Y
Hacker News
new
|
ask
|
show
|
jobs
How Easy Is It to Trick an AI? Notes from a Red Team Competition
(
medium.com
)
6 points
by
pol_avec
102 days ago
1 comments
pol_avec
102 days 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
link
Happy to discuss if someone's more knowledgeable and share more