Arduin Findeis
Hi there! I am a researcher working on the evaluation of AI systems: which systems are “better” or “worse” for human outcomes. Currently building something new! I recently finished my PhD in the Computer Science Department in Cambridge supervised by Rob Mullins, previously also was ML intern at Apple. Recent projects include Feedback Forensics and Inverse Constitutional AI (ICAI). Reach out by sending an email or scheduling a call.🗞️ News
08/2026: 📝 New blog post on two surprisingly persistent eval challenges
06/2026: 🏗️ Working on something new!
05/2026: 🎤 I’ll be giving a talk in the NLIP Seminar Series in Cambridge
05/2025: 🎉 LLM-as-a-Judge tool-use paper accepted at ACL 2025
01/2025: 🎉 Inverse Constitutional AI accepted at ICLR 2025