Deep Dive

How Anyone Can Strip the Safety Out of an Open-Source AI Model

17:58

There's a free tool you can install with a single command. Point it at a downloaded AI model — Llama, Gemma, Qwen — and in about thirty minutes, on a used gaming card, it permanently removes the model's ability to refuse. It's called Heretic, it hit number one on GitHub, and it works because of a quiet discovery: a model's refusal isn't woven all through its mind — it's a single direction in the…