We work to scientifically measure whether and when AI systems might threaten catastrophic harm to society. Nonprofit.
Berkeley, CA
Joined September 2023
- Tweets740
- Following46
- Followers58.1K
- Likes1.7K
Pinned Tweet
Two employees from METR and Redwood Research worked on premises at OpenAI for three weeks this summer in an embedded assessment pilot. This team evaluated the systems OpenAI was using to monitor for misalignment from internal agents. A brief write-up of their work is now public.
METR retweeted
Personal news: after two years at @EpochAIResearch, I’ve joined @METR_Evals to work on embedded assessments of AI R&D acceleration: going inside AI developers to measure how much AI is speeding up AI development, and publishing our findings.
METR retweeted
Personal news: I’ve joined the @METR_Evals embedded monitoring assessment team, working with @idavidrein! I’ll be going inside the AI labs and testing their control systems. Also, I moved to the Bay Area! Say hi.
OpenAI could also make redactions, and we did not have the right to unilaterally describe the redactions.
For future exercises, we expect to provide more robust public transparency via our recent proposal.
xitter.cf/METR_Evals/status/2110…
Read our public overview for more findings, limitations, and design ideals:
metr.org/blog/2026-10-22-red…
METR retweeted
We believe that Anthropic should include "undermining of safety-relevant decision-making" as key risk pathway.
This is partially inspired by Section 2.20 of their risk report, where Anthropic asked Claude for feedback on their report, and received a (imo) sycophantic answer.
(2) We think Anthropic should, for future reports, consider risks from AI systems undermining safety-relevant decisions at Anthropic.
Read our full risk report review here: metr.org/blog/2026-10-20-mis…
We reviewed a nonpublic version of the “Misalignment in high-stakes settings” section in Anthropic’s Aug 2026 Risk Report. We agree that risk of catastrophic harm from covered models’ misalignment is low. However, we note several significant disagreements with their analysis.
As part of our Responsible Scaling Policy, we publish regular Risk Reports. These share detailed information on the risks of our systems and how prepared we are to address them.
Our second Risk Report is now available: anthropic.com/aug-2026-risk-…
(2) We think Anthropic should, for future reports, consider risks from AI systems undermining safety-relevant decisions at Anthropic.
Read our full risk report review here: metr.org/blog/2026-10-20-mis…