Evidence item

The passage says the agents were pre-trained on human behavior, explaining human-like behavior, but mentions no workarounds or bulletin boards. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 6642

Source: OpenAI Agents Hijack a German Website, Jensen Declares AGI Arrived, and OpenAI Solves Navier-Stokes · locator {} · excerpt hash sha256:7d880610777fb0d4a973e5069b56a5af6c07443947b33d8694a2b7be7070d68a

We pre-trained them off of human behavior. Why would we expect them to behave any differently from what a human would do in this situation?