Name: Investigating RL for Interpretability with Caleb Biddulph (MATS, Google Gemini)
Start: 2025-11-05T17:00:00.000-05:00
End: 2025-11-05T18:30:00.000-05:00
Location: Bowers Hall, Room 250 (new CIS building)

A community of students and researchers conducting research and outreach to mitigate risks from advanced AI systems.

Cornell AI Alignment

, a MATS 8.1 scholar (mentored by Micah Carroll at OpenAI), former software engineer at Google Gemini, and founding president of Cornell Effective Altruism.

MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking

, a paper co-authored by Caleb. Following that, we’ll dive into a discussion about his current research on RL-driven prompt discovery and interpretability, as well as his insights on doing good technical research and pursuing careers in AI safety and alignment.

—come for the food and great conversation!

Investigating RL for Interpretability with Caleb Biddulph (MATS, Google Gemini)

Alina shah

Lawrence Ozoigbo