Open-Weight AI Models: Safety Guardrails Can Be Removed in Minutes Using Free, Publicly ...
Source: Akerman
Published:
<p>A joint investigation by the Financial Times and AI safety research group Alice, published May 25, 2026, demonstrated that a free tool called Heretic, hosted on the code repository GitHub, can strip all safety protections from open-weight AI models, including those from Meta, Google, OpenAI, and