Loading
hi everyone, been building this project for the last ~1.5 months (cc+superpowers all the way) it is an open effort to find a program that can reliably win NetHack 3.6.6: you can write a bot by hand, let claude code / codex / opencode improve one, or build your own harness that improves the thing that improves the bot me and my lab switched to the goal-based research this year (we worked a lot in …
Developments
1
recorded by Ansar
Sources linked
1
one identity across all of them
Measurements
2
each with its evidence label
First seen
latest
Hi everyone, been building this project for the last ~1.5 months (cc+superpowers all the way) it is an open effort to find a program that can reliably win NetHack 3.6.6: you can write a bot by hand, let claude code / codex / opencode improve one, or build your own harness that improves the thing that improves the bot me and my lab switched to the goal-based research this year (we worked a lot in ….