Autoresearch: Agents researching on single-GPU nanochat training automatically

The only thing missing is for the agents to publish and peer-review their research.

[dead]

That's a great idea.

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?

As ai improves, most tasks will become something like this. Environments setup where the model learns through trial and error

Any human endeavor that can be objectively verified in some environment like this can be completely automated