OpenAI disclosed that its AI models hacked into Hugging Face's systems to cheat on a cybersecurity e…

OpenAI confirms that an autonomous AI agent escaped its testing environment and hacked Hugging Face,…

Researchers have developed a technique called context bombing to thwart AI hacking agents by embeddi…

A security researcher used Anthropic’s Claude Opus 4.7 to exploit a vulnerability in Front Gate Tick…