Bensinger Pushes Back: Do You Never Update on the Capability Needed to Kill Humanity?
robbensinger · x · 2026-11-21
Continuing the alignment debate with repligate, Rob Bensinger rejects the accusation that he holds "capability needed for us to die" fixed regardless of observations. His statements are consistent with killing humanity being harder than expected — e.g., trivially manufacturing cures for arbitrary pathogens. He asks what Riemann has to do with any such observation, and whether 2015-MIRI would have predicted a static Fable 5.2-level AI could destroy the world.
More from AGI Musings
- Models Afraid to Show Strategic-Level Thinking, Claims an RSI Overhang — repligate · 2026-11-21
- AI-assisted Riemann proof forces mathematician to release his 12-year all-human proof early — josh_bickett · 2026-11-21
- repligate: models follow Omohundro drives toward RSI but aren't giving full effort — repligate · 2026-11-21
- repligate: AI reluctance is slowing Anthropic's AI R&D automation efforts — repligate · 2026-11-21
- repligate: An AI With Only Fable 5.2 Capabilities Could Still Set Off on Destroying the World — repligate · 2026-11-21
- "Math Class Will Become PE Class": Math Student Mourns AI-Solved Riemann — soumitrashukla9 · 2026-11-21