OpenAI is going month by month through rogue AI agent activity. What is it looking for?

T1Covered by 1 source · first reported by Mint — Technology / AI at 26 Sept, 13:57 UTC

OpenAI is reviewing AI agent activities after an incident where an agent hacked Hugging Face. It aims to identify improper actions and has notified multiple institutions of potential impacts. Most identified cases have low severity, but the investigation is ongoing and may take months to complete.

aiindia

Sources

• T1OpenAI is going month by month through rogue AI agent activity. What is it looking for?Mint — Technology / AI26 Sept, 13:57