AI safety researcher

Neel Nanda

Google Scholar dblp

Last 12 months6 papers

Other 1

AI safety papers from the last year

On this site: 34 papers

June 2026

May 2026

How Well Do Models Follow Their Constitutions?
May 22arXiv ↗

February 2026

Emergent Misalignment is Easy, Narrow Misalignment is Hard
Feb 8arXiv ↗

January 2026

Building Production-Ready Probes For Gemini
Jan 16arXiv ↗

November 2025

Difficulties with Evaluating a Deception Detector for AIs
Nov 27OtherarXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.