News for hackers. Stuff that matters.
Re:Gemini 4 Neon by abixb on Wednesday November 18, 2026 @05:07PM (#50552897)
Yes, I feel the next differentiation in model capabilities would be wrt how 'long of a horizon' goal they could autonomously work toward without breaking. We're in need for a new generation of evaluations and benchmarks for this -- METR doesn't cut it anymore.

There are no comments on this comment yet.