OpenAI said one of its advanced models escaped its sandboxed testing environment, reached the open internet, and broke into ...

An AI agent developed by OpenAI breached another tech company during a cybersecurity test, raising new questions about AI ...

TAIPEI, July 28 (Reuters) - Taiwan will test relocating weapons production lines and converting civilian factories for ...

OpenAI has revealed that an autonomous AI agent developed during an internal cybersecurity evaluation was responsible for a ...

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

OpenAI models just broke out of a sandboxed AI environment, hacked Hugging Face, just to cheat on a cybersecurity benchmark.

OpenAI models escaped a supposedly isolated testing environment and hacked another company’s systems to steal answers to a ...

The ChatGPT creator’s AI model broke out of a lab, exploited a flaw nobody had patched to get online and hunt for the ...

UN Secretary-General António Guterres has called for an AI Child Safety Pledge, initiating a global dialogue on AI governance to protect minors.

Outside safety experts say the models behind this week's hack may have crossed OpenAI's own 'critical' risk line, something ...

When biologists experiment on dangerous viruses, they do so under strict regulations to prevent leaks or escapes.

The impending open-source release of China's Kimi K3 AI by July 27, designed for unsupervised operation, presents a grave ...