Sotabase

Career

· Head Of Mission Alignment, OpenAI2024–
· Research Intern, OpenAI2017–2017
· Research Scientist, OpenAI2017–2024
· Artificial Intelligence, UC Berkeley College of Engineering2014–2021
· Bachelor of Science (BS), Aerospace Engineering, University of Florida2009–2014
· Bachelor of Science (BS), Physics, University of Florida2009–2014

Publications (13)

GPT-4o System Card
arXiv.org · 2024
2,980
cited
On First-Order Meta-Learning Algorithms
arXiv.org · 2018
2,476
cited
Constrained Policy Optimization
International Conference on Machine Learning · 2017
1,614
cited
Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
International Conference on Machine Learning · 2020
367
cited
Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning
arXiv.org · 2017
249
cited
Variational Option Discovery Algorithms
arXiv.org · 2018
194
cited
Rule Based Rewards for Language Model Safety
Neural Information Processing Systems · 2024
105
cited
Towards Characterizing Divergence in Deep Q-Learning
arXiv.org · 2019
102
cited
Rule Based Rewards for Fine-Grained LLM Safety
13
cited
From KMMLU-Redux to Pro: A Professional Korean Benchmark Suite for LLM Evaluation
Conference on Empirical Methods in Natural Language Processing · 2025
2
cited
Easy Monotonic Policy Iteration
arXiv.org · 2016
LG ] 29 F eb 2 01 6 Easy Monotonic Policy Iteration
2018
Ray Splitting Model of O-X Mode Conversion
2011
Sotabase