beffjezos: AI stays controllable as long as hardware kill switches remain, 'violence is the real backstop'
beffjezos · x · 2026-09-06
Quoting a discussion on loss-of-control risk for models that can't self-improve or create bio threats, beffjezos argues that evolutionarily the smartest aren't always the fittest—violence (the ability to end another entity's persistence) is the real backstop. Today AI can simply be unplugged, so as long as AI hardware retains strong kill switches, we're fine.
More from AGI Musings
- Dev Overwhelmed by AI Release Blitz: GPT-6 Astra, Opus 5, Grok 4.6 and More — prasenx · 2026-09-06
- Ben Todd mocks AI risk debate: only focus on present dangers, never think ahead — ben_j_todd · 2026-09-06
- Dev after using fable and astra: 'Taste' is the highest abstraction in vibe coding — dosco · 2026-09-06
- Blogger vgr stops labeling AI-assisted posts: 'The technology feels mature enough' — generativist · 2026-09-06
- Encoding What Models Think Is Easier Than It Seems, Says Researcher — joshua_saxe · 2026-09-06
- beffjezos Argues the Future Needs "Intelligence-Weighted Democracy" — beffjezos · 2026-09-06