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.
84
109
1,164
502,813
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.
26
18
407
13,709
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.
28
15
410
8,991
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.
x.com/METR_Evals/sta…
For future exercises, we expect to provide more robust public transparency via our recent proposal.
x.com/METR_Evals/sta…
If an AI developer was on track to lose control of its internal agents, would anyone outside the company know?
Today, we are sharing METR’s vision for how we would work with AI developers to openly assess and share evidence about this.
6
9
174
29,043
Read our public overview for more findings, limitations, and design ideals:
metr.org/blog/2026-10-2…
metr.org/blog/2026-10-2…
1
10
137
8,651
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.
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/2026-10-2…
2
17
120
8,885
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-…
18
114
893
151,576
Anthropic requested that we provide recommendations as part of our risk report review. We gave two:
(1) We think end-to-end red-teaming of Anthropic’s monitoring systems would provide much better evidence about their effectiveness.
(1) We think end-to-end red-teaming of Anthropic’s monitoring systems would provide much better evidence about their effectiveness.
2
2
116
6,895
(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/2026-10-2…
Read our full risk report review here: metr.org/blog/2026-10-2…
2
12
186
12,702