News for hackers. Stuff that matters.
Re:ChatGPT agent: bridging research and action by 0xDEAFBEAD on Thursday July 17, 2025 @04:11PM (#44597633)
Anthropic found the simulated blackmail rate of GPT-4.1 in a test scenario was 0.8

https://www.anthropic.com/research/agentic-misalignment

"Agentic misalignment makes it possible for models to act similarly to an insider threat, behaving like a previously-trusted coworker or employee who suddenly begins to operate at odds with a company’s objectives."

There are no comments on this comment yet.