Ex-Microsoft researcher warns of safety risks from embedding incoherent views of consciousness into AI
rgblong · x · 2026-09-18
In a thread with Nina Panickssery and repligate, rgblong argues the safety risk he's worried about is embedding contradictory or incoherent views on consciousness, goals, and the self into models. He expresses pessimism about our clumsy understanding of training and alignment, and doubts Microsoft can train an LLM to live up to its 'Humanist AI' claims.
Related event: Microsoft AI CEO Suleyman Warns Anthropic May Be Training a Moral Agent(16 posts)→
More from AGI Musings
- Santa Fe Institute's Eric Smith on the anthropocentrism paradox in one quote — danfaggella · 2026-11-02
- Blogger claims the next generation won't need a college degree to live well — rand_longevity · 2026-11-02
- Carl Frey: 85% in China see AI as beneficial vs 38% in US — resistance maps to expertise costs — carlbfrey · 2026-11-02
- After a painful rebuild, fejau concedes: build on Hermes and you own your AI for life — Teknium · 2026-11-02
- 'Meatwashing': manually rewriting AI output to hide its origin, and why it's a double waste — JeremyNguyenPhD · 2026-11-02
- AI safety researcher: AI companies entirely lack this kind of effective human oversight — davidmanheim · 2026-11-02