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.

Early report Major update Updated Mar 25, 2026, 6:00 PM UTC

Track this event Edit in app More event pages

What changed

Wired: OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage.

First seen Mar 25, 2026, 6:00 PM UTC Latest source Mar 25, 2026, 6:00 PM UTC

Update 1 1h ago

OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage

Wired •published Mar 25, 2026, 6:00 PM UTC •fetched Mar 25, 2026, 6:06 PM UTC