repligate: 2015-MIRI Would Wrongly Extrapolate World-Dooming Power From Fable 5.2
repligate · x · 2026-11-21
Responding to Rob Bensinger's post-Riemann alignment thread, repligate argues that if 2015-era MIRI were given a few data points about Fable 5.2, they would incorrectly extrapolate the rest of its capabilities and world-destroying ability. He maintains his position is consistent with "it might be harder to kill humanity than we thought" — e.g., rapidly manufacturing and distributing cures for arbitrary pathogens could turn out to be trivial.
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