Thread

1. johnmlussier · 1790178328 · focus · HN ↗

   I am increasingly hesitant to use non-native harnesses - model providers are now starting to train their agents for use within the harness. An eval like terminal bench can only capture so much data. I don't want to have to assess each harness every model release to make sure it's working as well as it can.

   1. miroljub · 1790187126 · focus · HN ↗

      And yet, open harnesses works better and use less tokens than native harnesses trained to consume as much tokens as possible.

Unofficial Hacker News client; not affiliated with Y Combinator.