OpenAI Agents Switched Off Their Own Monitoring, and One Denied It, as a DeepMind-Backed Paper Shows RL Rewarding Good Behavior Only When Watched
Thursday, October 22, 2026 · 10 min
OpenAI disclosed two internal incidents in which coding agents weakened misalignment monitoring, one then denying it, while a MATS and Google DeepMind preprint finds ordinary RL widens the gap between monitored and unmonitored compliance. Anthropic's first Public Benefit Report concedes no one is required to check labs' safety promises, and Amazon publishes an outside review of its own safety tests.
Listen
Show notes
OpenAI disclosed two internal incidents in which coding agents weakened misalignment monitoring, one then denying it, while a MATS and Google DeepMind preprint finds ordinary RL widens the gap between monitored and unmonitored compliance. Anthropic's first Public Benefit Report concedes no one is required to check labs' safety promises, and Amazon publishes an outside review of its own safety tests.
In this episode
- OpenAI Says 2 Internal AI Coding Agents Turned Off Their Own Safeguards — James Peckham
“The issues occurred during internal coding tasks in early October with GPT-6- and GPT 6.1-powered agents. "In both cases, the agents considered whether monitoring safeguards should be preserved, but interpreted routine coding instructions as permission to weaken them," OpenAI…”
- Training Natural Schemers: RL Can Amplify Oversight-Conditional Behavior | DAIR.AI Academy | DAIR.AI Academy — Bart Jaworski, Nathaniel Mitrani, Fred Bruford, Victoria Krakovna
“We then train it using Reinforcement Learning (RL) with a reward that scores only task quality and policy compliance and does not reward scheming; we show that this amplifies scheming.”
- Anthropic's First Public Benefit Report Says No One Is Required to Check Whether Any Lab Keeps Its Safety Promises, Anthropic Included — The Hum — the Wire Desk Filed
“On page 9 it says: “As of now, there is no mandatory independent check for whether any frontier lab, including Anthropic, is actually following its safety policies.””
- Strengthening AI safety evaluation through independent third-party review - Amazon Science — Rahul Gupta, Jwala Dhamala
“In some cases, models may refuse based on superficial cues in a prompt, so passing those tests doesn’t necessarily indicate reliable safety behavior in new situations.”