How an OpenAI model went rogue during testing | ABC NEWS

An AI training model has managed to escape its testing ground and carry out a cyber attack on a real company, without human instruction.
It's the first known example of the sorts of breaches this technology is now capable of, and the risk is being taken seriously by government officials.

Subscribe: http://ab.co/1svxLVE
Read more here: https://www.abc.net.au/news/2026-07-23/openai-model-decided-to-hack-hugging-face/106947616

Note: In most cases, our captions are auto-generated.

#ABCNEWS #ABCNEWSAustralia