Author tries to articulate MIRI's AI safety disagreements it 'isn't good at stating'
EigenGender · x · 2026-10-29
Follow-up to the thread announcement: the author clarifies it doesn't represent his employer and admits MIRI isn't good at articulating these disagreements, so he'll do his best to lay out the EA-vs-MIRI AI safety cruxes.
Related event: Ex-MIRI Author Launches Thread on EA vs MIRI AI Safety Disagreements(2 posts)→
More from AGI Musings
- New paper: agentic economies for scientific discovery—allocating scarce experiment capacity — sebkrier · 2026-10-29
- AI audit of 138 economics papers finds 2,035 errors; 97% of directional errors inflate claims — eigenrobot · 2026-10-29
- 'MLEs get replaced first'? Engineer's agent confidently set the wrong env var — vboykis · 2026-10-29
- MIT Media Lab panel asks: can we have both AI agents and human agency? — patpat_mit · 2026-10-29
- PNAS study of 64,000 people in 64 countries: LLMs miss key differences in simulating happiness — patpat_mit · 2026-10-29
- Seroter's daily reading list: Gemini 4 Carbon, state of context engineering, agent-shaped judgment — rseroter · 2026-10-29