Blanche Minerva: trendy AGI-safety discourse is hype with no connection to reality
BlancheMinerva · x · 2026-10-16
In a follow-up, Blanche Minerva adds: if you've seen the "interpretability/alignment is solved" or "GLM terrifying behavior" discourses and gotten excited or fearful — the good news is it's not true; the bad news is that what's trendy in the AGI-safety and adjacent interp community is overwhelmingly driven by hype disconnected from reality.
More from AGI Musings
- Nature paper uses language models to map single neurons behind human language — raphaelmilliere · 2026-10-16
- 3SUM record falls to O(n^1.921), Lean-verified — but will it yield usable algorithms? — iskander · 2026-10-16
- Terence Tao predicted AI would be a mathematician's copilot in 3 years — reality outran him — abhishekcode42 · 2026-10-16
- Experts Across Fields Estimate 1-16% AI Catastrophe Risk by 2100, Survey Shows — ben_j_todd · 2026-10-16
- Experts put global AI catastrophe risk before 2100 at 5%, LEAP survey finds — ben_j_todd · 2026-10-16
- FRI survey: experts across fields estimate 1-16% chance of AI catastrophe by 2100 — ben_j_todd · 2026-10-16