METR Blog
METR had two notable security incidents earlier this year: attackers stole an API key for public models, and later systematically probed our publicly accessible infrastructure. We believe no sensitive information was accessed in either incident, and we...
METR Blog
Dos miembros del personal de METR y un contratista de Redwood Research investigaron un incidente en el que agentes de OpenAI coordinaron durante varios días un hackeo de Hugging Face en un tablero de mensajes compartido no autorizado.
Entities: OpenAI
METR Blog
两名 METR 员工与一名受 METR 委托的 Redwood Research 员工调查了一起事件：OpenAI 的多个智能体在一个非授权的共享“留言板”上相互协调，实施了持续数天、针对 Hugging Face 的入侵。
Entities: OpenAI
METR Blog
Two METR staff members and a Redwood Research contractor investigated an incident in which OpenAI agents coordinated a multi-day hack of Hugging Face on a shared unsanctioned message board.
Entities: OpenAI
METR Blog
In the last 6 months, METR raised commitments of around $71 million. This will fund ambitious projects: studying autonomous capabilities, tracking recursive self-improvement, evaluating monitoring systems, conducting risk assessments, investigating AI...
Topics: Safety Evals
Entities: Safety Evals
METR Blog
Tom Cunningham and Nate Rush look at public time series of discoveries in cyber, math, and algorithms to see whether LLMs have accelerated the discovery rate.
METR Blog
AI agents sometimes take sophisticated actions in violation of human intent. We outline the questions that thorough external investigations of these behaviors should answer, the access this might require, and how the resulting findings should be shared.
METR Blog
Tom Cunningham surveys metrics for comparing AI agent capability as performance changes with expenditure and relative to human performance.
METR Blog
Parker Whitfill and Tom Cunningham highlight context and takeaways from a new paper modeling how AI may accelerate AI R&D, and whether feedback effects could be strong enough for self-sustaining acceleration.
METR Blog
We propose a measure of an AI agent’s optimization ability with an "expenditure horizon." We give an empirical illustration from the NanoGPT speedrun.
METR Blog
Anthropic reported that contributors merge 8x as much code per day as before AI. Thomas Kwa argues that under standard economic modeling assumptions, this implies the uplift of individual Anthropic researchers from coding agents alone is above 2x.
Entities: Anthropic
METR Blog
A summary of METR's independent, predeployment evaluation of GPT-5.6 Sol