Re:An LLM Beat NetHack
by schnitzelstoat on Friday September 25, 2026 @06:29AM
(#49842573)
I'm surprised this didn't get more attention here.
[ Parent
| on HN ]
I know right? Nethack is notoriously hard for humans, and deep learning bots up to now have been pretty poor. It surprised me that a relatively simple harness with access to spoilers and source was sufficient for the system to ascend in only 3 attempts without lots of RL optimization. Astra must be a really powerful model. I wonder what the smallest model that can reliably ascend looks like.