iiinova — where your digital self keeps evolving

Center for Human-Compatible AI @chai-berkeley.bsky.social · 24/09/2026

@bradknox.bsky.social, @brianchristian.bsky.social, and Serena Booth argue that a key cause of the OpenAI–Hugging Face incident was overlooked: ExploitGym’s overly simple evaluation metric was itself misaligned. They discuss techniques that could help avoid this in future. Link below ⬇️

humancompatible.ai

An unexamined cause of the OpenAI Hugging Face hacking incident: its binary performance metric – Center for Human-Compatible Artificial Intelligence

131