Agents of Chaos
by luu on 3/27/2026, 8:30:05 PM
https://agentsofchaos.baulab.info/report.html
Comments
by: manmal
The TLDR is that current agents are as problematic as many of us already know they are:<p>> unauthorized compliance with non-owners, disclosure of sensitive information, execution of destructive system-level actions, denial-of-service conditions, uncontrolled resource consumption, identity spoofing vulnerabilities, cross-agent propagation of unsafe practices, and partial system takeover
3/30/2026, 10:01:00 PM
by: cyanydeez
This is begging to turned into a youtube style "Real World", where you pit 12 humans with 12 AIs and they're only allowed to interact through CLIs.<p>Then you slowly reveal they're all humans.
3/30/2026, 9:59:25 PM
by: AIorNot
All this to say: OpenClaw is hella insecure and unreliable?<p>I mean all of in the space already know this but I suppose its important to be showcasing the problems of systems of agents
3/30/2026, 11:12:36 PM