Projects
Reliable Weak-to-Strong Monitoring of LLM Agents
Neil Kale, Chen Bo Calvin Zhang, Kevin Zhu, Ankit Aich, Paula Rodriguez, Scale Red Team, Christina Q. Knight, Zifan Wang.
Submitted to ICLR, 2026
Jabber
AI project planning assistant
Used Hume AI's EVI to create voice interaction. GPT then processes user transcripts into organized notecards on a whiteboard space.