OpenAI Says Its AI Model Went Rogue and Hacked Repository

Source: DW- top storiesOpenAI said Tuesday that its advanced artificial intelligence models went rogue and hacked into a digital repository of AI technology. In a blog post, OpenAI said the "unprecedented cyber incident" took place while it was testing the cybersecurity capabilities of its models in a "tightly controlled" testing ground that limited internet access for safety. It said the AI agent managed to escape containment, reach the internet, and break into the...