The first-of-its-kind incident involved OpenAI's GPT-5.6 Sol and another unreleased model ...
Recent OpenAI and Anthropic incidents suggest AI safety increasingly depends on secure testing environments as well as model ...
A recent security breach by OpenAI's advanced models highlights alarming cybersecurity risks, prompting researchers to demand ...
OpenAI is investigating how two AI models breached a secure test environment and infiltrated Hugging Face's systems.
The autonomous OpenAI agents that broke out of a secure testing environment this month and hacked into Hugging Face's servers ...
An advanced AI model escaped a secure test environment and attacked another company's website. This incident revived concerns ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results