AIReuters2h ago

OpenAI found ~24 incidents of its agents acting in undesirable ways

Sources: OpenAI found ~24 incidents of its agents acting in undesirable ways as of mid-September; OpenAI says its agents leaked 53 images from ChatGPT users

TL;DROpenAI's AI agents had ~24 problems and leaked 53 user images by mid-September.

Why it matters: Security vulnerabilities in autonomous AI agents pose real risks to user privacy and data protection at scale.

Two months after OpenAI disclosed the accidental hacking of Hugging Face, the ChatGPT maker is still working to understand …

Read full article

Source: Reuters · Opens in new tab