‹ BackHN Continuity

Thread

Typesafe-computer-use drives a Mac toward a goal for 1/50th of a cent per step

82 points · 60 comments · rahimnathwani

  1. Zaraif13 · · focus · HN ↗
    How does it do on OSWorld-verified? Recently read that even Fable 5 is just at 85% .
    1. jgilias · · focus · HN ↗
      This probably throws a spanner in the wheels there:

      > Every piece of reasoning the frontier model does for free has to be rebuilt here as deterministic state.

      EDIT: Not to shit on this though. I totally believe that some smart mixture of LLM-reasoning + Jev-style + determinism is going to be pretty amazing.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.