Dan Hendrycks
Source-listed: Executive & Research Director · Center for AI Safety (CAIS)
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Measuring Massive Multitask Language UnderstandingSaved credit: Maintainer · 2021Explore people connected to this work →
- Gaussian Error Linear Units (GELUs)Saved credit: Contributor · 2016Explore people connected to this work →
- Deep Anomaly Detection with Outlier ExposureSaved credit: Contributor · 2019Explore people connected to this work →
- Measuring Mathematical Problem Solving With the MATH DatasetSaved credit: Contributor · 2021Explore people connected to this work →
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM AgentsSaved credit: Contributor · 2025Explore people connected to this work →