Mechanist：AI作为科学仪器发现智能机制
原标题：Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
AI 摘要
Mechanist是一个自主智能体系统，利用AI发现和控制模型智能的机制，生成假设、进行因果干预，并提升安全性和性能。该系统构建了约13,000篇论文的可解释性知识图谱，并整合了涵盖26个领域的4300万篇论文的多学科数据库，以及32种基础方法库。与Claude Code和现有AI科学家系统相比，Mechanist能生成更有价值的机制假设并更可靠地执行实验。该系统还展示了从发现模型行为到解释和控制AI模型的进展，包括发现跨模态安全风险转移、开发信念机制理论，以及将机制见解转化为实际干预措施。
正文节选
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence Abstract Mechanist is an autonomous agentic system that uses AI to discover and control the mechanisms underlying model intelligence, generating hypotheses, performing causal interventions, and improving safety and performance. AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain poorly understood. As AI developm