Back
Dan Hendrycks - GitHub Profile (ML Safety Researcher)
webCredibility Rating
3/5
Good(3)Good quality. Reputable source with community review or editorial standards, but less rigorous than peer-reviewed venues.
Rating inherited from publication venue: GitHub
Dan Hendrycks is one of the most prolific researchers at the intersection of ML robustness and AI safety; his GitHub hosts datasets and benchmarks widely used to evaluate model safety and reliability across the field.
Metadata
Importance: 72/100homepage
Summary
GitHub profile of Dan Hendrycks, a prominent ML safety researcher and director of the Center for AI Safety. His public repositories include foundational benchmarks and datasets for evaluating robustness, out-of-distribution detection, and AI safety, including MMLU, ARC, and corruption robustness benchmarks.
Key Points
- •Home to influential benchmarks like MMLU (Massive Multitask Language Understanding) used widely to evaluate LLM capabilities
- •Includes robustness benchmarks (ImageNet-C, CIFAR corruption) for measuring model reliability under distribution shift
- •Repos cover anomaly detection, calibration, and out-of-distribution detection — core technical safety concerns
- •Work directly informs AI safety evaluation methodology and is widely cited in alignment and capabilities research
- •Hendrycks is director of the Center for AI Safety (CAIS), making this profile a key resource hub for safety tooling
Cited by 1 page
| Page | Type | Quality |
|---|---|---|
| FAR AI | Organization | 76.0 |
Cached Content Preview
HTTP 200Fetched Apr 9, 20264 KB
hendrycks (Dan Hendrycks) · GitHub
Skip to content
You signed in with another tab or window. Reload to refresh your session.
You signed out in another tab or window. Reload to refresh your session.
You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
hendrycks
Follow
More
Overview
Repositories
Projects
Packages
Stars
hendrycks
Follow
Dan Hendrycks
hendrycks
Follow
PhD student at UC Berkeley.
1.2k
followers
·
0
following
Berkeley, California
danhendrycks.com
X
@hendrycks
Achievements
x2 x3 Achievements
x2 x3
Block or Report
Block or report hendrycks
-->
Block user
Prevent this user from interacting with your repositories and sending you notifications.
Learn more about blocking users .
You must be logged in to block users.
Add an optional note
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Block user
Report abuse
Contact GitHub support about this user’s behavior.
Learn more about reporting abuse .
Report abuse
More
Overview
Repositories
Projects
Packages
Stars
hendrycks / README .md
I'm Dan, a PhD student in ML at UC Berkeley.
See my webpage for my research.
See below for my code.
Pinned
Loading
outlier-exposure outlier-exposure Public
Deep Anomaly Detection with Outlier Exposure (ICLR 2019)
Python
575
107
robustness robustness Public
Corruption and Perturbation Robustness (ICLR 2019)
Python
1.1k
151
natural-adv-examples natural-adv-examples Public
A Harder ImageNet Test Set (CVPR 2021)
Python
616
52
ss-ood ss-ood Public
Self-Supervised Learning for OOD Detection (NeurIPS 2019)
Python
269
30
anomaly-seg anomaly-seg Public
The Combined Anomalous Object Segmentation (CAOS) Be
... (truncated, 4 KB total)Resource ID:
941e0dbd9dddc0ba | Stable ID: sid_NOzECsq9Ly