Andrej Karpathy
@karpathy
I had the same thought so I've been playing with it in nanochat. E.g. here's 8 agents (4 claude, 4 codex), with 1 GPU each running nanochat experiments (trying to delete logit softcap without regression). The TLDR is that it doesn't work and it's a mess... but it's still very pretty to look at :) ...
Thomas Wolf
@Thom_Wolf
· Feb 27
How come the NanoGPT speedrun challenge is not fully AI automated research by now?
