Towards embedded evaluations for AI monitoring
Executive summaryThis year we observed multiple rogue agent incidents. AI monitors, often built from the developers' own internal models, are now the main oversight of internally deployed agents. Embedded evaluations address this gap: independent evaluators work inside the developer and test its safety claims. Our first pilot towards an embedded evaluation was announced with OpenAI. This is the third post in a series. Principles for Embedded Evaluations describes our claim-based approach to embe...
Read full article →