Collin Burns
AI alignment researcher; lead author of OpenAI's Weak-to-Strong Generalization; previously at Anthropic and now at the Center for AI Standards and Innovation.
- Role
- researcher
- Currently at
- Center for AI Standards and Innovation (CAISI)
- twitter.com/collinburns4
- GitHub
- github.com/collin-burns
- Scholar
- scholar.google.com/citations
- Papers
- 6
Cite
Notes
Only stored in your browser.
Authored papers
6Measuring Mathematical Problem Solving With the MATH Dataset
NeurIPS
Measuring Coding Challenge Competence With APPS
arXiv 2021
CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review
arXiv 2021
Measuring Massive Multitask Language Understanding
ICLR
Aligning AI With Shared Human Values
arXiv 2020
Interpreting Black Box Models via Hypothesis Testing
arXiv 2019
Affiliations
Frequent co-authors
10from 6 papers
Dan Hendrycks
director
Dawn Song
professor
Jacob Steinhardt
founder
Steven Basart
researcher
Akul Arora
researcher
Mantas Mazeika
researcher
Saurav Kadavath
researcher
Andrew Critch
Andy Zou
founder
Anya Chen