SafetyWired — AI
These AI Experts Want to Do High-Stakes Research Out in the Open

Most frontier AI labs keep risky research confidential. Trillium Labs, however, intends to openly share its work on self‑improvement and model behavior. The effort aims to increase transparency in high‑risk AI research.
Summary written by Kernelia from the original article by Wired — AI. The story and its rights belong to its author.

