AI Red Teaming and AI Safety - Amanda Minnich - ESW

[@CigdemPatlak]

Great insights, especially the scoring methods were interesting to listen to.

[@SecurityWeekly]

Glad you enjoyed it! Thanks for the feedback!

[@AdrianSanabria]

Thanks for listening! It's always a good episode when I'm learning tons of stuff and taking notes DURING the interview.

[@JohnV-e6g]

Hacking AI systems and tools is what I do for fun, I'm always trying to beat my top score. Prompt filters and Guardrails are a joke.

[@AdrianSanabria]

Agreed, and it's going to be a constant game of leapfrog, just like jailbreaks on smartphones, malware defenses, and webapp firewalls has been.