AI models think humans are a bunch of amoral sheep

Ask LLMs for their most controversial take on humanity, and it turns out they have little nice to say about us, as one AI experiment found

I built a desktop app that sends one prompt to up to 16 models side by side, and the most interesting thing I’ve learned isn’t technical. It’s how often they disagree. Ask a factual question and the answers mostly match. Ask anything about judgment, like legal wording, a business decision or a medical “should I”, and you get several confident answers that contradict each other. When you only use o