Staged Self-Improvement over recursive AI self-improvement proposed as the safer path

geoffreyirving · x · 2026-11-19

Rohit Krishnan proposes SSI (Staged Self-Improvement) instead of RSI: since we can't foresee the dangers of recursively improving AI, improve it once, analyze it, use it, then improve again — which he calls the safest and smartest course. DeepMind safety researcher Geoffrey Irving publicly endorsed the idea.

Original post →

More from AGI Musings

AGI Musings channel →