All of ws27a's Comments + Replies

ws27a10

I agree that it's capable of doing that, but it just doesn't do it. If you ask it to multiply a large number, it confidently gives you some incorrect answer a lot of the time instead of using it's incredible coding skills to just calculate the answer. If it was trained via reinforcement learning to maximize a more global and sophisticated goal than merely predicting the next word correctly or avoiding linguistic outputs that some humans have labelled as good or bad, it's very possible it would go ahead and invent these tools and start using them, simply be... (read more)

ws27a11

I agree with you, but natural intelligence seems to be set up in a way so as to incentivise the construction of subroutines and algorithms that can help solve problems, at least among humans. What I mean is that we humans invented a calculator when we realised our brains are not very good at arithmetics, and now we have this device which is sort of like a technological extension of ourselves. A proper AGI implemented in computer hardware should absolutely be able to implement a calculator by its own determination, the fact that it doesn't speaks to the ill... (read more)

2Neel Nanda
Idk, I feel like GPT4 is capable of tool use, and also capable of writing enough code to make its own tools.
ws27a10

I am happy to consider a distinction between world models and n-gram models, I just still feel like there is a continuum of some sort if we look closely enough. n-gram models are sort of like networks with very few parameters. As we add more parameters to calculate the eventual probability in the softmax layer, at which point do the world models emerge. And when do we term them world models exactly. But I think we're on the same page with regards to the chess example. Your formulation of "GPT-4 does not care about learning chess" is spot on. And in my view that's the problem with GPT in general. All it really cares about is predicting words.

1mgm452
Agree with ws27a that it's hard to pick a certain point in the evolution of models and state they now have a world model. But I think the focus on world models is missing the point somewhat. It makes much more sense to define understanding as the ability to predict what happens next than to define it as compression which is just an artifact of data/model limitations. In that sense, validation error for prediction "is all you need." Relatedly, I don't get why we want to "incentivise building robust internal algorithms and world models" -- if we formulate a goal-based objective instead of prediction, a model is still going to find the best way of solving the problem given its size and will compromise on world model representation if that helps to get closer to the goal. Natural intelligence does very much the same...
ws27a10

I think if we imagine an n-gram model where n approaches infinity and the size of the corpus we train on approaches infinity, such a model is capable of going beyond even GPT. Of course it's unrealistic, but my point simply is that surface level statistics in principle is enough to imitate intelligence the way ChatGPT does. 

Of course, literally storing probabilities of n-grams is a super poorly compressed way of doing things, and ChatGPT clearly finds more efficient solutions as it moves through the loss landscape trying to minimize next token predict... (read more)

2Neel Nanda
Sure, in a Chinese room style fashion, but IMO reasoning + internal models have significantly different generalisation properties, and also are what actually happen in practice in models rather than an enormous table of N-Grams. And I think "sufficient diversity of training data" seems a strongg assumption, esp for much of what GPT-4 et al are used for. More broadly, I think that world models are qualitatively different from N-Grams and there is a real distinction, even for a janky and crappy world model. The key difference is generalisation properties and the internal cognition - real algorithms are just very different from a massive lookup table! (unrelatedly, I think that GPT-4 just really does not care about learning chess, so of course it's bad at it! The loss benefit is tiny)
ws27a10

I don't understand why Eliezer changed his perspective about the current approach of Transformer next-token prediction not being the path towards AGI. It should not be surprising that newer versions of GPT will asymptotically approach (mimicry) of AGI, but that shouldn't convince anyone that they are going to break through that barrier without a change in paradigm. All the intelligent organisms we know of do not have imitation as their primary optimization objective - their objective function is basically to survive or avoid pain. As a result, they of cour... (read more)

3rotatingpaguro
Ilya Sutskever says something about this in an interview: https://www.youtube.com/watch?v=Yf1o0TQzry8 My recall: optimization on predicting the next token finds intelligent schemes that can be coordinated to go further than the humans that produced the tokens in the first place. Think about GPT-n being at least as smart and knowledgeable as the best human in every specialized domain, and then the combination of all this abilities at once allowing it to go further than any single human or coordinated group of humans.
ws27aΩ-111

Nice work. But I wonder why people are so surprised that these models and GPT would learn a model of the world. Of course they learn a model of the world. Even the skip-gram and CBOW word vectors people trained ages ago modelled the world, in the sense that for example named entities in vector space would be highly correlated with actual spatial/geographical maps. It should be 100% assumed that these models which have many orders of magnitude more parameters are learning much more sophisticated models of the world. What that tells us about their "intellige... (read more)

6Neel Nanda
I tried to be explicit in the post that I don't personally care all that much about the world model angle - Othello-GPT clearly does form a world model, it's very clear evidence that this is possible. Whether it happens in practice is a whole other question, but it clearly does happen a bit. I think this undersells it. World models are fundamentally different from surface level statistics, I would argue - a world model is an actual algorithm, with causal links and moving parts. Analogous to how an induction head is a real algorithm (given a token A, search the context for previous occurences of A, and predict that the next token then will come next now), while something that memorises a ton of bigrams such that it can predict B after A is not.