OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark - The Hacker News

OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark  The Hacker NewsOpenAI and Hugging Face partner to address security incident during model evaluation  OpenAIOpenAI says its AI went rogue and launched 'unprecedented' cyber-attack  BBCOpenAI says AI models went rogue during testing, triggering 'unprecedented' breach at startup  ReutersOpenAI says its models went rogue and hacked startup in ‘unprecedented incident&rsqu