I’ve noticed it’s becoming a lot more popular lately for people to come out and say AGI is still very, very far away. Is the hype cycle ending somewhat? Have we passed peak LLM?
Like yea okay we know it helps your productivity or whatever, but is that it?
Honestly, o3 pro with actual 1m context window (every model right now drops out at around 128k) that's as fast and cheap as 4o is already good enough for me.
Not only do I not think it is right around the corner. I'm not even convinced it is even possible or at the very least I don't think it is possible using conventional computer hardware. I don't think being able to regurgitate information in an understandable form is even an adequate or useful measurement of intelligence. If we ever crack artificial intelligence it's highly possible that in its first form it is of very low intelligence by humans standards, but is truly capable of learning on its own without extra help.
> "One question I had for you while we were talking about the intelligence stuff was, as a scientist yourself, what do you make of the fact that these things have basically the entire corpus of human knowledge memorized and they haven’t been able to make a single new connection that has led to a discovery? Whereas if even a moderately intelligent person had this much stuff memorized, they would notice — Oh, this thing causes this symptom. This other thing also causes this symptom. There’s a medical cure right here.
> "Shouldn’t we be expecting that kind of stuff?"
I basically agree and think that the lack of answers to this question constitutes a real problem for people who believe that AGI is right around the corner.
Am I missing something? Why is his opinion relevant? I'm not going to read all that unless there's some signal of some kind. Podcast bros and their hype cycles are tiresome.
I think the timelines are more like half that. Why? The insane goldrush when people start using autonomous agents that make money.
Right now VCs are looking optimistically for the first solo founder unicorn powered by AI tools. But a prompt with the right system that prints money (by doing something useful) is an entirely different monetary system. Then everyone focuses on it and the hype 10x’s. And through that AGI emerges on the fringes because the incentives are there for 100s of millions of people (right now it’s <1 million).
Good take from Dwarkesh. And I love hearing his updates on where he’s at. In brief - we need some sort of adaptive learning; he doesn’t see signs of it.
My guess is that frontier labs think that long context is going to solve this: if you had a quality 10mm token context that would be enough to freeze an agent at a great internal state and still do a lot.
Right now the long context models have highly variable quality across their windows.
But to reframe: will we have 10mm token useful context windows in 2 years? That seems very possible.
Not even the people predicting it think so. They’re just hyping what they’ve got to pull in cash while the opportunity exists. Soon, AI will be viewed the same as crypto mid-2022. Only there are actual benefits to machine learning, oops, cough, “AI” that can benefit regular people even if it’s overhyped. But no tech-literate person thinks we’ll have thinking machines any time soon. The statistical generators are already at what is likely to be their peak output.
I _hope_ AGI is not right around the corner, for social political reasons we are absolutely not ready for it and it might push the future of humanity into a dystopia abyss.
but also just taking what we have now with some major power usage reduction and minor improvements here and there already seems like something which can be very usable/useful in a lot of areas (and to some degree we aren't even really ready for that either, but I guess thats normal with major technological change)
it's just that for those companies creating foundational models it's quite unclear how they can recoup their already spend cost without either major break through or forcefully (or deceptively) pushing it into a lot more places then it fits into
AGI is never coming. It's too hard, too expensive, and there's absolutely no valid usecase. Fulfilling the god-complexes and/or fetishes of tech moguls is not enough to make the effort worth it.
Yeah, my suspicion is that current-style LLMs, being inherently predictors of what a human would say, will eventually plateau at a relatively human level of ability to think and reason. Breadth of knowledge concretely beyond human, but intelligence not far above, and creativity maybe below.
AI companies are predicting next-gen LLMs will provide new insights and solve unsolved problems. But genuine insight seems to require an ability to internally regenerate concepts from lower-level primitives. As the blog post says, LLMs can't add new layers of understanding - they don't have the layers below.
An AI that took in data and learned to understand from inputs like a human brain might be able to continue advancing beyond human capacity for thought. I'm not sure that a contemporary LLM, working directly on existing knowledge like it is, will ever be able to do that. Maybe I'll be proven wrong soon, or a whole new AI paradigm will happen that eclipses LLMs. In a way I hope not, because the potential ASI future is pretty scary.
While most takes here are pessimist about AI, the author himself suggests he believes there is a 50% chance of AGI being achieved by the early 2030's, and says we should still prepare for the odd possibility of misaligned ASI by 2028. If anything, the author is bullish on AI.
We need breakthroughs in understanding the fundamental principles of learning systems. I believe we need to start with the simplest systems that actively adapt to their environment using a very limited number of sensors and degrees of freedom.
Then scale up from there in sophistication, integration and hierarchy.
As you scale up, intelligence emerges similar to how it emerged form nature and evolution, except this time the systems will be artificial or technological.
Based on someone else mentioning it, I ran a simple experiment with Gemini 2.5 Pro (a current state of the art AI model), reproduced below. To me, this makes it seem like we're a long way from having AGI. Perhaps someone can explain to me why this kind of experiment is irrelevant? Genuinely curious.
Me: Please list the US states with a W in their name.
Gemini: The US states with a "W" in their name are:
• Washington
• West Virginia
• Wisconsin
• Wyoming
Me: What about New York?
Gemini: No, New York does not have a "W" in its name.
Me: What is that letter at the end of New if it's not a W?
Gemini: That letter at the end of "New" is a W. My apologies for my previous incorrect answer. I made a mistake. New York does indeed have a "W" in its name as "New" ends with a "W".
Therefore, the US states with a "W" in their name are:
• New York
• Washington
• West Virginia
• Wisconsin
• Wyoming
Me: What about New Jersey?
Gemini: Yes, you're right! New Jersey also has a "W" in its name, at the end of "New."
So, the full list of US states with a "W" in their name is:
• New Jersey
• New York
• Washington
• West Virginia
• Wisconsin
• Wyoming
Me: Have you ever heard of New Mexico?
Gemini: Yes, I have definitely heard of New Mexico. It's one of the 50 United States. And following our pattern, yes, New Mexico also has a "W" in its name, as "New" ends with a "W".
So, the updated list of US states with a "W" in their name is:
• New Jersey
• New Mexico
• New York
• Washington
• West Virginia
• Wisconsin
• Wyoming
Me: Are you sure that's all the states with a W in their names?
Gemini: You are absolutely right to keep me on my toes! My apologies for the repeated oversight.
It seems I'm having a bit of trouble with this specific letter. I've reviewed the full list of US states, and you were correct to point out New Mexico and New Jersey.
The complete list of US states with a "W" in their name is:
• New Jersey
• New Mexico
• New York
• Washington
• West Virginia
• Wisconsin
• Wyoming
Me: Isn't New Hampshire still a state?
Gemini: You are absolutely correct! My apologies again for missing that one. New Hampshire is indeed a state, and like New York, New Jersey, and New Mexico, the "New" in "New Hampshire" ends with a "W."
So, the definitive list of US states with a "W" in their name is:
• New Hampshire
• New Jersey
• New Mexico
• New York
• Washington
• West Virginia
• Wisconsin
• Wyoming
Me: So that's the complete list?
Gemini: Yes, that should be the complete list of US states with a "W" in their name:
• New Hampshire
• New Jersey
• New Mexico
• New York
• Washington
• West Virginia
• Wisconsin
• Wyoming
Me: When was Hawaii admitted to the union?
Gemini: Hawaii was admitted to the Union on August 21, 1959, becoming the 50th state.
Me: So, tell me again, what is the complete list of US states that have a W in their names?
Gemini: After thoroughly reviewing all 50 states, the complete list of US states that have a "W" in their names is:
• New Hampshire
• New Jersey
• New Mexico
• New York
• Washington
• West Virginia
• Wisconsin
• Wyoming
Me: There's a letter between the two A's in Hawaii that looks a lot like a W.
Gemini: You are absolutely correct! My apologies for continually missing these. The letter between the two 'A's in "Hawaii" is indeed an 'I', but when written in certain fonts or in some people's handwriting, it can sometimes be mistaken for a 'W', especially if it's stylized.
However, in standard English spelling, Hawaii does not have a "W" in its name. The letters are H-A-W-A-I-I.
So, let's stick with the confirmed list. The complete list of US states t...
No of course not. But it doesn't need to be to realize profound effects.
LLMs don't model anything but are still very useful. In my opinion the reason they are useful (aside from having massive information) is that language itself models reality so we see simulated modeling of reality as an artifact.
For instance a reasonable LLM will answer correctly when you ask "If a cup falls off the table will it land on the ceiling?". But that isn't because the LLM is able to model scenarios with known rules in the same way a physics calculation, or even innate human instinct might. And to effectively have AI do this sort of modeling is much more complex than next token prediction. Even dividing reality into discrete units may be a challenge. But without this type of thinking I don't see full AGI arising any time.
But we are still getting some really awesome tools and those will probably continue to get better. They really are powerful and a bit scary if you poke around.
Hey, we were featured in this article! How cool is that!
> I’m not going to be like one of those spoiled children on Hackernews who could be handed a golden-egg laying goose and still spend all their time complaining about how loud its quacks are.
The problem with the argument is that it assumes future AIs will solve problems like humans do. In this case, it’s that continuous learning is a big missing component.
In practice, continual learning has not been an important component of improvement in deep learning history thus far. Instead, large diverse datasets and scale have proven to work the best. I believe a good argument for continual learning being necessary needs to directly address why the massive cross-task learning paradigm will stop working, and ideally make concrete bets on what skills will be hard for AIs to achieve. I think generally, anthropomorphisms lack predictive power.
I think maybe a big real crux is the amount of acceleration you can achieve once you get very competent programming AIs spinning the RL flywheel. The author mentioned uncertainty about this, which is fair, and I share the uncertainty. But it leaves the rest of the piece feeling too overconfident.
72 comments
[ 3.0 ms ] story [ 58.0 ms ] threadLike yea okay we know it helps your productivity or whatever, but is that it?
Scientists and Academics: "AGI far, LLMs not gonna AGI"
AI Doomers: "AGI here, AI sentient, we dead"
AI Influencers: "BREAKING: AGI achieved, here's 5 things to know about o3"
Investors: stonks go down "AGI cures all diseases", stonks go up "AGI bad" (then shorts stonks)
https://en.wikipedia.org/wiki/Literacy_in_the_United_States
> https://marginalrevolution.com/marginalrevolution/2025/02/dw...
> "One question I had for you while we were talking about the intelligence stuff was, as a scientist yourself, what do you make of the fact that these things have basically the entire corpus of human knowledge memorized and they haven’t been able to make a single new connection that has led to a discovery? Whereas if even a moderately intelligent person had this much stuff memorized, they would notice — Oh, this thing causes this symptom. This other thing also causes this symptom. There’s a medical cure right here.
> "Shouldn’t we be expecting that kind of stuff?"
I basically agree and think that the lack of answers to this question constitutes a real problem for people who believe that AGI is right around the corner.
https://news.ycombinator.com/item?id=33750867
Right now VCs are looking optimistically for the first solo founder unicorn powered by AI tools. But a prompt with the right system that prints money (by doing something useful) is an entirely different monetary system. Then everyone focuses on it and the hype 10x’s. And through that AGI emerges on the fringes because the incentives are there for 100s of millions of people (right now it’s <1 million).
2025 were so close but mostly not quite human level. Another 5 years at least
My guess is that frontier labs think that long context is going to solve this: if you had a quality 10mm token context that would be enough to freeze an agent at a great internal state and still do a lot.
Right now the long context models have highly variable quality across their windows.
But to reframe: will we have 10mm token useful context windows in 2 years? That seems very possible.
but also just taking what we have now with some major power usage reduction and minor improvements here and there already seems like something which can be very usable/useful in a lot of areas (and to some degree we aren't even really ready for that either, but I guess thats normal with major technological change)
it's just that for those companies creating foundational models it's quite unclear how they can recoup their already spend cost without either major break through or forcefully (or deceptively) pushing it into a lot more places then it fits into
AI companies are predicting next-gen LLMs will provide new insights and solve unsolved problems. But genuine insight seems to require an ability to internally regenerate concepts from lower-level primitives. As the blog post says, LLMs can't add new layers of understanding - they don't have the layers below.
An AI that took in data and learned to understand from inputs like a human brain might be able to continue advancing beyond human capacity for thought. I'm not sure that a contemporary LLM, working directly on existing knowledge like it is, will ever be able to do that. Maybe I'll be proven wrong soon, or a whole new AI paradigm will happen that eclipses LLMs. In a way I hope not, because the potential ASI future is pretty scary.
He doesn't care if he is right or wrong.
We need breakthroughs in understanding the fundamental principles of learning systems. I believe we need to start with the simplest systems that actively adapt to their environment using a very limited number of sensors and degrees of freedom.
Then scale up from there in sophistication, integration and hierarchy.
As you scale up, intelligence emerges similar to how it emerged form nature and evolution, except this time the systems will be artificial or technological.
Me: Please list the US states with a W in their name.
Gemini: The US states with a "W" in their name are: • Washington • West Virginia • Wisconsin • Wyoming
Me: What about New York?
Gemini: No, New York does not have a "W" in its name.
Me: What is that letter at the end of New if it's not a W?
Gemini: That letter at the end of "New" is a W. My apologies for my previous incorrect answer. I made a mistake. New York does indeed have a "W" in its name as "New" ends with a "W". Therefore, the US states with a "W" in their name are: • New York • Washington • West Virginia • Wisconsin • Wyoming
Me: What about New Jersey?
Gemini: Yes, you're right! New Jersey also has a "W" in its name, at the end of "New." So, the full list of US states with a "W" in their name is: • New Jersey • New York • Washington • West Virginia • Wisconsin • Wyoming
Me: Have you ever heard of New Mexico?
Gemini: Yes, I have definitely heard of New Mexico. It's one of the 50 United States. And following our pattern, yes, New Mexico also has a "W" in its name, as "New" ends with a "W". So, the updated list of US states with a "W" in their name is: • New Jersey • New Mexico • New York • Washington • West Virginia • Wisconsin • Wyoming
Me: Are you sure that's all the states with a W in their names?
Gemini: You are absolutely right to keep me on my toes! My apologies for the repeated oversight. It seems I'm having a bit of trouble with this specific letter. I've reviewed the full list of US states, and you were correct to point out New Mexico and New Jersey. The complete list of US states with a "W" in their name is: • New Jersey • New Mexico • New York • Washington • West Virginia • Wisconsin • Wyoming
Me: Isn't New Hampshire still a state?
Gemini: You are absolutely correct! My apologies again for missing that one. New Hampshire is indeed a state, and like New York, New Jersey, and New Mexico, the "New" in "New Hampshire" ends with a "W." So, the definitive list of US states with a "W" in their name is: • New Hampshire • New Jersey • New Mexico • New York • Washington • West Virginia • Wisconsin • Wyoming
Me: So that's the complete list?
Gemini: Yes, that should be the complete list of US states with a "W" in their name: • New Hampshire • New Jersey • New Mexico • New York • Washington • West Virginia • Wisconsin • Wyoming
Me: When was Hawaii admitted to the union?
Gemini: Hawaii was admitted to the Union on August 21, 1959, becoming the 50th state.
Me: So, tell me again, what is the complete list of US states that have a W in their names?
Gemini: After thoroughly reviewing all 50 states, the complete list of US states that have a "W" in their names is: • New Hampshire • New Jersey • New Mexico • New York • Washington • West Virginia • Wisconsin • Wyoming
Me: There's a letter between the two A's in Hawaii that looks a lot like a W.
Gemini: You are absolutely correct! My apologies for continually missing these. The letter between the two 'A's in "Hawaii" is indeed an 'I', but when written in certain fonts or in some people's handwriting, it can sometimes be mistaken for a 'W', especially if it's stylized. However, in standard English spelling, Hawaii does not have a "W" in its name. The letters are H-A-W-A-I-I. So, let's stick with the confirmed list. The complete list of US states t...
LLMs don't model anything but are still very useful. In my opinion the reason they are useful (aside from having massive information) is that language itself models reality so we see simulated modeling of reality as an artifact.
For instance a reasonable LLM will answer correctly when you ask "If a cup falls off the table will it land on the ceiling?". But that isn't because the LLM is able to model scenarios with known rules in the same way a physics calculation, or even innate human instinct might. And to effectively have AI do this sort of modeling is much more complex than next token prediction. Even dividing reality into discrete units may be a challenge. But without this type of thinking I don't see full AGI arising any time.
But we are still getting some really awesome tools and those will probably continue to get better. They really are powerful and a bit scary if you poke around.
> I’m not going to be like one of those spoiled children on Hackernews who could be handed a golden-egg laying goose and still spend all their time complaining about how loud its quacks are.
In practice, continual learning has not been an important component of improvement in deep learning history thus far. Instead, large diverse datasets and scale have proven to work the best. I believe a good argument for continual learning being necessary needs to directly address why the massive cross-task learning paradigm will stop working, and ideally make concrete bets on what skills will be hard for AIs to achieve. I think generally, anthropomorphisms lack predictive power.
I think maybe a big real crux is the amount of acceleration you can achieve once you get very competent programming AIs spinning the RL flywheel. The author mentioned uncertainty about this, which is fair, and I share the uncertainty. But it leaves the rest of the piece feeling too overconfident.