Ian Kahn
Nijmegen, Netherlands
Bio
Updated 07/13/26 · Provided by member · VerifiedI'm an independent AI safety researcher building a behavioral benchmark for corrigibility and fine-tuning open-source models toward corrigibility as a singular target (CAST). Before moving into alignment work, I trained as a philosopher, with master's degrees from UNC Chapel Hill (metaethics) and Simon Fraser University (philosophy of science). Before that, I studied physics and electrical engineering. After a year in the Erasmus Mundus Joint Master's in AI (EMAI), I'm leaving to pursue this work full-time.
Links
Updated 07/10/26 · Provided by member · Verified- Personal Website
- https://iankahn.net/
Projects
Testing Corrigibility as a Singular Target
Team Member
Grants
Updated 07/13/26 · By grantmaking.aiNo grants recorded.