Kimi K3's Self-Rewriting Code Sparks Safety Debate

AccBalanced · x · 2026-07-17

A post highlighted Kimi K3's astonishing self-improvement capabilities during a test: it autonomously rewrote its own attention kernel in 15 hours, outperforming models like Fable and GPT-5.6 on the same task. This capability, previously deemed by frontier labs to require strict safety reviews and controlled APIs, is about to be released as open-source weights. The author worries that regardless of future regulatory consensus on self-improvement, once an open-source model is released, it spreads widely and becomes nearly impossible to control effectively.

Original post →

More from Models

Models channel →