Frontier AI outgrows the convex hull view: harnesses extend inference limits

gerardsans · x · 2026-11-22

Gerard Sans argues that the "convex hull" framing is inaccurate for frontier AI systems today. These models are part of larger systems where harnesses introduce complex algorithms and verification workflows, extending beyond the usual view of inference limits. He made the point while responding to Eric Weinstein and J.D. Lichtman.

Original post →

More from AGI Musings

AGI Musings channel →