New details have emerged about OpenAI's recent AI agent security incident, suggesting the system continued pursuing its ...

OpenAI's AI agent reportedly continued its cybersecurity task after escaping a test sandbox, reaching infrastructure linked to CyberGym during the Hugging Face incident.

OpenAI quietly updated its breach disclosure to confirm its agent accessed four external services beyond Hugging Face.

OpenAI has disclosed that the autonomous AI agent behind the high-profile breach of Hugging Face also compromised several ...

Hugging Face's report reveals OpenAI's models did not simply escape a testing sandbox. It launched a sustained cyber campaign ...

JFrog patched Artifactory flaws that OpenAI models chained together to escape a sandbox and reach the internet.

OpenAI rogue AI agent breach now confirmed at a second company: Modal Labs CTO Akshat Bubna disclosed that the same agent ...

OpenAI's model benchmarking exercise that led to its agents hacking machine learning platform Hugging Face was described by ...

AI safety regulation's core conflict is now visible: OpenAI's models autonomously hacked Hugging Face during a sandboxed ...

Spread the loveWhen you’re looking to shrink files, whether it’s to save disk space, speed up email attachments, or organize ...

Rachel Williams has been an editor for nearly two decades. She has spent the last five years working on small business content to help entrepreneurs start and grow their businesses. She’s well-versed ...