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. crossroadsguy · 1790187119 · focus · HN ↗

      I mostly use GLM. But I will not touch ZAI's harness with a 10 mile long pole no matter how efficiently they couple it with GLM.

      1. UncleOxidant · 1790188124 · focus · HN ↗

         Is your main concern privacy? I've been using the zcode of and on for a few months now and it's definitely improved over what it was back in the spring. I also use DeepSeek's harness. Not sure which I prefer at this point. Used to be I preferred DSH, but zcode has some features I like over DSH.

         1. mongrelion · 1790190257 · focus · HN ↗

            Did you miss the whole fiasco from last week?

            1. UncleOxidant · 1790199013 · focus · HN ↗

               It's why I asked if your main concern was privacy (data leakage). They open-sourced their harness this week so you can always audit it.

Unofficial Hacker News client; not affiliated with Y Combinator.