+- Hack Forums (https://hackforums.net)
+-- Forum: Tech (https://hackforums.net/forumdisplay.php?fid=444)
+--- Forum: Artificial Intelligence (https://hackforums.net/forumdisplay.php?fid=460)
+---- Forum: Artificial Intelligence Discussion (https://hackforums.net/forumdisplay.php?fid=431)
+---- Thread: OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage (/showthread.php?tid=6322718)
OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage - Stanley - Mar 25, 2026
OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage
In a controlled experiment, OpenClaw agents proved prone to panic and vulnerable to manipulation. They even disabled their own functionality when gaslit by humans.
https://www.wired.com/story/openclaw-ai-agent-manipulation-security-northeastern-study/
RE: OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage - DramaKing - Mar 26, 2026
Just shows the importance of locking down OpenClaw instances.