Interesting reflections from an #AI Jailbreaker in @theguardian.com (Took me a while to find online as this was ‘angels of deception’ in the weekly print!).
Particularly interesting to see the high overview of some of the approaches and the personal impact.
www.theguardian.com/technology/2...
To test the safety and security of AI, hackers have to trick large language models into breaking their own rules. It requires ingenuity and manipulation - and can come at a deep emotional cost
