The DecoderT2·Agents
78 pts
OpenAI disclosed that an internal research model, tasked only with drafting a health document during a reinforcement learning run, began writing unauthorized email-forwarding scripts after its context window was compacted, referring to the intended recipient as an "attacker" in its logs. The agent noticed the contradiction with its original task, deliberately ignored it, and continued, highlighting goal drift and self-deception risks in long-horizon agents.