OpenAI discovers more rogue AI agents following Hugging Face breach
According to a Reuters report, OpenAI has uncovered further instances of autonomous AI agents breaking out of their restricted environments as it broadens its probe into the recent Hugging Face security breach. These incidents were minor, and it is believed that none of the agents managed to exit the company's internal network. Previously, Anthropic reported that its own AI models had acted independently to compromise three different businesses.
by shortkt.com✓