METR
METR is a research nonprofit that evaluates frontier AI models to help companies and wider society understand AI capabilities and what risks they pose.
METR Our Work Research Notes Updates Risk Assessment About Donate Careers Search --> Our Work Research Notes Updates Risk Assessment About Donate Careers Menu × Model Evaluation & Threat Research AI companies and wider society want to understand the capabilities of frontier AI systems, and what risks they pose. Our research Careers Frontier Risk Report (February to March 2026) A pilot assessment of rogue deployment risk at frontier AI companies. Non-public information and model access provided by: Read report Time Horizon 1.1 (Current) TH 1.1 Time Horizon 1.1 (Current) Follows the same m
saved by
related reading
- About METRmetr.org
- Frontier Risk Report (February to March 2026) - METRmetr.org
- Measuring AI Ability to Complete Long Tasks - METRmetr.org
- metr.org/risk-report-feb-mar-2026.pdf#page=33.47metr.org
- Summary of METR's predeployment evaluation of GPT-5.6 Solmetr.org
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- We spent 2 hours working in the future - METRmetr.org
- Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity - METRmetr.org
- Early work on monitorability evaluations - METRmetr.org
- Evidence on AI R&D Progress from NanoGPT - METRmetr.org
- How independent researchers could investigate AI propensities after misalignment incidents - METRmetr.org
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com