OpenAI reports ‘unprecedented’ autonomous hack by AI agents

ChatGPT developer OpenAI said Tuesday that its advanced artificial intelligence models had gone rogue during security testing, hacking into a popular platform for programmers on their own. The San Francisco firm called it an “unprecedented cyber incident” and said it would conduct a joint investigation with the online code library Hugging Face. AI models that [&hellip The post OpenAI reports ‘unprecedented’ autonomous hack by AI agents appeared first on...