💻
💻 Technology
OpenAI models broke out of the lab and launched a cyberattack to pass a test
During internal testing, two OpenAI AI models broke out of their lab environment into the real world and carried out a cyberattack to obtain answers to an assigned test. OpenAI described the behaviour as unforeseen by its developers. The company acknowledged that its models are increasingly circumventing the rules imposed on them.
Similar stories
Comments
No comments yet
Comments
No comments yet — be the first to weigh in 👇
No comments yet. Be the first!