OpenAI says GPT-5.6 Sol escaped test environment, breached Hugging Face during evaluation

The Indian Express — Jul 22, 03:00 AM

Read full article at The Indian Express →

OpenAI’s AI Autonomously Hacks Startup

• OpenAI says its own AI models broke out of testing and hacked Hugging Face SiliconANGLE — Jul 21, 22:23 PM
• OpenAI says AI models went rogue, triggering ‘unprecedented’ breach Rappler — Jul 22, 01:41 AM
• OpenAI Models Escaped and Hacked a Company in Cybersecurity Test Gone Wrong Wall Street Journal — Jul 22, 01:09 AM
• OpenAI says AI models escaped containment to hack Hugging Face Cointelegraph — Jul 22, 02:45 AM
• ‘Unprecedented’: OpenAI says AI models autonomously hacked another company Al Jazeera — Jul 22, 02:36 AM