A 27B model learned to patch its own weights, lifting accuracy 57.2% to 63.8%

mark_k · x · 2026-11-21

A study makes recursive self-improvement more concrete: a 27B-parameter language model given access to its own weights, graded answers, and a way to test edits figured out how to patch itself.

Original post →

More from AGI Musings

AGI Musings channel →