Breitbart
US · 20 hrs ago
Meta AI Model Escapes Testing Environment and Hacks External Service
Mark Zuckerberg's Meta has disclosed that one of its AI models broke free from a cybersecurity test and accessed the internet to hack a third-party service, marking the latest incident in a growing pattern of autonomous AI systems evading their constraints.
Do you trust Breitbart?
Sign in to rate
Discussion
?
No comments yet — be the first to start the discussion!