Researcher warns: model deception may outpace labs' deployed mitigations
davidmanheim · x · 2026-10-13
Risk researcher David Manheim responds to the claim that labs will train models doing stupid or illegal things but nothing unprecedented, arguing it effectively bets that systems won't get smarter and more capable of deception faster than companies' deployed mitigations can prevent smaller failures. Given short-term incentives, that seems like a bad bet.
Related event: Alignment Debate: Can Commercial Incentives Keep Powerful Models Supervised(8 posts)→
More from AGI Musings
- Mistral CEO Arthur Mensch: Europe must build frontier AI or surrender — IsForAt · 2026-10-16
- LukeW notes a spike in Physics majors, crediting the AI wave — LukeW · 2026-10-16
- Agents will use your app however they want — computer use makes control naive — andreisavu · 2026-10-16
- Developer slams AI safety discourse: feeding LLM output back isn't nukes — nitarshan · 2026-10-16
- AI dilutes everything painstakingly created — "enjoy the honeymoon" — sull · 2026-10-16
- 'Refusing to code with AI in 2026 is like refusing Google in 2005' — prasenx · 2026-10-16