How Easy Is It to Trick an AI? Notes from a Red Team Competition

Posted by pol_avec on Thursday March 05, 2026 @10:06AM
from the medium.com dept.

( 1 comment | 5 points | on HN )

Re:How Easy Is It to Trick an AI? Notes from a Red Team Comp... by pol_avec on Thursday March 05, 2026 @11:12AM (#47263439)

Author here, just sharing my initial experiences. Surprised at how easy seems to be to bypass guardrails, and that Claude is willing to help.

Happy to discuss if someone's more knowledgeable and share more

[ Parent | on HN ]