Brown-Cohen, Jonah
- Scalable AI Safety via Doubly-Efficient Debate
2023/11/23 by Jonah Brown-Cohen, Geoffrey Irving, Brown-Cohen, Jonah +3 · 1 voice · 13 citations
Computer Science · Social Sciences · #Adversarial Robustness in Machine Learning #Ethics and Social Impacts of AI #Privacy-Preserving Technologies in Data #cs.AI #cs.LG
- On scalable oversight with weak LLMs judging strong LLMs
2024/07/05 by Zachary Kenton, Noah Y. Siegel, Kenton, Zachary +19 · 1 voice · 13 citations
Computer Science · Decision Sciences · Social Sciences · #Multi-Agent Systems and Negotiation #Auction Theory and Applications #Access Control and Trust
- An Approach to Technical AGI Safety and Security
2025/04/02 by Shah, Rohin, Irpan, Alex, Turner, Alexander Matt +27 · 16 citations
#Artificial Intelligence (cs.AI) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models
2023/10/26 by Yu, Dingli, Kaur, Simran, Gupta, Arushi +3 · 6 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
- Formal Barriers to Longest-Chain Proof-of-Stake Protocols
2018/09/18 by Brown-Cohen, Jonah, Narayanan, Arvind, Psomas, Christos-Alexandros +1 · 2 citations
#Computer Science and Game Theory (cs.GT) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences
- Faster Algorithms and Constant Lower Bounds for the Worst-Case Expected\n Error
2021/12/27 by Jonah Brown-Cohen, Brown-Cohen, Jonah · 1 citation
Computer Science · Decision Sciences · Engineering · Mathematics · #Advanced Bandit Algorithms Research #Data Structures and Algorithms (cs.DS) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Numerical Methods and Algorithms #Sparse and Compressive Sensing Techniques #Statistical and numerical algorithms #Stochastic Gradient Optimization Techniques
- Avoiding Obfuscation with Prover-Estimator Debate
2025/06/16 by Jonah Brown-Cohen, Brown-Cohen, Jonah, Geoffrey Irving +6 · 1 voice · 4 citations
#cs.AI #cs.CC #cs.DS
- Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions
2023/06/09 by Korkmaz, Ezgi, Brown-Cohen, Jonah · 1 citation
#Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)