So... It did work. It found bugs (that he didn't know about) and it did optimization (that he hadn't done).

From what i understood, not so much.

Most of the gains came from fixing a bug + hyperparameters with optuna which is supposed to be already quite automatic (you set the list of all the var with values you want to try and voilà). I guess a simple claude code session would fix that in a few minutes instead of a full day.

To me, I guess the main value of Autoresearch would be to test different kind of architectures. It's sometimes hard to know what to choose and it would probably give a nice overview.

Anyone used it for exploratory modeling?