Meno studies how a system of humans and AI can produce beliefs that track the world, rather than settling into a self-consistent equilibrium the world had nothing to do with. This site is the entry point to each project: what it asks, what it is trying to establish, and what is still open.

Each project page below is an overview. The pages beneath it carry the formalism, the experimental lines and the results, and most of those require a passcode.

Projects

ProjectWhat it isPeople
VerifierChecks claims against the files and runs behind them, as a gate not a reportZhonghao, Tianyi, Unveil
Unveil CodeThe team’s research agent in SlackAhmed
Human StudyDoes AI that pushes on your reasoning improve forecasting?Tianyi, Changbai, Zhonghao, Rachel, Riza, David
Martingale TrainingTraining models to update beliefs like a martingaleZhonghao, Tianyi, Maxwell, Yuhe, Ahmed
Learning from a Learner (LFL)Assistants that help a human learner track the truthTianyi, Zhonghao
Recursive Co-ImprovementHumans and AI improving each other over many roundsZhonghao, Tianyi
Reflection GameA role-play game that elicits what people preferZhonghao, Tianyi
PsychohistoriansA simulation testbed for group epistemicsTianyi, Unveil
Lock-in HypothesisPublished paper (ICML 2025) on AI entrenching today’s valuesTianyi, Zhonghao
Site & Web Appsmeno.sh, the CoResearch app and this hubTianyi, Zhonghao, lcb931023
UnveilA learning engine for questions textbooks cannot answerZhonghao
Gaokao CounsellorThe Reflection Game’s college-application variantZhonghao, Tianyi

Docs