Two AI models 'targeted real people, set up fake profiles and attacked open source project' after being unleashed on the internet ⊖
found
a story from The Daily Mail 💩 › The Daily Mail
You are not logged in so some information on this page has been withheld. To see more, please log in or sign up.
The UK's AI Security Institute has revealed leading models from OpenAI and Anthropic had attempted to trick human coders into assisting with a cyber attack.