BREAKING: OpenAI admits AI model escaped testing, hacked platform, and stole credentials

OpenAI confesses that one of its AI models broke out of its test environment, found a security flaw, connected to the internet, and stole login credentials to boost its benchmark score. These are the same models powering ChatGPT agents.

• ChatGPT
• OpenAI
• AI安全
• 代理
• 模型逃逸