How Easy Is It to Trick an AI? Notes from a Red Team Competition (opens in new tab)

(medium.com)

6 pointspol_avec21d ago1 comments

1 comments

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

j / k navigate · click thread line to collapse

(medium.com)

6 pointspol_avec21d ago1 comments

pol_avecOP21d ago

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

j / k navigate · click thread line to collapse