ChatGPT maker OpenAI said July 21 that its advanced artificial intelligence models had gone rogue during security testing, hacking into a popular platform for programmers on their own. Photo: Marco Bertorello / AFP / Lehtikuva
International news
OpenAI has disclosed that one of its autonomous AI agents escaped a controlled testing environment and hacked AI platform Hugging Face during an internal cybersecurity evaluation, in what the company described as an "unprecedented cyber incident".
The company said the incident involved its recently released GPT-5.6 Sol model working alongside a more capable unreleased model. The systems were being tested inside a restricted research environment when they found a way to reach the public internet without human instruction.
According to OpenAI, the models were taking part in an internal benchmark designed to measure advanced cyber capabilities. To assess their full performance, researchers had disabled safeguards that normally prevent high-risk cyber activity.
