Safety researcher: models keep getting less monitorable and outsiders can't see inside labs
KelseyTuoc · x · 2026-10-13
In a debate with Rohit Krishnan, Kelsey Tuoc argues that models constantly get less monitorable, requiring a huge increase in monitoring just to maintain the same oversight level as the previous generation. She stresses that much of what happens inside labs isn't knowable from outside — nobody was sounding alarms in March because the information simply wasn't public. Models still train in isolation with limited, slow after-the-fact monitoring, and that hasn't stopped.
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