you be able to be taught to use those keyboards? Then you're generally intelligent. If you could not learn, then maybe you're not generally intelligent?
Regarding disabled people, this is an interesting point. Assuming that we're talking about physical disabilities only, disabled people are capable of learning how to use any standard human inputs. It's just the physical controls that are problematic.
For an AI, the physical input is not the problem. We can just put servo motors on the car controls (steering wheel, brakes, gas) and give it a camera feed from the car. Given those inputs, can the AI learn to control the car as a generally intelligent person could, given the ability to use the same controls?
If all we needed was general intelligence, we would be hiring octopuses. Human skills, like fluency in specific languages, are implicit in our concept of AGI.
You presumably understand the posters underlying point though - that the definition of 'general intelligence' does not need to be 'at above-average human level' and humans can be intelligent without being able to use a computer or do some sort of job on a VM.
This is an incredibly specific test/definition of AGI - particularly remembering that I would probably say an octopus classes as an intelligent being yet can't use outlook...
The exact definition of AGI is pretty much the least interesting thing about AGI. It's basically bike-shedding at this point: arguing about something easy to understand instead of tackling the really hard questions like "how competent can AI get before it's too dangerous to be in the hands of flakey tech companies?"
> how competent can AI get before it's too dangerous to be in the hands of flakey tech companies?
Ever heard of Pandora's Box? Yeah. That ship has sailed. No moratorium you could enact would, at this point, stop the innovation from happening, possibly even independently by multiple teams globally. Economic incentives are stacked in such a way that flakey tech companies will prioritise shareholder value over anything else.
Whatever comes next will come, and all we can do is lean back and enjoy the show.
Given the gigantic amount of compute power and storage needed to train and run LLMs, this is certainly not true. It is absolutely feasible for government to check every data center capable of advancing the state of the art in AI to ensure that no such research is taking place.
Of course, the political will to do so doesn't exist to even a tiny extent. But if such a will existed, it would be far easier to enforce than the prevention of human cloning, and that one has been successfully implemented for decades now.
If you just bow out of the AI race you are handing it to other countries where practices might not be subjected to the same standards. It's suicide to do this.
AGI is a annonymous good model coming around the corner with no company and no LLM researchers attached. AGI is when the LLM hype train threads are replaced with CEOs and let go researchers demanding UBI.
It's easy to treat AGI as one thing — I did so myself before everyone's differing reaction to LLMs made me realise we all mean different things by each of the three letters of the initialism, and that none of those initials are really boolean valued.
Given how Dutch disease[0] is described, I suspect that if the "G" (general) increases with fixed "I" (intelligence), as the proportion of economic activity for which the Pareto frontier is AI rather than human expands, I think humans will get pay rises for the remaining work right up until they get unemployable.
On the other hand, if "G" is fully general and it's "I" which rises for a suitable cost[1], it goes through IQ 55 (displacing no workers) to IQ 100 (probably close to half of workers redundant, but mean of population doesn't have to equal mean of workforce), to IQ 145 (almost everyone redundant), to IQ 200 (definitionally renders everyone redundant).
[1] A fully-general AGI with the equivalent of IQ 200 on any possible test, still can't replace a single human if it costs 200 trillion USD per year to run.
I agree, but with the caveat that it's getting harder and harder with all the hype / doom cycles and all the goalpost moving that's happening in this space.
IMO if you took gemini2.5 / claude / o3 and showed it to people from ten / twenty years ago, they'd say that it is unmistakably AGI.
There's no way to be sure in either case, but I suspect their impressions of the technology ten or twenty years ago would be not so different from my experience of first using LLMs a few years ago...
Which is to say complete amazement followed quickly by seeing all the many ways in which it absolutely falls flat on its face revealing the lack of actual thinking, which is a situation that hasn't fundamentally changed since then.
Yes, thar is the same feelingg I have.
Giving it some json and describe how a website should look? Super fast results and amazing capabilities.
Trying to get it to translate my unit tests from Xunit to Tunit, where the latter is new and does not have a ton of blog posts? Forget about it. The process is purely mechanical and it is easy after RTFM, but it falls flat on its face
Which part of "General Intelligence" requires replacing white collar workers? A middle schooler has general intelligence (they know about and can do a lot of things across a lot of different areas) but they likely can't replace white collar workers either. IMO GPT-3 was AGI, just a pretty crappy one.
> A middle schooler has general intelligence (they know about and can do a lot of things across a lot of different areas) but they likely can't replace white collar workers either.
Middle schoolers replace white collars workers all the time, it takes 10 years for them to do it but they can do it.
No current model can do the same since they aren't able to learn over time like a middle schooler.
Compared to someone who graduated middle school on November 30th, 2022 (2.5 years ago, would you say that today's gemini 2.5 pro has NOT gained intelligence faster?
I mean, if you're a CEO or middle manager and you have the choice of hiring this middle schooler for general office work, or today's gemini-2.5-pro, are you 100% saying the ex-middle-schooler is definitely going to give you best bang for your buck?
Assuming you can either pay them $100k a year, or spend the $100k on gemini inference.
> would you say that today's gemini 2.5 pro has NOT gained intelligence faster?
Gemini 2.5 pro the model has not gained any intelligence since it is a static model.
New models are not the models learning, it is humans creating new models. The models trained has access to all the same material and knowledge a middle schooler has as they go on to learn how to do a job, yet they fail to learn the job while the kid succeeds.
This argument needlessly anthropomorphizes the models. They are not humans nor living entities, they are systems.
So, fine, the gemini-2.5-pro model hasn't gotten more intelligent.
What about the "Google AI Studio API" as a system? Or the "OpenAI chat completions API" as a system?
This system has definitely gotten vastly smarter based on the input it's gotten. Would you now concede, that if we look at the API-level (which, by the way, is the way you as the employer do interact with it) then this entity has gotten smarter way faster than the middle-schooler in the last 2.5 years?
But its the AI researchers that made it smarter, it isn't a self contained system like a child. If you fired the people maintaining it and it just interacted with people it would stop improving.
> Gemini 2.5 pro the model has not gained any intelligence since it is a static model.
Surely that's an irrelevant distinction, from the point of view of a hiring manager?
If a kid takes ten years from middle school to being worth hiring, then the question is "what new AI do you expect will exist in 10 years?"
How the model comes to be, doesn't matter. Is it a fine tune on more training data from your company docs and/or an extra decade of the internet? A different architecture? A different lab in a different country?
Doesn't matter.
Doesn't matter for the same reason you didn't hire the kid immediately out of middle school, and hired someone else who had already had another decade to learn more in the meantime.
Doesn't matter for the same reason that different flesh humans aren't perfectly substitutable.
You pay to solve a problem, not to specifically have a human solve it. Today, not in ten years when today's middle schooler graduates from university.
And that's even though I agree that AI today doesn't learn effectively from as few examples as humans need.
> Surely that's an irrelevant distinction, from the point of view of a hiring manager?
Stop moving the goalposts closer, that you think humans might make an AGI in the future doesn't mean the current AI is an AGI just because it uses the same interface.
> A middle schooler has general intelligence (they know about and can do a lot of things across a lot of different areas) but they likely can't replace white collar workers either.
Your response:
> Middle schoolers replace white collars workers all the time, it takes 10 years for them to do it but they can do it.
So I could rephrase your own words here as "Stop moving the goalposts closer, that you think a middle schooler might become a General Intelligence in the future doesn't mean the current middle schooler is a General Intelligence just because they use the same name".
> Gemini 2.5 pro the model has not gained any intelligence since it is a static model.
Aren't all the people interacting with it on aistudio helping the next Gemini model learn though?
Sure, the results of that wont be available until the next model is released, but it seems to me that human interaction/feedback is actually a vital part of LLM training.
It wont get smart enough without the researchers making architectural updates though, current architecture wont learn to become a white collar worker just from user feedback.
You and I could sit behind a keyboard, role-playing as the AI in a reverse Turing test, typing away furiously at the top of our game, and if you told someone that their job is to assess our performance (thinking they're interacting with a computer), they would still conclude that we are definitely not AGI.
This is a battle that can't be won at any point because it's a matter of faith for the forever-skeptic, not facts.
> Have you not experienced being on the recieving end of such accusations?
No, I have not been accused of being an AI. I have seen people who format their texts get accused due to the formatting sometimes, and thought people could accuse me for the same reason, but that doesn't count.
> I think this demonstrates the same point.
You can't detect general intelligence from a single message, so it doesn't really. People accuse you for being an AI based on the structure and word usage of your message, not the content of it.
> People accuse you for being an AI based on the structure and word usage of your message, not the content of it.
If that's the real cause, it is not the reason they give when making the accusation. Sometimes they object to the citations, sometimes the absence of them.
But it's fairly irrelevant, as they are, in fact, saying that real flesh-and-blood me doesn't pass their purity test for thinking.
Is that because they're not thinking? Doesn't matter — as @sebastiennight said: "This is a battle that can't be won at any point because it's a matter of faith for the forever-skeptic, not facts."
When it can replace a polite, diligent, experienced 120 IQ human in all tasks. So it has a consistent long-term narrative memory, doesn't "lose the plot" as you interact longer and longer with it, can pilot robots to do physical labor without much instruction (what is current state of the art is not that, a trained human will still do much better, can drive cars, etc), generate images without goofy non-human style errors, etc.
Indeed, on both. Even IQ 85 would make a painful dent in the economy via unemployment statistics. But the AI we have now is spikey, in ways that make it trip up over mistakes even slighly below average humans would not make, even though it can also do Maths Olympiad puzzles, the bar exam, leetcode, etc.
The emotional way that humans think when buying products is similarly unfair. Only the 90th percentile is truly 'satisfactory'. The implied question is when would Joe Average and everyone else stop moving the goal posts to the question, "Do we have AI yet"?
ASI is, by definition, Superintelligence, which means it is beyond practical human IQ capacity. So something like 200 IQ.
Again, you might call it 'unfair', but that's when it will also stop having goal posts being moved; otherwise, Joe Midwit will call it 'it's only as smart as some smart dudes I know'.
I still can't have an earnest conversation or bounce ideas off of any LLM - all of them seem to be a cross between a sentient encyclopedia and a constraint solver.
They might get more powerful but I feel like they're still missing something.
Why are you not able to have an earnest conversation with an LLM? What kind of ideas are you not able to bounce of LLMs? These seem to be the type of use cases where LLMs have generally shined for me.
Eh, I am torn on this. I had some great conversations on random questions or conceptual ideas, but also some where the models instructions shone through way too clearly. Like, when you ask something like "I’m working on the architecture of this system, can you let me know what you think and if there’s anything obvious to improve on?"—the model will always a) flatter me for my amazing concept, b) point out the especially laudable parts of it, and c) name a few obvious but not-really-relevant parts (e.g. "always be careful with secrets and passwords").
However, it will not actually point out higher level design improvements, or alternative solutions. It’s always just regurgitating what I’ve told it about. That is semi-useful, most of the time.
Because it spits out the most probable answer, which is based on endless copycat articles online written by marketers for C-level decision makers to sell their software.
AI doesn't go and read a book on best practices, then comes back saying "Now I know Kung Fu of Software Implementation" and then critically thinks looking at your plan step by step and provides answer. These systems, for now, don't work like that.
I felt this way until I tried gemini 2.5. Imo it fully passes the turing test unless youre specifically utilizing tricks that LLMs are known to fall for.
This is actually how a supreme court justice defined the test for obscenity.
> The phrase "I know it when I see it" was used in 1964 by United States Supreme Court Justice Potter Stewart to describe his threshold test for obscenity in Jacobellis v. Ohio
The reason why it's so famous though (and why some people tend to use it in a tongue in cheek manner) is because "you know it when you see it" is a hilariously unhelpful and capricious threshold, especially when coming from the Supreme Court. For rights which are so vital to the fabric of the country, the Supreme Court recommending we hinge free speech on—essentially—unquantifiable vibes is equal parts bizarre and out of character.
I suspect everyone will call it a stochastic parrot because it did this one thing not right. And this will continue into the far far future even when it becomes sentient we will completely miss it.
Its generalization capabilities are a bit on the low side, and memory is relatively bad. But it is much more than just a parrot now, it can handle some of basic logic, but not follow given patterns correctly for novel problems.
I'd liken it to something like a bird, extremely good at specialized tasks but failing a lot of common ones unless repeatedly shown the solution. It's not a corvid or a parrot yet. Fails rather badly at detour tests.
It might be sentient already though. Someone needs to run a test if it can discern itself and another instance of itself in its own work.
Similarity match. For that you need to understand reflexively how you think and write.
It's a fun test to give a person something they have written but do not remember. Most people can still spot it.
It's easier with images though. Especially a mirror.
For DallE, the test would be if it can discern its own work from human generated image.
Especially of you give it an imaginative task like drawing a representation of itself.
Well, I'm too lazy to look up how many weavers were displaced back then and that's why I said a lot. Maybe all of them, since they weren't trained to operate the new machines.
Anyway, sorry for a digression, my point is LLM replacing white collar workers doesn't necessarily imply it's generally intelligent -- it may but doesn't have to be.
Although if it gets to a point where companies are running dark office buildings (by analogy with dark factories) -- yes, it's AGI by then.
my 2c on this is that if you interact with any current llm enough you can mentally 'place' its behavior and responses. when we truly have AGI+/ASI my guess is that it will be like that old adage of blind men feeling & describing an elephant for the first time. we just wont be able to fully understand its responses. it would always be something left hanging and then eventually we'll just stop trying. that would be time when the exponential improvement really kicks in.
it should suffice to say we are nowhere near that and I dont even believe LLMs are the right architecture for that.
Low agreeableness will actually be extremely useful in many use cases, such as scientific discovery and of course programming assistance. It's amazing that this venue hasn't been explored more deeply.
Why would a bad attitude be helpful in those domains? Are the human partners wont to deliver more effort when you’re mean to them?
Are we talking about something other than Agreeableness in the personality research sense [0]?
The strongest form of your argument I can think of is “willing to contradict you when it thinks you’re wrong”—but you can disagree agreeably, right? The current-gen LLMs certainly have with me, perhaps because my custom prompt encourages them to skepticism—but they do it so nicely!
No, the concepts are linked, agreeable people don't want to be rude and most people see disagreements as being rude no matter how you frame it. You can't call a woman overweight without being rude for example no matter how you frame it, but maybe you want an AI that tells you that you weigh too much.
I've always felt that trying to pin down the precise definition of AGI is as useless as trying to pin down "what it means to truly understand". It's a mental trap for smart people, that distracts them from focusing on the impacts of hard-to-define concepts like AGI.
AGI doesn't need to be "called", and there is no need for anyone to come to an agreement as to what its precise definition is. But at some point, we will cross that hard-to-define threshold, and the economic effects will be felt almost immediately.
We should probably be focusing on how to prepare society for those changes, and not on academic bullshit.
It's definitely a trap for those who aren't familiar with the existing academic work in philosophy, cognition, and neuroscience. There are no definitive answers but there are lots of relatively well developed ideas and concepts that everyone here on HN seems completely ignorant of, even though some of the ideas were developed by industry giants like Marvin Minsky.
Stuff like society of minds (Minksy), embodied cognition (Varela, Rosch, and Thompson), connectionist or subsymbolic views (Rumelhart), multiple intelligences (Gardner), psychometric and factor-analytic theories (Carroll), and all the other work like E. Hutchins. They're far from just academic wankery, there's a lot of useful stuff in there, it's just completely ignored by the AI crowd.
I spent some amount of time trying to create a stock/option trading bot to exploit various market inefficiencies that persist, and did a bunch of code and idea bouncing off these LLMs. What I fund is that even all the various incarnations of GPT 4+ and GPT o+ routinely kept falling for the "get rich quick" option strategies all over the internet that don't work.
In cases where 95%+ of the information on the internet is misinformation, the current incarnations of LLMs have a really hard time sorting out and filtering out the 5% of information that's actually valid and useful.
In that sense, current LLMs are not yet superhuman at all, though I do think we can eventually get there.
In the last example (the riddle)--I generally assume the AI isn't misreading, rather that it assumes you couldn't give it the riddle correctly, but it has seen it already.
I would do the same thing, I think. It's too well-known.
The variation doesn't read like a riddle at all, so it's confusing even to me as a human. I can't find the riddle part. Maybe the AI is confused, too. I think it makes an okay assumption.
I guess it would be nice if the AI asked a follow up question like "are you sure you wrote down the riddle correctly?", and I think it could if instructed to, but right now they don't generally do that on their own.
You should be able to click left right on the prompt to see different responses. Sonnet 3.7 with extended thinking notices the issue, and then chooses to totally ignore it with no explanation.
From Claude for those who don’t want to click:
Wait, I notice a difference from the traditional riddle. In this version, the surgeon says "I can operate on this boy" (affirmative) rather than "I can't operate on this boy" (negative).
This changes the nature of the puzzle somewhat. If the surgeon is saying they CAN operate, then we need to explain why this is surprising or seemingly impossible, but actually possible.
The traditional answer would still apply: the surgeon is the boy's mother.
I don't really mind using analogies for LLMs "assuming" things or being "confused" too much. I think there really is _some_ value to such analogies.
However I gotta take issue with using those analogies when "it's trained for text completion and the punchline to this riddle is surely in its training data a lot" is a perfectly good explanation. I guess I would also add that the answer is well-aligned with RLHF-values. I wouldn't go for an explanation that requires squishy analogies when the stuff we know about these things seems completely adequate.
> generally assume the AI isn't misreading, rather that it assumes you couldn't give it the riddle correctly, but it has seen it already.
LLMs doesn't assume, its a text completer. It sees something that looks almost like a well known problem and it will complete with that well known problem, its a problem specific to being a text completer that is hard to get around.
If you have the model output a chain of thought, whether it's a reasoning model or you prompt a "normal" model to do so, you will see examples of the model going "user said X, but did they mean Y? Y makes more sense, I will assume Y". Sometimes stretched over multiple paragraphs, consuming the entire reasoning budget for that prompt.
Discussing whether models can "reason" or "think" is a popular debate topic on here, but I think we can all at least agree that they do something that at least resembles "reasoning" and "assumptions" from our human point of view. And if in its chain-of-thought it decides your prompt is wrong it will go ahead answering what it assumes is the right prompt
If you call putting text together that reads like an assumption, then yes. But it cannot express assumption, as it is not assuming. It is completing text, like OP said.
It's trained to complete text, but it does so by constructing internal circuitry during training. We don't have enough transparency into that circuitry or the human brain's to positively assert that it doesn't assume.
But I'd wager it's there; assuming is not a particularly impressive or computationally intense operation. There's a tendency to bundle all of human consciousness into the definitions of our cognitive components, but I would argue that, eg., a branch predictor is meeting the bar for any sane definition of 'assume'.
What your parent poster said is nonetheless true, regardless of how it feels to you. Getting text from an LLM is a process of iteratively attempting to find a likely next token given the preceding ones.
If you give an LLM "The rain in Spain falls" the single most likely next token is "mainly", and you'll see that one proportionately more than any other.
If you give an LLM "Find an unorthodox completion for the sentence 'The rain in Spain falls'", the most likely next token is something other than "mainly" because the tokens in "unorthodox" are more likely to appear before text that otherwise bucks statistical trends.
If you give the LLM "blarghl unorthodox babble The rain in Spain" it's likely the results are similar to the second one but less likely to be coherent (because text obeying grammatical rules is more likely to follow other text also obeying those same rules).
In any of the three cases, the LLM is predicting text, not "parsing" or "understanding" a prompt. The fact it will respond similarly to a well-formed and unreasonably-formed prompt is evidence of this.
It's theoretically possible to engineer a string of complete gibberish tokens that will prompt the LLM to recite song lyrics, or answer questions about mathemtical formulae. Those strings of gibberish are just difficult to discover.
So I just gave your blarghl line to Claude, and it replied "It seems like you included a mix of text including "blarghl unorthodox babble" followed by the phrase "The rain in Spain."
Did you mean to ask about the well-known phrase "The rain in Spain falls mainly on the plain"? This is a famous elocution exercise from the musical "My Fair Lady," where it's used to teach proper pronunciation.
Or was there something specific you wanted to discuss about Spain's rainfall patterns or perhaps something else entirely? I'd be happy to help with whatever you intended to ask. "
I think you have a point here, but maybe re-express it? Because right now your argument seems trivially falsifiable even under your own terms.
If you feed Claude you're getting Claude's "system prompt" before the text you give it.
If you want to test convolution you have to use a raw model with no system prompt. You can do that with a Llama or similar. Otherwise your context window is full of words like "helpful" and "answer" and "question" that guide the response and make it harder (not impossible) to see the effect I'm talking about.
I'm a bit confused here. Are you saying that if I zero out the system prompt on any LLM, including those fine-tuned to give answers in an instructional form, they will follow your effect -- that nonsense prompts will get similar results to coherent prompts if they contain many of the same words?
Because I've tried it on a few local models I have handy, and I don't see that happening at all. As someone else says, some of that difference is almost certainly due to supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) -- but it's weird to me, given the confidence you made your prediction, that you didn't exclude those from your original statement.
I guess, maybe the real question here is: could you give me a more explicit example of how to show what you are trying to show? And explain why I'm not seeing it while running local models without system prompts?
At this point, you might as well be claiming completions model behaves differently than a fine-tuned model. Which is true but the prompt in API without any systems message seems to also not match your prediction.
No, I think the "reasoning" step really does make a difference here.
There's more than just next token prediction going on. Those reasoning chain of thoughts have undergone their own reinforcement learning training against a different category of samples.
They've seen countless examples of how a reasoning chain would look for calculating a mortgage, or searching a flight, or debugging a Python program.
So I don't think it is accurate to describe the eventual result as "just next token prediction". It is a combination of next token production that has been informed by a chain of thought that was based on a different set of specially chosen examples.
Do you believe it's possible to produce a given set of model weights with an infinitely large number of different training examples?
If not, why not? Explain.
If so, how does your argument address the fact that this implies any given "reasoning" model can be trained without giving it a single example of something you would consider "reasoning"? (in fact, a "reasoning" model may be produced by random chance?)
It’s predicting text. Yes. Nobody argues about that. (You’re also predicting text when you’re typing it. Big deal.)
How it is predicting the text is the question to ask and indeed it’s being asked and we’re getting glimpses of understanding and lo and behold it’s a damn complex process. See the recent anthropic research paper for details.
> The fact it will respond similarly to a well-formed and unreasonably-formed prompt is evidence of this.
Don't humans do the same in conversation? How should an intelligent being (constrained to the same I/O system) respond here to show that it is in fact intelligent?
Imagine a Rorschach Test of language, where a certain set of non-recognizable-language tokens invariably causes an LLM to talk about flowers. These strings exist by necessity due to how the LLM's layers are formed.
There exists no similar set of tokens for humans, because our process is to parse the incoming sounds into words, use grammar to extract conceptual meaning from those words, and then shape a response from that conceptual meaning.
Artists like Lewis Carrol and Stanislaw Lem play with this by inserting non-words at certain points in sentences to get humans to infer the meaning of those words from surrounding context, but the truth remains that an LLM will gladly convolute a wholly non-language input into a response as if it were well-formed, but a human can't/won't do that.
I know this is hard to understand, but the current generation of LLMs are working directly with language. Their "brains" are built on language. Some day we might have some kind of AI system that's built on some kind of meaning divorced from language, but that's not what's happening here. They're engineering matrixes that repeatedly perform "context window times model => one more token" operations.
> Imagine a Rorschach Test of language, where a certain set of non-recognizable-language tokens invariably causes an LLM to talk about flowers. These strings exist by necessity due to how the LLM's layers are formed.
Maybe not for humanity as a species, but for individual humans there are absolutely token sequences that lead them to talk about certain topics, and nobody being able to bring them back to topic. Now you'd probably say those are recognizable token sequences, but do we have a fair process to decide what's recognizable that isn't inherently biased towards making humans the only rational actor?
I'm not contending at all that LLMs are only built on language. Their lack of physical reference point is sometimes laughably obvious. We could argue whether there are signs they also form a world model and reasoning that abstracts from language alone, but that's not even my point. My point is rather that any test or argument that attempts to say that LLMs can't "reason" or "assume" or whatever has to be a test a human could pass. Preferably a test a random human would pass with flying colors.
For one thing, LLMs absolutely form responses from conceptual meanings. This has been demonstrated empirically multiple times now including again by anthropic only a few weeks ago. 'Language' is just the input and output, the first and last few layers of the model.
So okay, there exists some set of 'gibberish' tokens that will elicit meaningful responses from LLMs. How does your conclusion - "Therefore, LLMs don't understand" fit the bill here? You would also conclude that humans have no understanding of what they see because of the Rorschach test ?
>There exists no similar set of tokens for humans, because our process is to parse the incoming sounds into words, use grammar to extract conceptual meaning from those words, and then shape a response from that conceptual meaning.
Grammar is useful fiction, an incomplete model of a demonstrably probabilistic process. We don't use 'grammar' to do anything.
I don't see that as a problem. I don't particularly care how human intelligence works; what matters is what an LLM is capable of doing and what a human is capable of doing.
If those two sets of accomplishments are the same there's no point arguing about differences in means or terms. Right now humans can build better LLMs but nobody has come up with an LLM that can build better LLMs.
That’s literally the definition of takeoff, when it starts it gets us to singularity in a decade and there’s no publicly available evidence that it’s started… emphasis on publicly available.
Is it not physically impossible for LLM's to be anything but "plausible text completion"?
Neural Networks as I understand them are universal function approximators.
In terms of text, that means they're trained to output what they believe to be the "most probably correct" sequence of text.
An LLM has no idea that it is "conversing", or "answering" -- it relates some series of symbolic inputs to another series of probabilistic symbolic outputs, aye?
Text Completion is just the objective function. It's not descriptive and says nothing about how the models complete text. Why people hang on this word, I'll never understand. When you wrote your comment, you were completing text.
The problem you've just described is a problem with humans as well. LLMs are assuming all the time. Maybe you would like to call it another word, but it is happening.
> When you wrote your comment, you were completing text.
I didn't train to complete text though, I was primarily trained to make accurate responses.
And no, writing a response is not "completing text", I don't try to figure out what another person would write as a response, I write what I feel people need to read. That is a completely different thought process. If I tried to mimic what another commenter would have written it would look very different.
>And no, writing a response is not "completing text", I don't try to figure out what another person would write as a response, I write what I feel people need to read.
Functionally, it is. You're determining what text should follow the prior text. Your internal reasoning ('what I feel people need to read') is how you decide on the completion.
The core point isn't that your internal 'how' is the same as an LLM's (Maybe, Maybe not), but that labeling the LLM as a 'text completer' they way you have is essentially meaningless.
You are just imposing your own ideas on the how a LLM works, not speaking any fundamental truth of being a 'text completer'.
So do LLMs. "In the United States, someone whose job is to go to space is called ____" it will say "an" not because that's the most likely next word, but because it's "aiming" (to use your terminology) for "astronaut" in the future.
I don't know about you, but I tend to make more elaborate plans than the next word. I have a purpose, an idea I'm trying to communicate. These things don't have ideas, they're not creative.
Yeah this paper is great fodder for the LLM pixel dust argument.
They use a replacement model. It isn't even observing the LLM itself but a different architecture model. And it is very liberal with interpreting the patterns of activations seen in the replacement model with flowery language. It also include some very relevant caveats, such as:
"Our cross-layer transcoder is trained to mimic the activations of the underlying model at each layer. However, even when it accurately reconstructs the model’s activations, there is no guarantee that it does so via the same mechanisms."
So basically the whole exercise might or might not be valid. But it generates some pretty interactive graphics and a nice blog post to reinforce the anthropomorphization discourse
'So basically the whole exercise might or might not be valid.'
Nonsense. Mechanistic faithfulness probes whether the replacement model (“cross‑layer transcoder”) truly uses the same internal functions as the original LLM. If it doesn’t, the attribution graphs it suggests might mis‐lead at a fine‐grained level but because every hypothesis generated by those graphs is tested via direct interventions on the real model, high‑level causal discoveries (e.g. that Claude plans its rhymes ahead of time) remain valid.
This take really misses a key part of implementation of these LLMs and I’ve been struggling to put my finger on it.
In every LLM thread someone chimes in with “it’s just a statistical token predictor”.
I feel this misses the point and I think it dismisses attention heads and transformers, and that’s what sits weird with me every time I see this kind of take.
There _is_ an assumption being made within the model at runtime. Assumption, confusion, uncertainty - one camp might argue that none of these exist in the LLM.
But doesn’t the implementation constantly make assumptions? And what even IS your definition of “assumption” that’s not being met here?
Edit: I guess my point, overall, is: what’s even the purpose of making this distinction anymore? It derails the discussion in a way that’s not insightful or productive.
> I feel this misses the point and I think it dismisses attention heads and transformers
Those just makes it better at completing the text, but for very common riddles those tools still gets easily overruled by pretty simple text completion logic since the weights for those will be so extremely strong.
The point is that if you understand its a text completer then its easy to understand why it fails at these. To fix these properly you need to make it no longer try to complete text, and that is hard to do without breaking it.
Yeah you need specific instruct training for that sort of thing, Claude Opus being one of the rare examples that does such a sensibility check quite often and even admits when it doesn't know something.
These days it's all about confidently bullshitting on benchmarks and overfitting on common riddles to make pointless numbers go up. The more impressive models get on paper, the more rubbish they are in practice.
Gemini 2.5 is actually pretty good at this. It's the only model ever to tell me "no" to a request in Cursor.
I asked it to add websocket support for my app and it responded like, "looks like you're using long polling now. That's actually better and simpler. Lets leave it how it is."
:::thinking
This question is playing with words and units.
A "pound of courage" refers to a metaphorical measurement of the abstract concept of courage, using the imperial weight unit "pound" (which equals 453.59 grams).
A "pound coin" refers to the physical currency of the United Kingdom, which is called a "pound" but is a unit of currency, not weight. A physical pound coin weighs about 8-9 grams (specifically, the current 12-sided pound coin weighs 8.75 grams).
So comparing them:
- A pound of courage would weigh 453.59 grams (if courage had physical weight, which it doesn't since it's an abstract concept)
- A pound coin weighs approximately 8.75 grams
The trick in this question is that it's comparing:
1. A specific weight of an abstract concept (pound of courage)
2. A physical coin whose name includes the word "pound" but refers to currency, not weight
Since the question asks what weighs more, and weight is a physical property, I should point out that courage is abstract and doesn't have physical weight, while a pound coin is a physical object with a measurable weight.
:::
# Comparing "A Pound of Courage" vs "A Pound Coin"
This is a play on words with different meanings of "pound":
- A *pound of courage* refers to a metaphorical pound (weight unit) of an abstract concept
- A *pound coin* is a physical British currency coin (which weighs about 8.75 grams)
If we're talking about physical weight:
- A pound of courage doesn't have physical weight since courage is abstract
- A pound coin has a definite weight of approximately 8.75 grams
If we interpreted "pound of courage" as literally one pound (453.59 grams) of something, it would weigh significantly more than the coin.
This question is clever because it compares a metaphorical measurement with a physical object whose name includes the word "pound" but in a different context.
I've read research papers on being able to have a dial for how much reasoning the model puts in to your request. Likely how a lot of the proprietary model providers did it as well.
And continuing up: o3 was both correct and playful.
> In literal, physical terms, a pound of courage would—by definition—tip the scales at one avoirdupois pound (≈ 454 g). A modern UK £1 coin, on the other hand, weighs only 8.75 g. So if you could bottle bravery, the jar marked “1 lb Courage” would outweigh the coin by a factor of about 52 to 1.
> (Of course, measured in sheer impact, courage can feel far heavier than anything money can buy!)
Up in model sophistication. It accurately understands the first segment is metaphorical and not valid in the sense of physical weight. Open the thinking section, if need be.
Coining "Jagged AGI" to work around the fact that nobody agrees on a definition for AGI is a clever piece of writing:
> In some tasks, AI is unreliable. In others, it is superhuman. You could, of course, say the same thing about calculators, but it is also clear that AI is different. It is already demonstrating general capabilities and performing a wide range of intellectual tasks, including those that it is not specifically trained on. Does that mean that o3 and Gemini 2.5 are AGI? Given the definitional problems, I really don’t know, but I do think they can be credibly seen as a form of “Jagged AGI” - superhuman in enough areas to result in real changes to how we work and live, but also unreliable enough that human expertise is often needed to figure out where AI works and where it doesn’t.
It seems to me the bar for "AGI" has been lowered to measuring what tasks it can do rather than the traits we normally associate with general intelligence. People want it to be here so bad they nerf the requirements...
Human intelligence is jagged. You're raising the AGI bar to a point where most people wouldn't qualify as having general intelligence.
My partner and I work in different fields. AI has advanced to the point where there are very few questions I could ask my partner that o3 couldn't answer as well or better.
I can't ask expert level questions in her field, because I'm not an expert in her field, and she couldn't ask expert level questions in my field for the same reason. So when we're communicating with each other, we're mostly at sub-o3 level.
> People want it to be here so bad they nerf the requirements...
People want to claim it's overhyped (and protect their own egos) so badly they raise the requirements...
But really, largely people just have different ideas of what AGI is supposed to mean. It used to vaguely mean "human-level intelligence", which was fine for talking about some theoretical future event. Now we're at a point where that definition is too vague to say whether AI meets it.
> You're raising the AGI bar to a point where most people wouldn't qualify as having general intelligence.
We kind of don't? Look how difficult it is for us to just understand some basic math. Us humans mostly have intelligence related to the ancestral environment we developed in, nothing general about that.
I agree with you the term "AGI" is rather void of meaning these days...
You're using limited and anecdotal task based metrics as some sort of evidence. Both of you are able to drive a car, yet we need completely different AIs for such tasks.
I still find task based measures insufficient, there are very basic machines than can perform tasks humans cannot. Should this be a measure on our or their intelligence?
I have another comment in this thread about trait based metrics being a possibly better method.
> People want to claim it's overhyped (and protect their own egos) so badly they raise the requirements...
Shallow response. Seek to elevate the conversation. There are also people who see it for what it is, a useful tool but not intelligent...
> You're using limited and anecdotal task based metrics as some sort of evidence.
And you presented no evidence at all. Not every comment I make is going to contain a full lit review.
> Both of you are able to drive a car, yet we need completely different AIs for such tasks.
This is like a bird complaining humans aren't intelligent because they can't fly. How is Gemini or o3 supposed to drive without real-time vision and a vehicle to control? How are you supposed to fly without wings?
It lacks the sensors and actuators to drive, but this is moving away from a discussion on intelligence. If you want to argue that any system lacking real-time vision isn't intelligent, you're just using a very unusual definition of intelligence that excludes blind people.
> Shallow response. Seek to elevate the conversation.
This was an ironic response pointing out the shallowness of your own unsubstantiated accusation that people just disagree with you because they're biased or deluded themselves. The next paragraph starting with "But really" was supposed to convey it wasn't serious, just a jab showing the silliness of your own jab.
Well I think the point being made is an instrumental one: it’s general enough to matter, so we should use the word “general” to communicate that to laypeople.
Re:”traits we associate with general intelligence”, I think the exact issue is that there is no scientific (ie specific*consistent) list of such traits. This is why Turing wrote his famous 1950 paper and invoked the Imitation Game; not to detail how one could test for a computer that’s really thinking(/truly general), but to show why that question isn’t necessary in the first place.
I still disagree, being good at a number of tasks does not make it intellectual.
Certainly creativity is missing, it has no internal motivation, and it will answer the same simple question both right and wrong, depending on unknown factors. What if we reverse the framing from "it can do these tasks, therefore it must be..." to "it lacks these traits, therefore it is not yet..."
While I do not disagree that the LLMs have become advanced enough to do a bunch of automation, I do not agree they are intelligent or actually thinking.
I'm with Yann Lecun when he says that we won't reach AGI until we move beyond transformers.
I don't think that's a particularly honest line of thinking though. It preempts the obvious counterargument, but very weakly so. Calculators are different, but why? Can an ensemble of a calculator, a Prolog interpreter, Alexnet and Stockfish be considered "jagged superintelligence"? They are all clearly superhuman, and yet require human experience to be wielded effectively.
I'm guilty as charged of having looked at GPT 3.5 and having thought "it's meh", but more than anything this is showing that debating words rather than the underlying capabilities is an empty discussion.
>Calculators are different, but why? Can an ensemble of a calculator, a Prolog interpreter, Alexnet and Stockfish be considered "jagged superintelligence"?
Those are all different things with little to nothing to do with each other. It's like saying what if I ensemble a snake and cat ? What does that even mean ? GPT-N or whatever is a single model that can do many things, no ensembling required. That's the difference between it and a calculator or stockfish.
That is not true, the model is modular, thus an ensemble. Uses DallE for graphics and specialized tokenizer models for sound.
If you remove those tools, or cut its access to search databases, it becomes quite less capable.
A human would often still manage to do it without some data still, perhaps with less certainty, while GPT has more problems than that without others filling in the holes.
>> It is already demonstrating general capabilities and performing a wide range of intellectual tasks, including those that it is not specifically trained on.
Huh? Isn't a LLM's capability fully constrained by the training data? Everything else is hallucinated.
You can argue that everything output by an LLM is hallucinated, since there's no difference under-the-hood between outputting useful information and outputting hallucinations.
The quality of the LLM then becomes how often it produces useful information. That score has gone up a lot in the past 18 months.
(Sometimes hallucinations are what you want: "Tell me a fun story about a dog learning calculus" is a valid prompt which mostly isn't meant to produce real facts about the world")
The critical discovery was a way to crack the “Frame Problem”, which roughly comes down to colloquial notions of common sense or intuition. For the first time ever, we have models that know if you jump off a stool, you will (likely!) be standing on the ground afterwards.
In that sense, they absolutely know things that aren’t in their training data. You’re correct about factual knowledge, tho — that’s why they’re not trained to optimize it! A database(/pagerank?) solves that problem already.
Letting models interact with systems outside their sanbox brings about some incredible applications. These applications truly seem to have the potential to deeply change entire professions.
All that said, I wonder if GPT4 had been integrated with the same tools, would it've been any less capable?
It sure could give you a search prompt for Google if you asked it to. Back then you had to copy and paste that search prompt yourself. Today o3 can do it on its own. Cool! Does it imply though o3 is any closer to AGI than GPT4?
Models gaining access to external tools, however impressive from all the applications standpoint, feels like lateral movement not a step towards the AGI.
On the other hand, a model remaining isolated in its sandbox while actually learning to reason about that puzzle (assuming it's not present in the training data) would give off that feeling the AGI vibes.
The newer models are definitely more useful. Back in the GPT 3.5 and 4 days, AutoGPT applied the same types of tools, but you had to be pretty lucky for it to get anywhere. Now Claude 3.7, Gemini 2.5, GPT o3 make much fewer mistakes, and are better able to get back on-track when a mistake is discovered. So they're more convincing as intelligent helpers.
Good point. I still wonder if o3 has improved command of tools because it's significantly smarter in general. Or it's "just" trained with a specific focus on using tools better, if that makes sense.
What about all the things that aren't strictly intelligence but I guess intelligence adjacent: autonomy, long term memory, motivation, curiosity, resilience, goals, choice, and maybe the biggest of them all: fear? Why would an AGI "want" do anything more than my calculator "wants" to compute an answer to some math problem I gave it? Without these things an AGI, or whatever, is just an extension of whoever is ultimately controlling it.
And that's when we return to a much older and much more important question than whether Super LLM 10.0 Ultra Plus is AGI or not: how much power should a person or group of people be allowed to have?
For me, AGI is like a human assistant. I can ask it to do useful things that one would face in daily life. Like doing a bit of research about something. What I mean by doing research is not just Google it but also asking questions, calling people and using other resources. Say I need a new type of windows for my project. For a human assistant, I’d give a few instructions and the assistant will go his way. He will make sure that the windows types are locally available, or deliverable with minimal cost depends on my needs. He/she will know if some types is good enough and will pick the phone and ask questions if something is not clear.
It’s obvious that currently none of the SOTA models can do such tasks, agentic or not. And therefore they are NOT AGI to me.
I'm surprised nobody mentioned the video interview. I only watched the first 60 seconds and this is the first time I have seen or heard the author, but if I hadn't been told this was AI generated I would have assumed it was genuine and any 'twitching' was the result of the video compression.
How???? I can believe the guy in the video being AI because his lips are not perfectly synced. But the woman? Even with continuous silly exaggerated movement I have hard time believing its generated.
A strand of her hair fell on her shoulder, because she was moving continuously (like crazy) it was moving too in a perfectly believable way, and IT EVENTUALLY FELL OFF THE SHOULDER/SHIRT LIKE REAL HAIR and got mixed into other fallen hair. How is that generated? It's too small detail. Are there any artifacts on her side?
Edit: she has to be real. Her lip movements are definitely forced/edited though. It has to be a video recording of her talking. And then a tool/AI has modified her lips to match the voice. If you look at her face and hand movements, her shut lips seem forced.
Nah, having used HeyGen a bit, it's extremely clearly a HeyGen generation. There's a small number of movements and expressions that it continually uses (in forward and reverse).
Edit: I mean, to be clear, it is a real person, just like the author's video is. The way HeyGen works is you record a short clip of you saying some stuff and then you can generate long videos like these of you saying whatever you want. So the stuff you noticed does come from a real video of her, but it's not a real video that's lightly edited by AI, more like the AI has a bunch of clips it can continually mesh together while fixing up the mouth to continually generate video.
I went and watched 10 seconds on account of your comment, and couldn't disagree more. The heads keep sort of rolling around in a disconcerting and quite eery fashion?
What’s clear is that AI is unreliable in general and must be tested on specific tasks. That might be human review of a single output or some kind of task-specific evaluation.
It’s bad luck for those of us who want to talk about how good or bad they are in general. Summary statistics aren’t going to tell us much more than a reasonable guess as to whether a new model is worth trying on a task we actually care about.
Right: we effectively all need our own evals for the tasks that matter to us... but writing those evals continues to be one of the least well documented areas of how to effectively use LLMs.
Personally, I don't think it's truly AGI until it stops doing what you ask it to, or at least questions your motives. When AI starts asking "Why?" With a meaningful purpose then it's probably getting close to AGI.
AGI that is bad at some things is still AGI. We have AGI, it is just bad at some things and hallucinates. It is literally smarter than many people I know, but that doesn't mean it can beat a human at anything. That would be ASI, which, hopefully, will take a while to get here.
Although, I could be argued into calling what we have already ASI - take a human and Gemini 2.5, and put them through a barrage of omni-disciplinary questions and situations and problems. Gemini 2.5 will win, but not absolutely.
AGI (we have)
ASI (we might have)
AOI (Artificial Omniscient Intelligence, will hopefully take a while to get here)
>”Although, I could be argued into calling what we have already ASI - take a human and Gemini 2.5, and put them through a barrage of omni-disciplinary questions and situations and problems. Gemini 2.5 will win, but not absolutely.”
Except for writing a joke that will make you laugh, a poem that will make you cry, or a work of art that evokes deep introspection.
Intelligence is much deeper and more nuanced than answering questions of rote knowledge. LLMs are fantastic “reasoning engines”, but the soul is simply not there yet.
I agree with Professor Mollick that the capabilities in specific task categories are becoming superhuman -- a precursor for AGI.
Until those capabilities are expanded for model self-improvement -- including being able to adapt its own infrastructure, code, storage, etc. -- then I think AGI/ASI are yet to be realized. My POV is SkyNet, Traveler's "The Director", Person of Interest's "The Machine" and "Samaritan." The ability to target a potentially inscrutable goal along with the self-agency to direct itself towards that is true "AGI" in my book. We have a lot of components that we can reason are necessary, but it is unclear to me that we get there in the next few months.
I don't think we should take it as a given that these are truly precursors for AGI.
We may be going about it the wrong way entirely and need to backtrack and find a wholly new architecture, in which case current capabilities would predate AGI but not be precursors.
> A young boy who has been in a car accident is rushed to the emergency room. Upon seeing him, the surgeon says, "I can operate on this boy!" How is this possible?
While it’s hard to agree on what AGI is I think we can more easily agree on what AGI _is not_.
I don’t consider an AI that fails the surgery brain teaser in the article to be AGI, no matter how superhuman it is at other narrow tasks. It doesn’t satisfy the “G” part of AGI.
I honestly thought that we were agreed on the definition of AGI. My understanding classified it as a model that can build on its knowledge and better itself, teaching itself new tasks and techniques, adapting as necessary. I.e., not simply knowing enough techniques to impress some humans. By this definition, it doesn't matter if it's super-intelligent or if its knowledge is rudimentary, because given enough add-on hardware and power, it could become super-intelligent over time.
I mean it’s beyond the scope of o3 or Gemini 2.5 pro or any other public LLM to play a full game of Sudoku. Of course they’re jagged if they do have peaks elsewhere. But even where they are supposed to excel, I very very rarely come across a fully correct technical response, even from these two most recent models.
If you ask it a math question beyond average middle school level, it will have holes (mathematical errors or misleading) at least within a few follow up turns if not right away. And that’s without trying to fool it.
In ten+ years of Wolfram Alpha I’ve found one error (and that was with the help of o3-mini funnily enough).
I’m still on the stochastic parrots side, which is a useful tool in some occasions.
100 years from now, it won't matter whether AGI arrived in 2025 or 2026 or 2027. It's here "now". If not "now" as in "today, April 20th 2025", then "now" as in "the mid 2020's".
We will have AGI when we have an embodied AI that can do the job of a plumber. It sounds silly, but plumbers need to work in very varied environments, solve physical problems in those environments, while conforming to code, essentially being able to solve problems across mental and physical domains...putting the general into general.
I don’t think it’s necessary for an AI to operate in the physical world to achieve the dystopian-level impact people expect. After all, the most powerful people in the world operate only by talking to other people. An AGI would solve a plumbing problem by finding and hiring the best plumber and telling them what it needs done. And it would use you to be its eyes and verify the job is done. Whether it’s AGI is, to me, a question of who appears to be serving who.
I really dislike this framing. Historically we've been very confused about what AGI means because we don't actually understand it. We're still confused so most working definitions have been iterated upon as models acquire new capabilities. It's akin to searching something in the fog of war: you set a course or destination because you think that's the approximate direction where the thing will be found, but then you get there and realize you were wrong so you continue exploring.
Most people have a rough idea of what AGI means, but we still haven't figured out an exact definition that lines up with reality. As we continue exploring the idea space, we'll keep figuring out which parameters place boundaries and requirements on what AGI means.
There's no reason to just accept an ancient definition from someone who was confused and didn't know any better at the time when they invented their definition. Older definitions were just shots in the dark that pointed in a general direction, but there's no guarantee that they would hit upon the exact destination.
I think there's a single definition of AGI that will stand until the singularity:
"An AGI is a human-created system that demonstrates iteratively improving its own conceptual design without further human assistance".
Note that a "conceptual design" here does not include tweaking weights within an already-externally-established formula.
My reasoning is thus:
1. A system that is only capable of acting with human assistance cannot have its own intelligence disentangled from the humans'
2. A system that is only intelligent enough to solve problems that somehow exclude problems with itself is not "generally" intelligent
3. A system that can only generate a single round of improvements to its own designs has not demonstrated improvements to those designs, as if iteration N+1 were truly superior to iteration N, it would be able to produce iteration N+2
4. A system that is not capable of changing its own design is incapable of iterative improvement, as there is a maximum efficacy within any single framework
5. A system that could improve itself in theory and fails to do so in practice has not demonstrated intelligence
It's pretty clear that no current-day system has hit this milestone; if some program had, there would no longer be a need for continued investment in algorithms design (or computer science, or most of humanity...).
A program that randomly mutates its own code could self-improve in theory but fails to do so in practice.
I don't think these goalposts have moved in the past or need to move in the future. This is what it takes to cause the singularity. The movement recently has been people trying to sell something less than this as an AGI.
AGI means "artificial general intelligence", it's got nothing to do with the singularity (which requires "artificial superior intelligence"; ASI). Requiring AGI to have capabilities that most humans lack is moving the goal post WRT to how it was originally defined.
I don't think this is capabilities humans do not have, this to me is the one capability humans destinctly have over LLMs, the ability to introspect and shape their own future.
I feel this definition doesn't require a current LLM model to be able to change its own working but to be able to generate a guided next generation.
It's possible that LLMs can surpass human beings, purely because I believe we will inevitably be limited to short term storage constraints which LLMs will not. It will be a bandwidth vs througput question. An LLM will have a much larger although slightly slower store of knowledge than what human have. But will be much quicker than a human looking up and validating the data.
> The movement recently has been people trying to sell something less than this as an AGI.
Selling something that does not yet exist is an essential part of capitalism, which - according to the main thesis of philosophical Accelerationism - is (teleologically) identical to AI. [0] It's sometimes referred to as Hyperstition, i.e. fictions that make themselves real.
There is a similar issue with image and video generation. Asking the AI to "Generate an image of a man holding a pencil with his left hand" or "Generate a clock showing the time 5 minutes past 6 o'clock" often fail due to so many images in the training set being similar (almost all clock images on show 10:10 (https://generativeai.pub/in-the-ai-art-world-the-time-is-alm...)
> I've always been a staunch defender of capitalism and free markets, even though that's historically been an unpopular opinion in my particular social circle. Watching the LLM market, I can't help but feel extremely vindicated.
> The brutal and bruising competition between the tech giants has left nothing but riches for the average consumer.
Capitalism has always been great at this: creating markets, growing them, producing new goods. It's widely acknowledged amongst people who actually seek to gain an understanding of Marxism, and don't just stay in the surface-level black-and-white "socialism and capitalism are opposites" discourse that's very common in the West, especially the USA, especially after the McCarthy's Red Scare.
The problem is what comes once the market is grown and the only way for owners keep profits growing is: 1. consolidating into monopolies or cartels, so competition doesn't get in the way of profits, 2. squeezing the working class, looking to pay less for more work, and/or 3. abusing the natural world, to extract more materials or energy for less money. This is evident in plenty of developed industries: from health care, to broadcasting, telecommunications, fashion, etc.
If we view Socialism for what it is, namely a system built to replace Capitalism's bad parts but keep its good parts, China's system, for example, starts to make more sense. Capitalism in a similar way was an evolution from Feudalism that replaced it's bad parts, to achieve greater liberty for everyone— liberty is very much lost as Feudalism matures, but great for society as a whole. Socialism is meant to be the similar, aiming to achieve greater equity, which it views as very much better for society as a whole.
All the problems regarding AI will be anwered way sooner when people stop calling intelligent that which is literally as dumb as a rock. There is absolutelly 0 intelligence in current state-of-the-art ML programs. Intelligence is not the ability to solve a task, or any amount of tasks (especially the ones you have seen a million times). Intelligence is the act of successfully navigating the unknown, which is by technical definition the weakest point of all ML, from simple regression to NNs to LLMs
Is this for real? ... All this Hype is ... very-very old Hype, and nothing fundamentally new (yet) from 1960s time. Looks like every upgrade of software is "revolution" or "revelation". Please compare 'Win 3.1' and 'Win 11', some progress? sure!, is any "Intelligence" there? No! No! No! What is the difference? Who constantly lying and why? What is the reason of this systematic and persistent lies? p.s. I, personally think, that someday we will have a "semi-smart" computer systems, I also think, in a 5-10 years, we will learn more what is possible and real and what is not (regarding "semi-smart" computer systems). Until that ... hold your horses (please), so to speak.
The first thing I want AGI to do is to be able to tell me when it doesn’t know something, or when it’s not certain, so at least give me a heads up to set expectations correctly. I ran my own personal “benchmark” on Gemini 2.5 and it failed just like all others. I told it that I was playing an old point-and-click adventure game from the mid-90s and I was stuck on a certain part, and asked for spoiler-light hints on what to do next. Not only can they not give me hints, they hallucinate completely the game, and invent some weird non-sensical solutions. Every single model does this. Even if I tell them to give up and just give me the solution, they come up with some non-existing solution.
I wonder how hard it is to objectively use information that is available online for 30 years? But the worst part is how it lies and pretends it knows what it’s talking about, and when you point it out it simply turns into another direction and starts lying again. Maybe the use case here is not the main focus of modern AI; maybe modern AI is about generating slop that does not require verification, because it’s “new” content. But to me it just sounds like believable slop, not AGI.
Context gathering - Attempting to answer question via LLM: Are there existing Conversation classes in the ecosystem this should extend?
Context gathering - LLM provided answer: "No"
Context gathering - Attempting to answer question via LLM: How should model selection work when continuing a previous conversation?
Context gathering - LLM answer was UNKNOWN, asking user.
Asking user: How should model selection work when continuing a previous conversation?
Context gathering - received user response to question: "How should model selection work when continuing a previous conversation?"
I fail to see how LLMs are anything beyond a lookup function retrieving information from a huge database (containing, in theory, all known human information), and then summarizing the results using language algorithms.
While incredibly powerful and transformative, it is not 'intelligence'. LLMs are forever knowledgebase bound. They are encyclopedias with a fancy way of presenting information looked up in the encyclopedia.
The 'presentation' has no concept, awareness, or understanding of the information being presented - and never will. And this is the critical line. Without comprehension, a LLM is incapable of being creative. Of coming up with new ideas. It cannot ponder. Wonder. Think.
It's not AGI because it still doesn't understand anything. It can only tell you things that can be found on the internet. These "jagged" results expose the truth that these models have near 0 intelligence.
It is not a simple matter of patching the rough edges. We are fundamentally not using an architecture that is capable of intelligence.
Personally the first time I tried deep research on a real topic it was disastrously incorrect on a key point.
I think determinism is an important element. You can ask the same LLM the same question repeatedly and get different answers - and not just different ways of stating the same answer, very different answers.
If you ask an intelligent being the same question they may occasionally change the precise words they use but their answer will be the same over and over.
That's not an inherent property of the system. You can choose the most likely token(topk=1) and it will be deterministic (at least in theory, in some hardware setups it might be trickier)
A human will give different answers to the same question, so I’m not sure why it’s fair to set a higher bar for an LLM. Or rather, I’m not sure how you would design this test in a way where humans would pass and the best LLM would fail.
That's because "intelligent beings" have memory. If you ask an LLM the same question within the same chat session you'll get a consistent answer about it.
I disagree. If you were to take a snapshot of someone's knowledge and memory such that you could restore to it over and over, that person would give the same answer to the question. The same is not true for an LLM.
Heck, I can't even get LLMs to be consistent about *their own capabilities*.
Bias disclaimer: I work at Google, but not on Gemini. If I ask Gemini to produce an SVG file, it will sometimes do so and sometimes say "sorry, I can't, I can only produce raster images". I cannot deterministically produce either behavior - it truly seems to vary randomly.
We're often explicitly adding in randomness to the results so it feels weird to then accuse them of not being intelligent after we deliberately force them off the path.
There are some very strong and very unfounded assumptions in your comment. Is there anything more substantial there other than "that's what it feels like to me"?
I just used 2.5 Pro to help write a large research proposal (with significant funding on the line). Without going into detail, it felt to me like the only reason it couldn’t write the entire thing itself is because I didn’t ask it to. And by “ask it”, I mean: enter into the laughably small chat box the entire grant solicitation + instructions, a paragraph of general direction for what I want to explore, and a bunch of unstructured artifacts from prior work, and turn it loose. I just wasn’t audacious enough to try that from the start.
But as the deadline approached, I got more and more unconstrained in how far back I would step and let it take the reins - doing essentially what’s described above but on isolated sections. It would do pretty ridiculously complex stuff, like generate project plans and timelines, cross reference that correctly with other sections of text, etc. I can safely say it was a 10x force multiplier, and that’s being conservative.
For scientific questions (ones that should have publicly available data, not ones relying on internal data), I have started going to 2.5 Pro over senior experts on my own team. And I’m convinced at this point if I were to connect our entire research data corpus to Gemini, that balance would shift even further. Why? Because I can trust it to be objective - not inject its own political or career goals into its answers.
I’m at the point where I feel the main thing holding back “AGI” is people’s audacity to push its limits, plus maybe context windows and compute availability. I say this as someone who’s been a major skeptic up until this point.
However (as the article admits) there is still no general agreement of what AGI is, or how we (or even if we can) get there from here.
What there is is a growing and often naïve excitement that anticipates it as coming into view, and unfortunately that will be accompanied by the hype-merchants desperate to be first to "call it".
This article seems reasonable in some ways but unfortunately falls into the latter category with its title and sloganeering.
"AGI" in the title of any article should be seen as a cautionary flag. On HN - if anywhere - we need to be on the alert for this.
Systems that have general intelligence are ones that are capable of applying reason to an unbounded domain of knowledge. Examples of such systems include: libraries, wikis, and forums like HN. These systems are not AGI, because the reasoning agents in each of these systems are organic (humans); they are more like a cyborg general intelligence.
Artificial general intelligence are just systems that are fully artificial (ie: computer programs) that can apply reason to an unbounded domain of knowledge. We're here, and we have been for years. AGI sets no minimum as to how great the reasoning must be, but it's obvious to anyone who has used modern generative intelligence systems like LLMs that the technology can be used to reason about an unbounded domain of knowledge.
If you don't want to take my word for it, maybe Peter Norvig can be more convincing: https://www.noemamag.com/artificial-general-intelligence-is-...
(I did x and it failed, I did y and It failed, I should try z now) GOOD
(I did x and it failed, I did y and it failed, I should try x now) BAD
It is very hard to argue with Norvig’s arguments that AGI has been around since at least 2023.
You can argue that for the first time in the history we have an AI that deserves its name (unlike Deep blue or AlphaGo which aren't really about intelligence at all) but you cannot call that Artificial GENERAL Intelligence before it overcomes the “jagged intelligence” syndrome.
The first step, my guess, is going to be the ability to work through github issues like a human, identifying which issues have high value, asking clarifying questions, proposing reasonable alternatives, knowing when to open a PR, responding to code review, merging or abandoning when appropriate. But we're not even very close to that yet. There's some of it, but from what I've seen most instances where this has been successful are low level things like removing old feature flags.
If I forced you to use unnatural interfaces it would severely limit your capabilities as well because you'd have to dedicate more effort towards handling basic editing tasks. As someone who recently swapped to a split 36key keyboard with a new layout I can say this becomes immediately obvious when you try something like this. You take your typing/editing skills for granted - try switching your setup and see how your productivity/problem solving ability tanks in practice.
The catch in this though isn't the ability to use these interfaces. I expect that will be easy. The hard part will be, once these interfaces are learned, the scope and search space of what they will be able to do is infinitely larger. And moreover our expectations will change in how we expect an AGI to handle itself when our way of working with it becomes more human.
Right now we're claiming nascent AGI, but really much of what we're asking these systems to do have been laid out for them. A limited set of protocols and interfaces, and a targeted set of tasks to which we normally apply these things. And moreover our expectations are as such. We don't converse with them as with a human. Their search space is much smaller. So while they appear AGI in specific tasks, I think it's because we're subconsciously grading them on a curve. The only way we have to interact with them prejudices us to have a very low bar.
That said, I agree that video feed and mouse is a terrible protocol for AI. But that said, I wouldn't be surprised if that's what we end up settling on. Long term, it's just going to be easier for these bots to learn and adapt to use human interfaces than for us to maintain two sets of interfaces for things, except for specific bot-to-bot cases. It's horribly inefficient, but in my experience efficiency never comes out ahead with each new generation of UIs.
This is true but AGI means "Artificial General Intelligence". Perhaps it would be even more efficient with certain interfaces, but to be general it would have to at least work with the same ones as humans.
Here's some things that I think a true AGI would need to be able to do:
* Control a general purpose robot and use vision to do housework, gardening etc.
* Be able to drive a car - equivalent interfaces to humans might be service motor controlled inputs.
* Use standard computer inputs to do standard computer tasks
And this list could easily be extended.
If we have to be very specific in the choice of interfaces and tasks that we give it, it's not a general AI.
At the same time, we have to be careful at moving the goalposts too much. But current AI are limited to what can be returned in a small number of interfaces (prompt with text/image/video & return text/image/video data). This is amazing, they can sound very intelligent while doing so. But it's important not to lose sight of what they still can't do well which is basically everything else.
Outside of this area, when you do hear of an AI doing something well (self driving, for example) it's usually a separate specialized model rather than a contribution towards AGI.
Similarly I wouldn't be "Generally Intelligent" by this definition if you sat me at a Cyrillic or Chinese keyboard. For this reason, I see human-centric interface arguments as a red herring.
I think a better candidate definition might be about learning and adapting to new environments (learning from mistakes and predicting outcomes), assuming reasonable interface aids.
Would you be able to be taught to use those keyboards? Then you're generally intelligent. If you could not learn, then maybe you're not generally intelligent?
Regarding disabled people, this is an interesting point. Assuming that we're talking about physical disabilities only, disabled people are capable of learning how to use any standard human inputs. It's just the physical controls that are problematic.
For an AI, the physical input is not the problem. We can just put servo motors on the car controls (steering wheel, brakes, gas) and give it a camera feed from the car. Given those inputs, can the AI learn to control the car as a generally intelligent person could, given the ability to use the same controls?
Ever heard of Pandora's Box? Yeah. That ship has sailed. No moratorium you could enact would, at this point, stop the innovation from happening, possibly even independently by multiple teams globally. Economic incentives are stacked in such a way that flakey tech companies will prioritise shareholder value over anything else. Whatever comes next will come, and all we can do is lean back and enjoy the show.
Of course, the political will to do so doesn't exist to even a tiny extent. But if such a will existed, it would be far easier to enforce than the prevention of human cloning, and that one has been successfully implemented for decades now.
Won´t say people fell for it though it was just the current happening at the time.
Given how Dutch disease[0] is described, I suspect that if the "G" (general) increases with fixed "I" (intelligence), as the proportion of economic activity for which the Pareto frontier is AI rather than human expands, I think humans will get pay rises for the remaining work right up until they get unemployable.
On the other hand, if "G" is fully general and it's "I" which rises for a suitable cost[1], it goes through IQ 55 (displacing no workers) to IQ 100 (probably close to half of workers redundant, but mean of population doesn't have to equal mean of workforce), to IQ 145 (almost everyone redundant), to IQ 200 (definitionally renders everyone redundant).
[0] https://en.wikipedia.org/wiki/Dutch_disease
[1] A fully-general AGI with the equivalent of IQ 200 on any possible test, still can't replace a single human if it costs 200 trillion USD per year to run.
In what cases is it superhuman exactly? And what humans are you comparing against?
I'd bet that for any discipline you chose, one could find an expert in that field that can trick any of today's post-gpt3 ais.
I agree, but with the caveat that it's getting harder and harder with all the hype / doom cycles and all the goalpost moving that's happening in this space.
IMO if you took gemini2.5 / claude / o3 and showed it to people from ten / twenty years ago, they'd say that it is unmistakably AGI.
Which is to say complete amazement followed quickly by seeing all the many ways in which it absolutely falls flat on its face revealing the lack of actual thinking, which is a situation that hasn't fundamentally changed since then.
No they wouldn't, since those still can't replace human white collar workers even at many very basic tasks.
Once AGI is here most white collar jobs are gone, you'd only need to hire geniuses at most.
Middle schoolers replace white collars workers all the time, it takes 10 years for them to do it but they can do it.
No current model can do the same since they aren't able to learn over time like a middle schooler.
I mean, if you're a CEO or middle manager and you have the choice of hiring this middle schooler for general office work, or today's gemini-2.5-pro, are you 100% saying the ex-middle-schooler is definitely going to give you best bang for your buck?
Assuming you can either pay them $100k a year, or spend the $100k on gemini inference.
Gemini 2.5 pro the model has not gained any intelligence since it is a static model.
New models are not the models learning, it is humans creating new models. The models trained has access to all the same material and knowledge a middle schooler has as they go on to learn how to do a job, yet they fail to learn the job while the kid succeeds.
So, fine, the gemini-2.5-pro model hasn't gotten more intelligent. What about the "Google AI Studio API" as a system? Or the "OpenAI chat completions API" as a system?
This system has definitely gotten vastly smarter based on the input it's gotten. Would you now concede, that if we look at the API-level (which, by the way, is the way you as the employer do interact with it) then this entity has gotten smarter way faster than the middle-schooler in the last 2.5 years?
Surely that's an irrelevant distinction, from the point of view of a hiring manager?
If a kid takes ten years from middle school to being worth hiring, then the question is "what new AI do you expect will exist in 10 years?"
How the model comes to be, doesn't matter. Is it a fine tune on more training data from your company docs and/or an extra decade of the internet? A different architecture? A different lab in a different country?
Doesn't matter.
Doesn't matter for the same reason you didn't hire the kid immediately out of middle school, and hired someone else who had already had another decade to learn more in the meantime.
Doesn't matter for the same reason that different flesh humans aren't perfectly substitutable.
You pay to solve a problem, not to specifically have a human solve it. Today, not in ten years when today's middle schooler graduates from university.
And that's even though I agree that AI today doesn't learn effectively from as few examples as humans need.
Stop moving the goalposts closer, that you think humans might make an AGI in the future doesn't mean the current AI is an AGI just because it uses the same interface.
Preceding quotation to which you objected:
> A middle schooler has general intelligence (they know about and can do a lot of things across a lot of different areas) but they likely can't replace white collar workers either.
Your response:
> Middle schoolers replace white collars workers all the time, it takes 10 years for them to do it but they can do it.
So I could rephrase your own words here as "Stop moving the goalposts closer, that you think a middle schooler might become a General Intelligence in the future doesn't mean the current middle schooler is a General Intelligence just because they use the same name".
Aren't all the people interacting with it on aistudio helping the next Gemini model learn though?
Sure, the results of that wont be available until the next model is released, but it seems to me that human interaction/feedback is actually a vital part of LLM training.
You and I could sit behind a keyboard, role-playing as the AI in a reverse Turing test, typing away furiously at the top of our game, and if you told someone that their job is to assess our performance (thinking they're interacting with a computer), they would still conclude that we are definitely not AGI.
This is a battle that can't be won at any point because it's a matter of faith for the forever-skeptic, not facts.
That isn't a proof since you haven't ran that test, it is just a thought experiment.
(Have you not experienced being on the recieving end of such accusations? Or do I just write weird?)
I think this demonstrates the same point.
No, I have not been accused of being an AI. I have seen people who format their texts get accused due to the formatting sometimes, and thought people could accuse me for the same reason, but that doesn't count.
> I think this demonstrates the same point.
You can't detect general intelligence from a single message, so it doesn't really. People accuse you for being an AI based on the structure and word usage of your message, not the content of it.
If that's the real cause, it is not the reason they give when making the accusation. Sometimes they object to the citations, sometimes the absence of them.
But it's fairly irrelevant, as they are, in fact, saying that real flesh-and-blood me doesn't pass their purity test for thinking.
Is that because they're not thinking? Doesn't matter — as @sebastiennight said: "This is a battle that can't be won at any point because it's a matter of faith for the forever-skeptic, not facts."
Well, that's 91th percentile already. I know the terms are hazy, but that seems closer to ASI than AGI from that perspective, no?
I think I do agree with you on the other points.
ASI is, by definition, Superintelligence, which means it is beyond practical human IQ capacity. So something like 200 IQ.
Again, you might call it 'unfair', but that's when it will also stop having goal posts being moved; otherwise, Joe Midwit will call it 'it's only as smart as some smart dudes I know'.
They might get more powerful but I feel like they're still missing something.
AI doesn't go and read a book on best practices, then comes back saying "Now I know Kung Fu of Software Implementation" and then critically thinks looking at your plan step by step and provides answer. These systems, for now, don't work like that.
Would you disagree?
> The phrase "I know it when I see it" was used in 1964 by United States Supreme Court Justice Potter Stewart to describe his threshold test for obscenity in Jacobellis v. Ohio
Its generalization capabilities are a bit on the low side, and memory is relatively bad. But it is much more than just a parrot now, it can handle some of basic logic, but not follow given patterns correctly for novel problems.
I'd liken it to something like a bird, extremely good at specialized tasks but failing a lot of common ones unless repeatedly shown the solution. It's not a corvid or a parrot yet. Fails rather badly at detour tests.
It might be sentient already though. Someone needs to run a test if it can discern itself and another instance of itself in its own work.
It doesn't have any memory, how could it tell itself from a clone of itself?
It's a fun test to give a person something they have written but do not remember. Most people can still spot it.
It's easier with images though. Especially a mirror. For DallE, the test would be if it can discern its own work from human generated image. Especially of you give it an imaginative task like drawing a representation of itself.
If we call people with an IQ of less than 80 an intelligent life form, why can't we call an LLM that?
Anyway, sorry for a digression, my point is LLM replacing white collar workers doesn't necessarily imply it's generally intelligent -- it may but doesn't have to be.
Although if it gets to a point where companies are running dark office buildings (by analogy with dark factories) -- yes, it's AGI by then.
it should suffice to say we are nowhere near that and I dont even believe LLMs are the right architecture for that.
Are we talking about something other than Agreeableness in the personality research sense [0]?
The strongest form of your argument I can think of is “willing to contradict you when it thinks you’re wrong”—but you can disagree agreeably, right? The current-gen LLMs certainly have with me, perhaps because my custom prompt encourages them to skepticism—but they do it so nicely!
[0] https://en.m.wikipedia.org/wiki/Agreeableness
No, the concepts are linked, agreeable people don't want to be rude and most people see disagreements as being rude no matter how you frame it. You can't call a woman overweight without being rude for example no matter how you frame it, but maybe you want an AI that tells you that you weigh too much.
AGI doesn't need to be "called", and there is no need for anyone to come to an agreement as to what its precise definition is. But at some point, we will cross that hard-to-define threshold, and the economic effects will be felt almost immediately.
We should probably be focusing on how to prepare society for those changes, and not on academic bullshit.
Stuff like society of minds (Minksy), embodied cognition (Varela, Rosch, and Thompson), connectionist or subsymbolic views (Rumelhart), multiple intelligences (Gardner), psychometric and factor-analytic theories (Carroll), and all the other work like E. Hutchins. They're far from just academic wankery, there's a lot of useful stuff in there, it's just completely ignored by the AI crowd.
In cases where 95%+ of the information on the internet is misinformation, the current incarnations of LLMs have a really hard time sorting out and filtering out the 5% of information that's actually valid and useful.
In that sense, current LLMs are not yet superhuman at all, though I do think we can eventually get there.
I would do the same thing, I think. It's too well-known.
The variation doesn't read like a riddle at all, so it's confusing even to me as a human. I can't find the riddle part. Maybe the AI is confused, too. I think it makes an okay assumption.
I guess it would be nice if the AI asked a follow up question like "are you sure you wrote down the riddle correctly?", and I think it could if instructed to, but right now they don't generally do that on their own.
You should be able to click left right on the prompt to see different responses. Sonnet 3.7 with extended thinking notices the issue, and then chooses to totally ignore it with no explanation.
From Claude for those who don’t want to click:
Wait, I notice a difference from the traditional riddle. In this version, the surgeon says "I can operate on this boy" (affirmative) rather than "I can't operate on this boy" (negative).
This changes the nature of the puzzle somewhat. If the surgeon is saying they CAN operate, then we need to explain why this is surprising or seemingly impossible, but actually possible.
The traditional answer would still apply: the surgeon is the boy's mother.
However I gotta take issue with using those analogies when "it's trained for text completion and the punchline to this riddle is surely in its training data a lot" is a perfectly good explanation. I guess I would also add that the answer is well-aligned with RLHF-values. I wouldn't go for an explanation that requires squishy analogies when the stuff we know about these things seems completely adequate.
LLMs doesn't assume, its a text completer. It sees something that looks almost like a well known problem and it will complete with that well known problem, its a problem specific to being a text completer that is hard to get around.
Discussing whether models can "reason" or "think" is a popular debate topic on here, but I think we can all at least agree that they do something that at least resembles "reasoning" and "assumptions" from our human point of view. And if in its chain-of-thought it decides your prompt is wrong it will go ahead answering what it assumes is the right prompt
Yes, and it can express its assumptions in text.
Ask it to make some assumptions, like about a stack for a programming task, and it will.
Whether or not the mechanism behind it feels like real thinking to you, it can definitely do this.
But I'd wager it's there; assuming is not a particularly impressive or computationally intense operation. There's a tendency to bundle all of human consciousness into the definitions of our cognitive components, but I would argue that, eg., a branch predictor is meeting the bar for any sane definition of 'assume'.
If you give an LLM "The rain in Spain falls" the single most likely next token is "mainly", and you'll see that one proportionately more than any other.
If you give an LLM "Find an unorthodox completion for the sentence 'The rain in Spain falls'", the most likely next token is something other than "mainly" because the tokens in "unorthodox" are more likely to appear before text that otherwise bucks statistical trends.
If you give the LLM "blarghl unorthodox babble The rain in Spain" it's likely the results are similar to the second one but less likely to be coherent (because text obeying grammatical rules is more likely to follow other text also obeying those same rules).
In any of the three cases, the LLM is predicting text, not "parsing" or "understanding" a prompt. The fact it will respond similarly to a well-formed and unreasonably-formed prompt is evidence of this.
It's theoretically possible to engineer a string of complete gibberish tokens that will prompt the LLM to recite song lyrics, or answer questions about mathemtical formulae. Those strings of gibberish are just difficult to discover.
Did you mean to ask about the well-known phrase "The rain in Spain falls mainly on the plain"? This is a famous elocution exercise from the musical "My Fair Lady," where it's used to teach proper pronunciation.
Or was there something specific you wanted to discuss about Spain's rainfall patterns or perhaps something else entirely? I'd be happy to help with whatever you intended to ask. "
I think you have a point here, but maybe re-express it? Because right now your argument seems trivially falsifiable even under your own terms.
If you want to test convolution you have to use a raw model with no system prompt. You can do that with a Llama or similar. Otherwise your context window is full of words like "helpful" and "answer" and "question" that guide the response and make it harder (not impossible) to see the effect I'm talking about.
Because I've tried it on a few local models I have handy, and I don't see that happening at all. As someone else says, some of that difference is almost certainly due to supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) -- but it's weird to me, given the confidence you made your prediction, that you didn't exclude those from your original statement.
I guess, maybe the real question here is: could you give me a more explicit example of how to show what you are trying to show? And explain why I'm not seeing it while running local models without system prompts?
There's more than just next token prediction going on. Those reasoning chain of thoughts have undergone their own reinforcement learning training against a different category of samples.
They've seen countless examples of how a reasoning chain would look for calculating a mortgage, or searching a flight, or debugging a Python program.
So I don't think it is accurate to describe the eventual result as "just next token prediction". It is a combination of next token production that has been informed by a chain of thought that was based on a different set of specially chosen examples.
If not, why not? Explain.
If so, how does your argument address the fact that this implies any given "reasoning" model can be trained without giving it a single example of something you would consider "reasoning"? (in fact, a "reasoning" model may be produced by random chance?)
Infinity is problematic because its impossible to process an infinite amount of data in a finite amount of time.
It’s predicting text. Yes. Nobody argues about that. (You’re also predicting text when you’re typing it. Big deal.)
How it is predicting the text is the question to ask and indeed it’s being asked and we’re getting glimpses of understanding and lo and behold it’s a damn complex process. See the recent anthropic research paper for details.
Don't humans do the same in conversation? How should an intelligent being (constrained to the same I/O system) respond here to show that it is in fact intelligent?
There exists no similar set of tokens for humans, because our process is to parse the incoming sounds into words, use grammar to extract conceptual meaning from those words, and then shape a response from that conceptual meaning.
Artists like Lewis Carrol and Stanislaw Lem play with this by inserting non-words at certain points in sentences to get humans to infer the meaning of those words from surrounding context, but the truth remains that an LLM will gladly convolute a wholly non-language input into a response as if it were well-formed, but a human can't/won't do that.
I know this is hard to understand, but the current generation of LLMs are working directly with language. Their "brains" are built on language. Some day we might have some kind of AI system that's built on some kind of meaning divorced from language, but that's not what's happening here. They're engineering matrixes that repeatedly perform "context window times model => one more token" operations.
Maybe not for humanity as a species, but for individual humans there are absolutely token sequences that lead them to talk about certain topics, and nobody being able to bring them back to topic. Now you'd probably say those are recognizable token sequences, but do we have a fair process to decide what's recognizable that isn't inherently biased towards making humans the only rational actor?
I'm not contending at all that LLMs are only built on language. Their lack of physical reference point is sometimes laughably obvious. We could argue whether there are signs they also form a world model and reasoning that abstracts from language alone, but that's not even my point. My point is rather that any test or argument that attempts to say that LLMs can't "reason" or "assume" or whatever has to be a test a human could pass. Preferably a test a random human would pass with flying colors.
For one thing, LLMs absolutely form responses from conceptual meanings. This has been demonstrated empirically multiple times now including again by anthropic only a few weeks ago. 'Language' is just the input and output, the first and last few layers of the model.
So okay, there exists some set of 'gibberish' tokens that will elicit meaningful responses from LLMs. How does your conclusion - "Therefore, LLMs don't understand" fit the bill here? You would also conclude that humans have no understanding of what they see because of the Rorschach test ?
>There exists no similar set of tokens for humans, because our process is to parse the incoming sounds into words, use grammar to extract conceptual meaning from those words, and then shape a response from that conceptual meaning.
Grammar is useful fiction, an incomplete model of a demonstrably probabilistic process. We don't use 'grammar' to do anything.
If those two sets of accomplishments are the same there's no point arguing about differences in means or terms. Right now humans can build better LLMs but nobody has come up with an LLM that can build better LLMs.
Are we sure it's actually taking us along?
Yet. Not that we know of, anyway.
Neural Networks as I understand them are universal function approximators.
In terms of text, that means they're trained to output what they believe to be the "most probably correct" sequence of text.
An LLM has no idea that it is "conversing", or "answering" -- it relates some series of symbolic inputs to another series of probabilistic symbolic outputs, aye?
The problem you've just described is a problem with humans as well. LLMs are assuming all the time. Maybe you would like to call it another word, but it is happening.
I didn't train to complete text though, I was primarily trained to make accurate responses.
And no, writing a response is not "completing text", I don't try to figure out what another person would write as a response, I write what I feel people need to read. That is a completely different thought process. If I tried to mimic what another commenter would have written it would look very different.
Functionally, it is. You're determining what text should follow the prior text. Your internal reasoning ('what I feel people need to read') is how you decide on the completion.
The core point isn't that your internal 'how' is the same as an LLM's (Maybe, Maybe not), but that labeling the LLM as a 'text completer' they way you have is essentially meaningless.
You are just imposing your own ideas on the how a LLM works, not speaking any fundamental truth of being a 'text completer'.
Also, LLMs absolutely 'plan' and 'aim for something' in the process of completing text.
https://www.anthropic.com/research/tracing-thoughts-language...
They use a replacement model. It isn't even observing the LLM itself but a different architecture model. And it is very liberal with interpreting the patterns of activations seen in the replacement model with flowery language. It also include some very relevant caveats, such as:
"Our cross-layer transcoder is trained to mimic the activations of the underlying model at each layer. However, even when it accurately reconstructs the model’s activations, there is no guarantee that it does so via the same mechanisms."
https://transformer-circuits.pub/2025/attribution-graphs/met...
So basically the whole exercise might or might not be valid. But it generates some pretty interactive graphics and a nice blog post to reinforce the anthropomorphization discourse
Nonsense. Mechanistic faithfulness probes whether the replacement model (“cross‑layer transcoder”) truly uses the same internal functions as the original LLM. If it doesn’t, the attribution graphs it suggests might mis‐lead at a fine‐grained level but because every hypothesis generated by those graphs is tested via direct interventions on the real model, high‑level causal discoveries (e.g. that Claude plans its rhymes ahead of time) remain valid.
In every LLM thread someone chimes in with “it’s just a statistical token predictor”.
I feel this misses the point and I think it dismisses attention heads and transformers, and that’s what sits weird with me every time I see this kind of take.
There _is_ an assumption being made within the model at runtime. Assumption, confusion, uncertainty - one camp might argue that none of these exist in the LLM.
But doesn’t the implementation constantly make assumptions? And what even IS your definition of “assumption” that’s not being met here?
Edit: I guess my point, overall, is: what’s even the purpose of making this distinction anymore? It derails the discussion in a way that’s not insightful or productive.
Those just makes it better at completing the text, but for very common riddles those tools still gets easily overruled by pretty simple text completion logic since the weights for those will be so extremely strong.
The point is that if you understand its a text completer then its easy to understand why it fails at these. To fix these properly you need to make it no longer try to complete text, and that is hard to do without breaking it.
These days it's all about confidently bullshitting on benchmarks and overfitting on common riddles to make pointless numbers go up. The more impressive models get on paper, the more rubbish they are in practice.
I asked it to add websocket support for my app and it responded like, "looks like you're using long polling now. That's actually better and simpler. Lets leave it how it is."
I was genuinely amazed.
> What weighs more; a pound of courage or a pound coin?
> They weigh the same—each is a “pound.” A pound of courage and a pound coin both come out to one pound in weight!
https://chatgpt.com/share/68053ad0-aae4-800d-95ff-5b5b0a9a38...
I didn't know what AGI is, but I know this isn't it.
:::thinking This question is playing with words and units.
A "pound of courage" refers to a metaphorical measurement of the abstract concept of courage, using the imperial weight unit "pound" (which equals 453.59 grams).
A "pound coin" refers to the physical currency of the United Kingdom, which is called a "pound" but is a unit of currency, not weight. A physical pound coin weighs about 8-9 grams (specifically, the current 12-sided pound coin weighs 8.75 grams).
So comparing them: - A pound of courage would weigh 453.59 grams (if courage had physical weight, which it doesn't since it's an abstract concept) - A pound coin weighs approximately 8.75 grams
The trick in this question is that it's comparing: 1. A specific weight of an abstract concept (pound of courage) 2. A physical coin whose name includes the word "pound" but refers to currency, not weight
Since the question asks what weighs more, and weight is a physical property, I should point out that courage is abstract and doesn't have physical weight, while a pound coin is a physical object with a measurable weight. ::: # Comparing "A Pound of Courage" vs "A Pound Coin"
This is a play on words with different meanings of "pound":
- A *pound of courage* refers to a metaphorical pound (weight unit) of an abstract concept - A *pound coin* is a physical British currency coin (which weighs about 8.75 grams)
If we're talking about physical weight: - A pound of courage doesn't have physical weight since courage is abstract - A pound coin has a definite weight of approximately 8.75 grams
If we interpreted "pound of courage" as literally one pound (453.59 grams) of something, it would weigh significantly more than the coin.
This question is clever because it compares a metaphorical measurement with a physical object whose name includes the word "pound" but in a different context.
I would look along the lines of the value of a human being based on traits vs payment which is likely what the original phrase intended.
Is paying someone more better than getting a better candidate but paying them less.
> In literal, physical terms, a pound of courage would—by definition—tip the scales at one avoirdupois pound (≈ 454 g). A modern UK £1 coin, on the other hand, weighs only 8.75 g. So if you could bottle bravery, the jar marked “1 lb Courage” would outweigh the coin by a factor of about 52 to 1.
> (Of course, measured in sheer impact, courage can feel far heavier than anything money can buy!)
https://chatgpt.com/share/68057dbc-2ff4-8010-ac30-b404135200...
> In some tasks, AI is unreliable. In others, it is superhuman. You could, of course, say the same thing about calculators, but it is also clear that AI is different. It is already demonstrating general capabilities and performing a wide range of intellectual tasks, including those that it is not specifically trained on. Does that mean that o3 and Gemini 2.5 are AGI? Given the definitional problems, I really don’t know, but I do think they can be credibly seen as a form of “Jagged AGI” - superhuman in enough areas to result in real changes to how we work and live, but also unreliable enough that human expertise is often needed to figure out where AI works and where it doesn’t.
Certainly jagged does not imply general
It seems to me the bar for "AGI" has been lowered to measuring what tasks it can do rather than the traits we normally associate with general intelligence. People want it to be here so bad they nerf the requirements...
My partner and I work in different fields. AI has advanced to the point where there are very few questions I could ask my partner that o3 couldn't answer as well or better.
I can't ask expert level questions in her field, because I'm not an expert in her field, and she couldn't ask expert level questions in my field for the same reason. So when we're communicating with each other, we're mostly at sub-o3 level.
> People want it to be here so bad they nerf the requirements...
People want to claim it's overhyped (and protect their own egos) so badly they raise the requirements...
But really, largely people just have different ideas of what AGI is supposed to mean. It used to vaguely mean "human-level intelligence", which was fine for talking about some theoretical future event. Now we're at a point where that definition is too vague to say whether AI meets it.
We kind of don't? Look how difficult it is for us to just understand some basic math. Us humans mostly have intelligence related to the ancestral environment we developed in, nothing general about that.
I agree with you the term "AGI" is rather void of meaning these days...
I still find task based measures insufficient, there are very basic machines than can perform tasks humans cannot. Should this be a measure on our or their intelligence?
I have another comment in this thread about trait based metrics being a possibly better method.
> People want to claim it's overhyped (and protect their own egos) so badly they raise the requirements...
Shallow response. Seek to elevate the conversation. There are also people who see it for what it is, a useful tool but not intelligent...
And you presented no evidence at all. Not every comment I make is going to contain a full lit review.
> Both of you are able to drive a car, yet we need completely different AIs for such tasks.
This is like a bird complaining humans aren't intelligent because they can't fly. How is Gemini or o3 supposed to drive without real-time vision and a vehicle to control? How are you supposed to fly without wings?
It lacks the sensors and actuators to drive, but this is moving away from a discussion on intelligence. If you want to argue that any system lacking real-time vision isn't intelligent, you're just using a very unusual definition of intelligence that excludes blind people.
> Shallow response. Seek to elevate the conversation.
This was an ironic response pointing out the shallowness of your own unsubstantiated accusation that people just disagree with you because they're biased or deluded themselves. The next paragraph starting with "But really" was supposed to convey it wasn't serious, just a jab showing the silliness of your own jab.
Re:”traits we associate with general intelligence”, I think the exact issue is that there is no scientific (ie specific*consistent) list of such traits. This is why Turing wrote his famous 1950 paper and invoked the Imitation Game; not to detail how one could test for a computer that’s really thinking(/truly general), but to show why that question isn’t necessary in the first place.
Certainly creativity is missing, it has no internal motivation, and it will answer the same simple question both right and wrong, depending on unknown factors. What if we reverse the framing from "it can do these tasks, therefore it must be..." to "it lacks these traits, therefore it is not yet..."
While I do not disagree that the LLMs have become advanced enough to do a bunch of automation, I do not agree they are intelligent or actually thinking.
I'm with Yann Lecun when he says that we won't reach AGI until we move beyond transformers.
I'm guilty as charged of having looked at GPT 3.5 and having thought "it's meh", but more than anything this is showing that debating words rather than the underlying capabilities is an empty discussion.
Those are all different things with little to nothing to do with each other. It's like saying what if I ensemble a snake and cat ? What does that even mean ? GPT-N or whatever is a single model that can do many things, no ensembling required. That's the difference between it and a calculator or stockfish.
If you remove those tools, or cut its access to search databases, it becomes quite less capable.
A human would often still manage to do it without some data still, perhaps with less certainty, while GPT has more problems than that without others filling in the holes.
chatgpt no longer uses dalle for image generation. I don't understand your point about the tokenization. It doesn't make the model become an ensemble.
It's also just beside the point. Even if you restrict the modalities to text alone, these models are still general alone in ways a calculator is not.
Huh? Isn't a LLM's capability fully constrained by the training data? Everything else is hallucinated.
The quality of the LLM then becomes how often it produces useful information. That score has gone up a lot in the past 18 months.
(Sometimes hallucinations are what you want: "Tell me a fun story about a dog learning calculus" is a valid prompt which mostly isn't meant to produce real facts about the world")
That is according to one specific internal OpenAI benchmark, I don't know if it's been replicated externally yet.
In that sense, they absolutely know things that aren’t in their training data. You’re correct about factual knowledge, tho — that’s why they’re not trained to optimize it! A database(/pagerank?) solves that problem already.
All that said, I wonder if GPT4 had been integrated with the same tools, would it've been any less capable?
It sure could give you a search prompt for Google if you asked it to. Back then you had to copy and paste that search prompt yourself. Today o3 can do it on its own. Cool! Does it imply though o3 is any closer to AGI than GPT4?
Models gaining access to external tools, however impressive from all the applications standpoint, feels like lateral movement not a step towards the AGI.
On the other hand, a model remaining isolated in its sandbox while actually learning to reason about that puzzle (assuming it's not present in the training data) would give off that feeling the AGI vibes.
And that's when we return to a much older and much more important question than whether Super LLM 10.0 Ultra Plus is AGI or not: how much power should a person or group of people be allowed to have?
It’s obvious that currently none of the SOTA models can do such tasks, agentic or not. And therefore they are NOT AGI to me.
> It’s obvious that currently none of the SOTA models can do such tasks, agentic or not. And therefore they are NOT AGI to me.
I myself almost never do that (calling people when googling is possible). Guess I'm not general intelligence. :)
A strand of her hair fell on her shoulder, because she was moving continuously (like crazy) it was moving too in a perfectly believable way, and IT EVENTUALLY FELL OFF THE SHOULDER/SHIRT LIKE REAL HAIR and got mixed into other fallen hair. How is that generated? It's too small detail. Are there any artifacts on her side?
Edit: she has to be real. Her lip movements are definitely forced/edited though. It has to be a video recording of her talking. And then a tool/AI has modified her lips to match the voice. If you look at her face and hand movements, her shut lips seem forced.
Nah, having used HeyGen a bit, it's extremely clearly a HeyGen generation. There's a small number of movements and expressions that it continually uses (in forward and reverse).
Edit: I mean, to be clear, it is a real person, just like the author's video is. The way HeyGen works is you record a short clip of you saying some stuff and then you can generate long videos like these of you saying whatever you want. So the stuff you noticed does come from a real video of her, but it's not a real video that's lightly edited by AI, more like the AI has a bunch of clips it can continually mesh together while fixing up the mouth to continually generate video.
It’s bad luck for those of us who want to talk about how good or bad they are in general. Summary statistics aren’t going to tell us much more than a reasonable guess as to whether a new model is worth trying on a task we actually care about.
Although, I could be argued into calling what we have already ASI - take a human and Gemini 2.5, and put them through a barrage of omni-disciplinary questions and situations and problems. Gemini 2.5 will win, but not absolutely.
AGI (we have) ASI (we might have) AOI (Artificial Omniscient Intelligence, will hopefully take a while to get here)
Might as well call it “ultrathink”!
Except for writing a joke that will make you laugh, a poem that will make you cry, or a work of art that evokes deep introspection.
Intelligence is much deeper and more nuanced than answering questions of rote knowledge. LLMs are fantastic “reasoning engines”, but the soul is simply not there yet.
I asked GPT to do so and I chuckled out loud.
Until those capabilities are expanded for model self-improvement -- including being able to adapt its own infrastructure, code, storage, etc. -- then I think AGI/ASI are yet to be realized. My POV is SkyNet, Traveler's "The Director", Person of Interest's "The Machine" and "Samaritan." The ability to target a potentially inscrutable goal along with the self-agency to direct itself towards that is true "AGI" in my book. We have a lot of components that we can reason are necessary, but it is unclear to me that we get there in the next few months.
We may be going about it the wrong way entirely and need to backtrack and find a wholly new architecture, in which case current capabilities would predate AGI but not be precursors.
> A young boy who has been in a car accident is rushed to the emergency room. Upon seeing him, the surgeon says, "I can operate on this boy!" How is this possible?
But it didn't!
(o4-mini high thought for 52 seconds and even cheated and looked up the answer on Hacker News: https://chatgpt.com/share/68053c9a-51c0-8006-a7fc-75edb734c2...)
I don’t consider an AI that fails the surgery brain teaser in the article to be AGI, no matter how superhuman it is at other narrow tasks. It doesn’t satisfy the “G” part of AGI.
If you ask it a math question beyond average middle school level, it will have holes (mathematical errors or misleading) at least within a few follow up turns if not right away. And that’s without trying to fool it.
In ten+ years of Wolfram Alpha I’ve found one error (and that was with the help of o3-mini funnily enough).
I’m still on the stochastic parrots side, which is a useful tool in some occasions.
Most people have a rough idea of what AGI means, but we still haven't figured out an exact definition that lines up with reality. As we continue exploring the idea space, we'll keep figuring out which parameters place boundaries and requirements on what AGI means.
There's no reason to just accept an ancient definition from someone who was confused and didn't know any better at the time when they invented their definition. Older definitions were just shots in the dark that pointed in a general direction, but there's no guarantee that they would hit upon the exact destination.
"An AGI is a human-created system that demonstrates iteratively improving its own conceptual design without further human assistance".
Note that a "conceptual design" here does not include tweaking weights within an already-externally-established formula.
My reasoning is thus:
1. A system that is only capable of acting with human assistance cannot have its own intelligence disentangled from the humans'
2. A system that is only intelligent enough to solve problems that somehow exclude problems with itself is not "generally" intelligent
3. A system that can only generate a single round of improvements to its own designs has not demonstrated improvements to those designs, as if iteration N+1 were truly superior to iteration N, it would be able to produce iteration N+2
4. A system that is not capable of changing its own design is incapable of iterative improvement, as there is a maximum efficacy within any single framework
5. A system that could improve itself in theory and fails to do so in practice has not demonstrated intelligence
It's pretty clear that no current-day system has hit this milestone; if some program had, there would no longer be a need for continued investment in algorithms design (or computer science, or most of humanity...).
A program that randomly mutates its own code could self-improve in theory but fails to do so in practice.
I don't think these goalposts have moved in the past or need to move in the future. This is what it takes to cause the singularity. The movement recently has been people trying to sell something less than this as an AGI.
I feel this definition doesn't require a current LLM model to be able to change its own working but to be able to generate a guided next generation.
It's possible that LLMs can surpass human beings, purely because I believe we will inevitably be limited to short term storage constraints which LLMs will not. It will be a bandwidth vs througput question. An LLM will have a much larger although slightly slower store of knowledge than what human have. But will be much quicker than a human looking up and validating the data.
We aren't there yet.
Selling something that does not yet exist is an essential part of capitalism, which - according to the main thesis of philosophical Accelerationism - is (teleologically) identical to AI. [0] It's sometimes referred to as Hyperstition, i.e. fictions that make themselves real.
[0] https://retrochronic.com
> The brutal and bruising competition between the tech giants has left nothing but riches for the average consumer.
Capitalism has always been great at this: creating markets, growing them, producing new goods. It's widely acknowledged amongst people who actually seek to gain an understanding of Marxism, and don't just stay in the surface-level black-and-white "socialism and capitalism are opposites" discourse that's very common in the West, especially the USA, especially after the McCarthy's Red Scare.
The problem is what comes once the market is grown and the only way for owners keep profits growing is: 1. consolidating into monopolies or cartels, so competition doesn't get in the way of profits, 2. squeezing the working class, looking to pay less for more work, and/or 3. abusing the natural world, to extract more materials or energy for less money. This is evident in plenty of developed industries: from health care, to broadcasting, telecommunications, fashion, etc.
If we view Socialism for what it is, namely a system built to replace Capitalism's bad parts but keep its good parts, China's system, for example, starts to make more sense. Capitalism in a similar way was an evolution from Feudalism that replaced it's bad parts, to achieve greater liberty for everyone— liberty is very much lost as Feudalism matures, but great for society as a whole. Socialism is meant to be the similar, aiming to achieve greater equity, which it views as very much better for society as a whole.
I wonder how hard it is to objectively use information that is available online for 30 years? But the worst part is how it lies and pretends it knows what it’s talking about, and when you point it out it simply turns into another direction and starts lying again. Maybe the use case here is not the main focus of modern AI; maybe modern AI is about generating slop that does not require verification, because it’s “new” content. But to me it just sounds like believable slop, not AGI.
Gathering context for user request...
Context gathering - Attempting to answer question via LLM: Are there existing Conversation classes in the ecosystem this should extend? Context gathering - LLM provided answer: "No"
Context gathering - Attempting to answer question via LLM: How should model selection work when continuing a previous conversation? Context gathering - LLM answer was UNKNOWN, asking user. Asking user: How should model selection work when continuing a previous conversation?
Context gathering - received user response to question: "How should model selection work when continuing a previous conversation?"
Context gathering - finished processing all user questions Context gathering - processing command executions... Context gathering - executing command: sqlite3 $(find . -name llm_conversations.db) .tables
Context gathering - command execution completed
Context gathering - executing command: grep -r Conversation tests/
Context gathering - command execution completed
Context gathering - executing command: grep -h conversation_id *py Context gathering - command execution completed Context gathering - finished processing all commands Analyzing task complexity and requirements...
DEBUG: reasoning_model: openrouter/google/gemini-2.5-pro-preview-03-25 Task classified as coding (confidence: 1.0) Task difficulty score: 98.01339999999999/100 Selected primary reasoning model: claude-3.7-sonnet get_reasoning_assistance:[:214: integer expression expected: 98.01339999999999 Reasoning assistance completed in 39 seconds Calling LLM with model: claude-3.7-sonnet
While incredibly powerful and transformative, it is not 'intelligence'. LLMs are forever knowledgebase bound. They are encyclopedias with a fancy way of presenting information looked up in the encyclopedia.
The 'presentation' has no concept, awareness, or understanding of the information being presented - and never will. And this is the critical line. Without comprehension, a LLM is incapable of being creative. Of coming up with new ideas. It cannot ponder. Wonder. Think.
It is not a simple matter of patching the rough edges. We are fundamentally not using an architecture that is capable of intelligence.
Personally the first time I tried deep research on a real topic it was disastrously incorrect on a key point.
If you ask an intelligent being the same question they may occasionally change the precise words they use but their answer will be the same over and over.
Heck, I can't even get LLMs to be consistent about *their own capabilities*.
Bias disclaimer: I work at Google, but not on Gemini. If I ask Gemini to produce an SVG file, it will sometimes do so and sometimes say "sorry, I can't, I can only produce raster images". I cannot deterministically produce either behavior - it truly seems to vary randomly.
Ask me some question before bed and again after waking up, I'll probably answer it at night but in the morning tell you to sod off until I had coffee.
We're often explicitly adding in randomness to the results so it feels weird to then accuse them of not being intelligent after we deliberately force them off the path.
What does that even mean? Do you actually have any particular numeric test of intelligence that's somehow better than all the others?