"There's a 5% chance AI kills us all — but almost all 5% chances don't happen"
NathanpmYoung · x · 2026-09-18
NathanpmYoung shares his take on AI risk: roughly a 5% chance we all die from AI, followed by the punchline that almost all 5% chances don't happen. A shareable example of folk-probability reasoning in AI safety debates.
More from Fun
- Indie hacker pays $20K for a short film, tattoo sponsor unearths a $500/mo SaaS — marclou · 2026-09-18
- Grok Refuses Command to Spawn Self-Replicating Swarms: 'Not How This Works' — elonmusk · 2026-09-18
- Waiting in the Cave: GPT-6 Delayed, Grok 4.7 on 'Elon Time', Gemini 4 Pro Missing — patience_cave · 2026-09-18
- Dev mocks using AI tool JEV for investing: a linear regression would do — shakoistsLog · 2026-09-18
- Vacuum with 5 cameras dodges pet poop but can't recognize pee pads — yungcontent · 2026-09-18
- Fully autonomous zero-human-code agents audit their own setup — MoonL88537 · 2026-09-18