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.
More from AGI Musings
- Chicago Study: More Reasoning Effort Makes LLM Shopping Agents Confident, Not Correct — Uchicago · 2026-11-19
- Amodei: 50% of entry-level white-collar jobs disrupted in 1-5 years, advice is learn to use AI — alvelda · 2026-11-19
- CVPR author: using LLMs for paper storytelling polish costs more than writing by hand — AntonObukhov1 · 2026-11-19
- "Don't confuse mimicry with intelligence": the LLM smartness debate resurfaces — AlexTensor · 2026-11-19
- austinhuang: think pieces about AI's future start from tooth-fairy narratives of the present — austinvhuang · 2026-11-19
- Should the METR Report Move Your AGI Timeline? A Pushback on Over-Updating — sayashk · 2026-11-19