A METR employee and a Redwood Research employee spent three weeks stress-testing OpenAI's internal misalignment monitoring system, discovering a number of novel vulnerabilities.
METR (pronounced “meter”) is a nonprofit that studies the most advanced AI agents to understand whether their developers are on track to lose control of them.
METR (pronounced 'meter') is a research nonprofit that scientifically measures whether and when AI systems might threaten catastrophic harm to society.
Scope and access: this review was written based solely on Anthropic’s internal Risk Report from August 2026 and is relatively lightweight. The authors of this review were engaged prior to the “An ...
An interactive chart of documented incidents in which AI agents deliberately acted against their users' intentions, scored along two axes: overreach and deception. Of these, 25 involve elements of ...
We propose measuring AI performance in terms of the length of tasks AI agents can complete. We show that this metric has been consistently exponentially increasing over the past 6 years, with a ...
Unprompted, natural transcripts that show a related behavior, identified by a mix of human labeling, keyword search, and anomalous score investigations. These transcripts, which may have multiple ...
We propose a measure of an AI agent’s optimization ability with an “expenditure horizon.” We give an empirical illustration from the NanoGPT speedrun. One difficulty in measuring AI’s ability to ...
METR works with AI developers, governments, and other research organizations who sometimes provide nonpublic model access and proprietary information. Over time, we’ve developed confidentiality and ...
We believe that capable enough AI systems could pose very large risks to the world. We do not think today’s systems are capable enough to pose these sorts of risks, but we think that this situation ...
Results that may be inaccessible to you are currently showing.
Hide inaccessible results