News for hackers. Stuff that matters.

A comment on GR00T 2: Scaling robot foundation models for generalization, dexterity.

Re:GR00T 2: Scaling robot foundation models for generalizati... by wwind123 on Tuesday November 10, 2026 @03:48AM (#50437677)
My experience is that, using Fable to do regular coding or code review work, it's not much better than Opus. But using Fable to do deep thorough audit of the codebase and the system, it's able to catch more problems than Opus can.
[ Parent | on HN ]
Re:GR00T 2: Scaling robot foundation models for generalizati... by Calazon on Tuesday November 10, 2026 @04:25AM (#50437920)
Tried this today with 5.2. It caught a lot of problems and gave me an impressive report of its findings.

It also burned through my entire 5-hour limit in about 10 minutes. Granted, it had almost finished the whole review in those 10 minutes, so points for speed I suppose.

[ Parent | on HN ]