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

[Zaraif13]

How does it do on OSWorld-verified? Recently read that even Fable 5 is just at 85% .

[jgilias → Zaraif13]

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.