[highfrequency]

Unless I'm missing something, this argument seems to apply only to the original pretraining era (eg GPT 1-4). The post-training and reinforcement learning paradigms are clearly doing variation, evaluation and selective retention no?

[kibibu]

The transcript does seem to overlook post-training steps like Reinforcement Learning with Verifiable Rewards (RLVR) (but I'll certainly won't claim that Rich Sutton is unaware of such things; RLVR has a very narrow set of evaluation approaches).

I wonder if this is a precursor to Keen Tech leaning into David Silver's Ineffable Intelligence approach.

[LarsDu88]

This was exactly what I was thinking of. RLVR is the secret sauce behind o3 and its many successors.

Its the secret sauce behind why the current models are so great at coding and soon to be unbeatable at math.

LLMs can pose many questions and if they are easily verifiable, fine tune very heavily. A lot of the world models discussion will inevitable lean into simulations as verification.

[code_biologist]

I'll admit that I miss having access to the ChatGPT 4.5 "absolutely gigantic model" with enough tuning to make it sane and useful. The RLVR models are superb for actual tasks in those RLVR domains, but that fine tuned view of the world as a verifiable problem to solve makes them feel worse for touchy feely stuff. Even for medical consultation and diagnosis, RLVR model's urge to reach a conclusion often is a liability.

[ACCount37]

Fable 5/Mythos 5 is the next "big chungus LLM".

It's RLVR tuned, but not to the ChatGPT level of brain damage, and it's still backed by a fuck off huge pool of model weights - which matters for what you call "touchy feely stuff".

[porridgeraisin]

RLVR still does not expand beyond the base distribution though, it only mode-seeks within it.

i.e, evaluation, retention yes. variation or "planning" no.

That is not to say you cannot use LLMs. Alpha evolve does exactly that. It uses an external simple evolutionary planner though. The overarching point he's making is that our planner is still "dumb" and we need to work on it.

When you iteratively guide an LLM in claude code, you are the external planner. That also works.

[highfrequency]

> RLVR still does not expand beyond the base distribution though, it only mode-seeks within it.

Seems clearly false. Pretraining finds the mean/mode of the data distribution. RL can easily generate many samples around that mode, evaluate them on an external source of truth (eg compile the code and run it) and then selectively train on the good samples. This clearly can go beyond the initial data distribution.

[porridgeraisin]

by base distribution, I meant the base model's output distribution

[highfrequency]

The model’s distribution will certainly change from the base model’s output distribution during reinforcement learning, shifting toward outputs that score well on an external evaluation. This is very different from mode-seeking. Am I missing something?

[porridgeraisin]

Mode-seeking is describing the way in which the distribution changes. RL is capable of picking out slightly lower probability trajectories and moving them toward the top of the distribution. However, exploration is fundamentally limited by the base policy itself. If a trajectory has near-zero probability under the original model, RLVR is unlikely to discover it because it must first be sampled before it can be rewarded. External search/planning methods such as MCTS or evolutionary search are useful precisely because they can explore candidate trajectories beyond what the policy would ordinarily generate. This is also not theoretical, GRPO style methods are shown to mostly improve `maj@k` and `pass@1` evals while not so much `pass@k` especially for high k, meaning it mostly sharpening the top of the distribution.

I'm not saying this makes it useless - it clearly helps for math and coding tasks. But the ceiling exists and that's what the original tweet was referring to. Alpha evolve also shows what lies beyond the ceiling, altho their planner was rudimentary.

[highfrequency]

Sure, but I'd say that moving desirable trajectories from very low probability to high probability is characteristic of genuine human learning and discovery. Technically, quantum gravity, a bestselling novel, or a yet undiscovered proof of the Riemann Hypothesis is "in my distribution", but when we are talking about a long chain of unlikely token completions (with multiplicative probabilities), whether that trajectory lives in the tail of the distribution vs. in the mode makes all the difference.

Would you agree that it is a matter of degrees rather than a qualitative distinction? There seems to be a broad misconception in Sutton and others that output quality cannot exceed that of the base internet distribution; my point is that RL allows you to easily produce an output distribution that is better than whatever data you trained on according to some evaluation criteria. There are no clear theoretical limits on how much better it can get, rather there are many people asserting guesses that there is an upper bound and it lives below "human creativity." I just haven't seen any solid theoretical argument, and the empirical evidence has so far shown continual improvement.

Also, I would be keen to look at any sources you have of pass@k not improving much during GRPO.