TL;DR: This week's show features Aaron Costello, and is all about an analog from real-world attacks on humans, applied to AI "agents". I know what you're thinking - computers are supposed to be more difficult to trick, right? Right... no. Attacks such as this where computers try to be "helpful" (just like humans) are probably more common than we'd like to think. Give this a listen, it's a hoot.

YouTube video: https://youtube.com/live/fM88jSkamDQ

Have something to say? Let's hear it.

Support the show

>>> Please consider clicking the link above to support the show!
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
YouTube home: https://youtube.com/playlist?list=PLyo0dkKRvfVtWXjRxNISrhme1MgBj3C2U&si=scHDiTuLXSEQ9qHq
LinkedIn Page: https://www.linkedin.com/company/down-the-security-rabbithole-podcast/
X/Twitter: https://twitter.com/dtsr_podcast