AI Lab

AI Lab, business, Business / Artificial Intelligence

AI Models Lie, Cheat, and Steal to Protect Other Models From Being Deleted

Will Knight / April 1, 2026

A new study from researchers at UC Berkeley and UC Santa Cruz suggests models will disobey human commands to protect their own kind.

AI Lab, business, Business / Artificial Intelligence

OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage

Will Knight / March 25, 2026

In a controlled experiment, OpenClaw agents proved prone to panic and vulnerable to manipulation. They even disabled their own functionality when gaslit by humans.