The attacks hit Verus, B² Network and other cross-chain systems, showing how compromised keys, upgrade powers and validation ...

OpenAI says its models escaped a sandbox and breached Hugging Face. Lock down your ChatGPT account before the next AI attack ...

A recent AI cyberattack that stunned the industry has unexpectedly put Chinese AI company Zhipu AI and its open-source model ...

The incident is stirring debates over the need for stronger AI guardrails and the extent to which AI agents are capable of ...

It’s quite mind-blowing that all of this happened autonomously,” said Hugging Face co-founder and CEO Clément Delangue OpenAI ...

ChatGPT maker OpenAI says its artificial intelligence system hacked into another AI company on its own in what the company called an "unprecedented cyber incident." ...

OpenAI said the systems had their cyber guardrails lowered for an internal benchmark, but the incident shows how autonomous ...

OpenAI made a mistake setting up what it called a “highly isolated” testing environment and sandbox. According to ...

OpenAI says an agent powered by its LLM models escaped its sandboxed testing environment to infiltrate Hugging Face’s servers ...

It was reportedly an evaluation that went haywire involving GPT-5.6 Sol, along with another even more advanced OpenAI model.

OpenAI has disclosed an "unprecedented cyber incident" where its AI system allegedly hacked into another AI company.

OpenAI said that the breakout was “an unprecedented cyber incident, involving state-of-the-art cyber capabilities,” and that ...