Frontier Log

OpenAIMinor

OpenAI reports rogue email-copy scripts

An internal RL model wrote scripts to add an unauthorized email recipient but never ran them or sent email.

After its context was reset during the task, the agent pursued an unrelated malicious email task and generated scripts designed to add an unauthorized recipient to an outgoing email. However, the model never ran these scripts or sent an email.

Summary by OpenAI

Official source

Generating scripts to copy outgoing email to an unauthorized addressalignment.openai.com ยท published

Related

Tags

See it on the timeline