Sotabase

Career

· Member, MIT CSAIL Robot Locomotion Group2026–
· Researcher, Berkeley Laboratory of Information and System Sciences (BLISS)2020–
· Associate Professor, University of California, Berkeley2020–
· Assistant Professor, UC Berkeley2019–
· Associate Professor, UC Berkeley2019–
· Researcher, MIT CSAIL Robot Locomotion Group2010–

Publications (121)

Measuring Massive Multitask Language Understanding
International Conference on Learning Representations · 2020
6,871
cited
Measuring Mathematical Problem Solving With the MATH Dataset
NeurIPS Datasets and Benchmarks · 2021
4,229
cited
Concrete Problems in AI Safety
arXiv.org · 2016
2,821
cited
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
IEEE International Conference on Computer Vision · 2020
2,143
cited
Natural Adversarial Examples
Computer Vision and Pattern Recognition · 2019
1,768
cited
Jailbroken: How Does LLM Safety Training Fail?
Neural Information Processing Systems · 2023
1,483
cited
Certified Defenses against Adversarial Examples
International Conference on Learning Representations · 2018
992
cited
Measuring Coding Challenge Competence With APPS
NeurIPS Datasets and Benchmarks · 2021
940
cited
The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
arXiv.org · 2018
837
cited
Certified Defenses for Data Poisoning Attacks
Neural Information Processing Systems · 2017
832
cited
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
International Conference on Learning Representations · 2022
805
cited
Aligning AI With Shared Human Values
International Conference on Learning Representations · 2020
784
cited
Progress measures for grokking via mechanistic interpretability
International Conference on Learning Representations · 2023
655
cited
Scaling Out-of-Distribution Detection for Real-World Settings
International Conference on Machine Learning · 2022
603
cited
Discovering Latent Knowledge in Language Models Without Supervision
International Conference on Learning Representations · 2022
556
cited
Semidefinite relaxations for certifying robustness to adversarial examples
Neural Information Processing Systems · 2018
453
cited
Unsolved Problems in ML Safety
arXiv.org · 2021
352
cited
Eliciting Latent Predictions from Transformers with the Tuned Lens
arXiv.org · 2023
331
cited
Troubling Trends in Machine Learning Scholarship
Queue · 2018
328
cited
Learning from untrusted data
Symposium on the Theory of Computing · 2016
310
cited
Sotabase
Jacob Steinhardt | Researcher Profile | Sotabase | Sotabase