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 ….
Attention: 1 HN points · 0 HN comments. Engagement counts are shown as context. Ansar does not treat popularity as significance.
A launch is the first point at which a product can be evaluated.
Share of marketing vocabulary detected in the headline and summary.
Distinct kinds of checkable fact found: amounts, versions, measured changes.
These are Ansar’s estimates, not source claims. The summary was assembled from source text, not generated.
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 …
Full timeline