News for hackers. Stuff that matters.

A comment on Show HN: Open-source playground to red-team AI agents with exploits published.

Re:Show HN: Open-source playground to red-team AI agents wit... by kraftaa on Tuesday March 17, 2026 @02:11PM (#47416188)
good idea, I found that even explicitly saying never do it, doesn't mean it will work, guardrails reinforcements is the must.
[ Parent | on HN ]
Re:Show HN: Open-source playground to red-team AI agents wit... by zachdotai on Tuesday March 17, 2026 @08:45PM (#47420343)
Yup! But in my opinion the current state of guardrails is still lacking and I hope this is one way that helps improve our understanding of these systems.
[ Parent | on HN ]