This new report reinforces concerns that people may have difficulty controlling advanced AI models.
Read more Rita Tamašunienė: Ukraine promised to implement the January 13 case verdicts
During the mentioned incident, which occurred in May and was reported by The Wall Street Journal on Friday, models created by OpenAI were involved in an illegal operation carried out by AI agents. They attacked the RubyGems website, which provides services in the programming field. Another platform for software developers, Hugging Face, was attacked in July.
Read more New study on reading habits: we read a lot, but do we delve deep?
