Working Paper Working Paper

Mitigating Agentic Misalignment via Jacobian Workspace Self-Supervision

Ifueko Igbinedion, Etienne Ricardez, Sertac Karaman, Eric So

Shows that monitoring an AI agent's internal states can detect reasoning headed toward harmful actions and trigger guided self-correction, substantially reducing agentic misalignment without retraining the model.

Working Paper Working Paper

Adding AI Advice to Trading Interfaces Induces Overtrading and Reduces Investor Welfare

Zoe De Simone, Etienne Ricárdez, Eric So, Andrew W. Lo

Finds that adding AI forecasts to a prediction-market interface pulls users toward advice weaker than market prices, lowering forecast accuracy and increasing trading.

Working Paper Research in progress

When AI Speaks, Do We Listen? Examining Factors in the Uptake of LLM Advice

Andrew Lo, Jillian Ross, Eric So

Studies the conditions that determine whether people accept, discount, or act on advice generated by large language models.

Working Paper Research in progress

Fee the People

Omri Even-Tov, Kimberlyn George, Shimon Kogan, Eric So

Investigates how fee structures affect investor behavior and the distribution of costs across market participants.