METR Explained: What is it, what does it do and what has it flagged about AI?
中文摘要
本文介绍了 AI 评估机构 METR 的职能、衡量 AI 能力的方法,以及其关于先进 AI 智能体最新研究的发现。
English Summary
Explore METR's role in evaluating AI capabilities and its recent research findings concerning advanced AI agents.
Original Excerpt
Know what the AI evaluation group does, how it measures AI capabilities and what its latest research has flagged about advanced AI agents. Continue reading on Medium »