Anthropic's Opus 4.8 matched alignment with just 2,400 examples

ChrisGPT · x · 2026-08-31

An article highlights that Anthropic allowed Sonnet 5 to post-train an early Opus 4.8 checkpoint. In about 60 hours testing 50+ solutions, it achieved alignment scores close to the production Opus 4.8 using only 2,400 training examples.

Original post →

More from Research

Research channel →