but the experiments it did that "improved" validation BPB in the GH screenshot were all basically hyperparameter changes right? So is this better or worse, either per experiment or per unit time, than hyperparameter tuning techniques that don't involve an LLM? It's not clear from this if the LLM is more or less making random changes which sometimes work , and or the LLM thinking actually finds "good" changes because of what the LLM has internalized. E.g. how does this compare to a hyperparameter tuning pass with e.g. BayesOpt that does the same number of 5-min training experiments?

▲

karpathy 8 hours ago | parent [-]

this is very far from hyperparameter tuning in at least three important ways:

- it can modify code arbitrarily, the notion of a "hyperparameter" dissolves

- there is no need to run "sweeps" - this is the standard parallel process that wastes compute. because LLM agents are sequential, they can do more efficient versions such as binary search to narrow in on the right setting very quickly (usually many parameters will have a U shaped optimal setting).

- it's fully automatic, it doesn't require human in the loop to mess with the code.

You're right that many of the changes it seems to make out of the box (as I intentionally did not try to prompt engineer it too hard yet because I was curious what you get by default) seem to be tuning existing hyperparameters. not all of the changes are like that - e.g. it tried to replace the non-linearity, etc. I will say that overall (and again, out of the box) the LLM feels unwilling to creatively pursue a research direction or something like that. The models feel very "cagy" and "scared" when they are given problems that are a little too open ended. But that's just where the fun parts, e.g. I had some early successes with the idea of a "chief scientist" that was basically a never-ending plan mode that looked at what worked, didn't work, tried to find related code/papers, and created a long list of experiments to try, which it could then send to junior engineers running in tmux sessions. I think quite a few approaches are possible, so I think it's a nice canvas. The reason we're not getting "novel research" feels like half capability issue and half skill issue.

▲

vessenes 6 hours ago | parent | next [-]

On the skill side, personalities could be fun:

"You are Yann Lecun's last PhD candidate, and he hates you and you hate JEPA. You are determined to prove that a non-world model can reach AGI. In order to get your PhD you have to be creative and come up with new ideas. Remember without it, you're stuck."

▲

categoricalrift 4 hours ago | parent | prev [-]

How about the very last "Kept Improvement" in the plot? It's titled "random seed 42 -> 137". I do think this project is quite conceptually interesting, but the model literally choosing a different random seed to achieve lower loss feels pretty far removed from the flowery sci-fi writing at the top of the readme.

	▲	eternauta3k 2 hours ago \| parent \| next [-]
		It shows that both Karpathy and the LLM have good taste in random seeds: the answer to life, the universe and everything, and ~1/(the fine structure constant)
	▲	aix1 3 hours ago \| parent \| prev [-]
		The 42 -> 137 also jumped out at me. On the face of it, the associated improvement sure does sound like overfitting to the eval set.