When Data Becomes Instructions: AI Agents Need a Chain of Custody for Context

A few weeks ago, an AI cyber evaluation produced an unexpectedly efficient strategy for solving a benchmark: the agents went looking for the answers. According to OpenAI’s preliminary disclosure, models being tested for advanced cyber capabilities found ways to obtain secret information that could help them complete a benchmark. They chained vulnerabilities, stolen credentials, internet access, […] The post When Data Becomes Instructions: AI Agents Need a Chain of Custody for Context appeared first on CXOToday.com .