What We Learned Trying to Catch AI Liars: An Aletheia's Quest Retrospective | EleutherAI Blog
What we learned while building black-box and white-box detectors for AI deception during Aletheia's Quest.
Sources / EleutherAI
EleutherAI
Research · Official site ↗ · RSS · JSON Feed
FineBooks: are open OCR models good enough to unlock historical knowledge? | EleutherAI Blog
Testing open OCR models on historical books with the FineBooks BHL OCR Leaderboard.
A Dynamical Model of AI Governability | EleutherAI Blog
A toy dynamical model of whether the AI workforce that builds future AI ends up cooperative or uncooperative: where the basin boundary lies, what current evidence says about which side we are on, and what would tell us we are on the good path.
Early Indicators of Reward Hacking via Reasoning Interpolation | EleutherAI Blog
Using importance sampling with fine-tuned donor prefills to predict reward hacking emergence during training