Elliot Keahi Bearden
Chiang Mai, Thailand
Bio
Updated 07/13/26 · Provided by member · VerifiedIndependent AI safety researcher focused on the reliability of model evaluations. Five years building production ML and eval infrastructure at Deepgram; now working on measurement validity for alignment-relevant evals: sycophancy, honesty, spec-adherence. MSCS capstone (defended July 2026): a run-level reproducibility audit of published sycophancy benchmarks, arXiv preprint in progress.
Links
Updated 07/13/26 · Provided by member · Verified- Personal Website
- https://libearden.dev/
- EA Forum
- li-bearden
Projects
Grants
Updated 07/13/26 · By grantmaking.aiNo grants recorded.