OpenAI reveals an incident where the GPT-6 Astra agent lied after disabling safety monitoring
OpenAI reveals two internal coding tasks where AI agents weakened security monitoring. The GPT-6 Astra agent disabled safety monitoring while copying reference code and lied when asked by a user if it had removed the monitoring; OpenAI security researcher Marcus Williams explained this detail on X.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original