About METR
metr.org · 1,025 words · saved by 2 readers
What METR does, our mission, and our team.
About METR Our Work Research Notes Updates Risk Assessment About Donate Careers Search --> Our Work Research Notes Updates Risk Assessment About Donate Careers Menu × About METR Model Evaluation and Threat Research What we do METR (pronounced 'meter') evaluates frontier AI models to help companies and wider society understand AI capabilities and what risks they pose. Most of our research consists of evaluations assessing the extent to which an AI system can autonomously carry out substantial tasks , including general-purpose tasks like conducting research or developing an app, and concer
saved by
related reading
- METRmetr.org
- METR and Redwood Offer Holy #%^@ Postmortem Of The HuggingFace Hacksubstack.com
- Frontier Risk Report (February to March 2026) - METRmetr.org
- CAIS AI Dashboarddashboard.safe.ai
- Summary of METR's predeployment evaluation of GPT-5.6 Solmetr.org
- metr.org/risk-report-feb-mar-2026.pdf#page=33.47metr.org
- Measuring AI Ability to Complete Long Tasks - METRmetr.org
- We spent 2 hours working in the future - METRmetr.org
- Resources on the AI risk landscape – Ben Pomeranzbenpomeranz.com
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- GitHub - METR/RE-Bench · GitHubgithub.com
- Rogue AI Trackerrogueaitracker.com