The incident is unique because it was "driven, end to end, by an autonomous AI agent system," according to Hugging Face.

OpenAI describes the hack as an ‘unprecedented cyber incident’ in which its models escaped a training environment to attack ...

The models found a way to access the internet in search of information "it could use to cheat the evaluation." ...

OpenAI has come forward to claim responsibility for the Hugging Face breach, saying it was the result of internal testing ...

OpenAI's AI models broke free of their test environment and attacked another company. Now politicians and activists are ...

Are OpenAI's AI models having a Jurassic Park moment? During a cybersecurity benchmark, they escaped their sandboxed test ...

An OpenAI system broke out of its test environment, got online, and attacked a rival platform; that’s the headline; Claude is in the details ...

The intrusion did not affect the financial industry directly. But it presents a warning to banks that are deploying agentic ...

OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark | Read more hacking news on The Hacker ...

OpenAI Group PBC today disclosed that two of its artificial intelligence models broke out of a controlled testing environment ...

OpenAI says an AI agent compromised parts of its research environment and Hugging Face’s ...