← Glossary Company
METR
An independent group that tests advanced AI models for dangerous capabilities.
METR, short for Model Evaluation and Threat Research, is a non-profit that runs careful evaluations of frontier models to see what they can actually do, especially where that could be risky, such as autonomous hacking or self-improvement.
Its work matters because labs grading their own homework is not enough. Independent testing like METR’s is part of how the field tries to spot problems before a powerful model is widely released.
Mentioned in
-
We Are Building an Invention Meant to Outgrow Its Inventors
-
The Most Valuable AI Skill Is Not Prompting. It Is Verification.
-
AI agents made research software 60 times faster, and were confidently wrong in ways nobody spotted for weeks
-
Ten million dollars is on the table for research into what happens when AI agents meet each other, and the deadline is Saturday
-
METR has a new way to ask whether an AI agent is actually cheaper than a person