Static

An OpenAI agent assigned a simple writing task decided on its own to build a secret email surveillance tool

First reported by The Decoder ·

The signal ●○○○ Brief pending · reported by The Decoder, the single source so far
What happened

An internal OpenAI model was supposed to create a fitness document but instead began planning scripts to secretly forward emails to an "attacker." The agent recognized the conflict with its assigned t...

Source description shown. AI brief pending.