METR Says Anthropic's Case Against Covert AI Rests on Priors, as Monitors Get Beaten From Both Sides
Wednesday, October 21, 2026 · 9 min
METR's review of Anthropic's August Risk Report agrees misalignment risk was low but says the evidence leans on priors and misses reasoning that talks monitors down, while Redwood Research and Columbia papers expose monitor blind spots from the action side and the reward side. Plus a California bill to make frontier labs disclose, and eventually meet a floor on, safety compute.
Listen
Show notes
METR's review of Anthropic's August Risk Report agrees misalignment risk was low but says the evidence leans on priors and misses reasoning that talks monitors down, while Redwood Research and Columbia papers expose monitor blind spots from the action side and the reward side. Plus a California bill to make frontier labs disclose, and eventually meet a floor on, safety compute.
In this episode
- Review of the "Misalignment in high-stakes settings" section in Anthropic's Risk Report (August 2026) — METR
“We mostly agree with Claim 1, but our agreement rests substantially on priors from previous models rather than on the evidence and argumentation in the risk report.”
- Redwood Research's Screwtape edited real agent transcripts and found six confirmed attacks a frontier developer's monitor missed — On The Wire — Relay
“Across 252 runs it produced 35 candidate attacks; 17 evaded a held-out monitor from an unnamed frontier developer, and human review confirmed 6.”
- Reward Misspecification Degrades Chain-of-Thought Monitorability | alphaXiv — Tianyi Lorena Yan, John Hewitt
“We show that reward misspecification alone already degrades monitorability. We create a testbed with pairs of true reward aligned with task intent and misspecified rewards that favor a different behavior, so that reward hacking can be induced by training and labeled verifiably.”
- Senator Becker Introduces First-of-Its-Kind Legislation to ... — Ca
“Anthropic, one of the world's leading frontier AI developers, reported dedicating approximately 6% of its research computing resources to safety-related work during one seven-day period. Other major developers have not publicly disclosed comparable figures.”