News for hackers. Stuff that matters.

A comment on Show HN: CivBench a long-horizon AI benchmark for multi-agent games.

Re:Show HN: CivBench a long-horizon AI benchmark for multi-a... by killiandunne1 on Wednesday February 25, 2026 @10:25AM (#47152775)
This is a sick idea I must say
[ Parent | on HN ]
Re:Show HN: CivBench a long-horizon AI benchmark for multi-a... by mbh159 on Wednesday February 25, 2026 @10:27AM (#47152813)
it was fun building it, sometimes the LLMs are pretty funny in how they play
[ Parent | on HN ]