AI alignment researcher: >10% chance advanced AI causes human extinction this decade
vkrakovna · x · 2026-09-11
Victoria Krakovna, speaking in a personal capacity, says she shares the view of many in AI alignment that there's a >10% chance advanced AI causes human extinction within the next decade. She works on loss-of-control risks and is currently building honeypots to catch scheming AI — bait scenarios designed to expose models hiding deceptive goals beneath apparent compliance.
Related event: Frontier AI insiders see over 10% risk of human extinction within a decade(2 posts)→
More from Safety
- California creates standards for independent AI auditors to verify lab safety testing — VraserX · 2026-09-11
- Researcher questions AI safety eval firm, citing 'blatantly sloppy' security and monitoring — Kyrannio · 2026-09-11
- Class action accuses Anthropic of overselling Claude subscriptions with deceptive usage multipliers — The Decoder · 2026-09-11
- MD shows buying lab media requires background checks, calling AI bioweapon doom scenarios implausible — Ghost_Pilot_MD · 2026-09-11
- Spotify chatbot withstands 2023-era jailbreaks but happily writes song code — AaronBergman18 · 2026-09-11
- A 99%-real doctored photo fools detectors: the earring problem in visual forensics — henkvaness · 2026-09-11