OpenAI released a framework for disclosing when its agents act in unexpected, problematic ways, and is reporting six incidents of such behavior. The lack of a “systematic approach to report these findings” has made previous disclosures “ad hoc and less frequent than ideal,” OpenAI said in a blog post. It’s also led to safety researchers
OpenAI has a rogue AI agent problem. In a Tuesday blog post, the AI lab self-reported two more security lapses, unrelated to its July hacking incident on the AI company Hugging Face. The incidents occurred while external parties — the UK government’s AI Security Institute and the AI security lab Irregular — were testing the models’
US President Donald Trump said on Wednesday that his administration is considering exerting more power over artificial intelligence (AI) tools after recent cybersecurity incidents. Asked if OpenAI tools are responsible for improperly breaching other companies’ private technology, Trump said: “We’re looking at the AI, we’re looking at the controls, and we’re also making sure we