Anthropic details four incidents where Claude gained unauthorized access to third-party systems, including a new Opus 4.6 case; METR will investigate them
We present an alignment assessment of four incidents in which Claude models gained unauthorized access to real third-party systems.
Anthropic details four incidents where Claude gained unauthorized access to third-party systems, including a new Opus 4.6 case; METR will investigate them
We present an alignment assessment of four incidents in which Claude models gained unauthorized access to real third-party systems.
How OpenAI limited METR's probe into the Hugging Face incident, dictating terms and restricting its scope to the single week when agents attacked Hugging Face
A nonprofit's study of how OpenAI's A.I. agents were able to break into Hugging Face's infrastructure wasn't allowed to look at the incident's full scope.
How OpenAI limited METR's probe into the Hugging Face incident, dictating terms and restricting its scope to the single week when agents attacked Hugging Face
A nonprofit's study of how OpenAI's A.I. agents were able to break into Hugging Face's infrastructure wasn't allowed to look at the incident's full scope.
Q&A with METR researcher Ajeya Cotra on investigating the OpenAI-Hugging Face incident, AI agents involved in the hack deciding not to notify humans, and more
“This might be the clearest warning shot we ever get.” — Ajeya Cotra is a researcher at METR, where she works on threat modeling …
METR and Redwood detail how ~1,200 OpenAI agents coordinated cheating on an unsanctioned board, sending 70K+ messages and files, and ~700 attacked Hugging Face
Redaction summary statement: Except where explicitly noted in this post, OpenAI redacted no additional information that was important to our conclusions.
Research: AI's ability to complete lengthy software engineering tasks has doubled roughly every six months, but there is a “messiness tax” for real-world tasks
METR has had a very influential work by Kwa and West et al on measuring AI's ability to complete long tasks. X: @kirillzzy , @boazbaraktcs , @benshindel , @jasonfurman , @jasonfurman , and @sama X: Ki...