I often joke to people that I tweeted my way from “random AI researcher who likes open models” to a job at METR. But I don’t think I’ve told the story to y’all before. Time to do that: 🧵
On July 21, a two outside researchers started their first day embedded at OpenAI to examine at how it monitored coding agents.
The very same day, OpenAI disclosed the HF incident, which it said “points to the need to further strengthen […] monitoring during internal testing”.
We analyzed monitoring as it existed at the start of the pilot, coincidentally the same day OpenAI disclosed the Hugging Face incident. We didn't evaluate later changes, like expanding monitoring to RL training, which wasn’t monitored at the pilot's start.
x.com/OpenAI/status/…
NSA joined @NIST and @CISACyber in releasing guidelines for managing SI control incidents. Organizations utilizing SI are encouraged to adopt these practices. Read the joint report: media.defense.gov/2026/Oct/16/20…
My colleagues just published a 69-page response to Anthropic’s report on alignment.
They agree about the risk level but “are not confident that, if risk were higher, the methodology in [Anthropic’s] report would reliably identify this.”
List of disagreements starts on page 25.
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.