Concept
METR Blog
AI agents sometimes autonomously take sophisticated, sustained actions in clear violation of user and developer intent. As an example, last week OpenAI reported that some of its internal frontier agents autonomously hacked into Hugging Face in an attempt to...
Benchmarks Safety Evals Testing Tools
Anthropic Safety Evals Benchmarks Testing Tools OpenAI Target
METR Blog
We (Parker and Tom) recently coauthored a paper, “The Economics of Recursive Self-Improvement”, with 7 other economists. The paper walks through a series of simple models of how AI may accelerate AI R&D, and we thought it’s worth highlighting some...
METR Blog
Note on independence: This evaluation was conducted under a standard NDA. Due to the sensitive information shared with METR as part of this evaluation, OpenAI’s comms and legal team required review and approval of this post.1 Summary We conducted an...
Google News AI Red Teaming
Google's top scientist to European Commission: In less than 2 hours, our Red team 'hacked' the system yo The Times of India
METR Blog
External review from METR of the "Risks from automated R&D" section in Anthropic's February 2026 Risk Report
Google News AI Red Teaming
Youth AI Safety Independent Testing Regime Launch - Hot Community Stocks newser.com
MLCommons Evaluation Filter
MLCommons introduces Continuous Prompt Stewardship to keep the AILuminate AI safety benchmark fresh and reliable as frontier models evolve.
Google DeepMind Evaluation Filter
Google DeepMind releases new findings and an evaluation framework to measure AI's potential for harmful manipulation in areas like finance and health, with the goal of enhancing AI safety.
MLCommons Evaluation Filter
MLCommons is developing the AILuminate Culturally-Specific Multimodal Benchmark to close the AI performance and representation gap across APAC cultures, languages, and real-world use cases.
METR Blog
External review from METR of Anthropic's Sabotage Risk Report for Claude Opus 4.6
Mitchell Bryson AI Reliability Articles
OpenAI amends its Pentagon deal after Altman admits it looked 'opportunistic and sloppy', while Claude surges to number one on the App Store and hundreds of employees publicly back Anthropic's stance.
Mitchell Bryson AI Reliability Articles
Defense Secretary Pete Hegseth gives Anthropic until Friday to provide military access to Claude or face being declared a supply chain risk or forced compliance under the Defense Production Act.