Christiano, Paul
- Training language models to follow instructions with human feedback
2022/03/04 by Long Ouyang, Jeff Wu, Ouyang, Long +38 · 9 voices · 2543 citations
Computer Science · #Topic Modeling #Natural Language Processing Techniques #Explainable Artificial Intelligence (XAI)
- Concrete Problems in AI Safety
2016/06/21 by Dario Amodei, Amodei, Dario, Chris Olah +9 · 7 voices · 213 citations
#cs.AI #cs.LG
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
2024/01/10 by Evan Hubinger, Carson Denison, Hubinger, Evan +77 · 18 voices · 99 citations
Computer Science · Social Sciences · #Adversarial Robustness in Machine Learning #Ethics and Social Impacts of AI #Topic Modeling #cs.AI #cs.CL #cs.CR #cs.LG #cs.SE
- Learning to summarize from human feedback
2020/09/02 by Nisan Stiennon, Long Ouyang, Stiennon, Nisan +16 · 3 voices · 338 citations
Computer Science · #Topic Modeling #Natural Language Processing Techniques #Multimodal Machine Learning Applications
- Deep reinforcement learning from human preferences
2017/06/12 by Paul Christiano, Paul F. Christiano, Jan Leike +11 · 1 voice · 578 citations
Computer Science · Engineering · Mathematics · #Artificial Intelligence (cs.AI) #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Reinforcement Learning in Robotics #Robot Manipulation and Learning #cs.AI #cs.HC #cs.LG #stat.ML
- AI safety via debate
2018/05/02 by Geoffrey Irving, Paul F. Christiano, Paul Christiano +4 · 3 voices · 72 citations
Computer Science · Mathematics · #Computability, Logic, AI Algorithms #Multi-Agent Systems and Negotiation #Reinforcement Learning in Robotics #cs.LG #stat.ML
- Fine-Tuning Language Models from Human Preferences
2019/09/18 by Daniel M. Ziegler, Nisan Stiennon, Ziegler, Daniel M. +13 · 251 citations
Computer Science · #Topic Modeling #Natural Language Processing Techniques #Speech and dialogue systems
- Supervising strong learners by amplifying weak experts
2018/10/19 by Paul F. Christiano, Christiano, Paul, Buck Shlegeris +3 · 26 citations
Computer Science · Decision Sciences · #Reinforcement Learning in Robotics #Advanced Bandit Algorithms Research #Machine Learning and Algorithms
- Recursively Summarizing Books with Human Feedback
2021/09/22 by Jeff Wu, Wu, Jeff, Long Ouyang +11 · 15 citations
Computer Science · #Advanced Text Analysis Techniques #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling
- Electrical Flows, Laplacian Systems, and Faster Approximation of Maximum Flow in Undirected Graphs
2010/10/14 by Paul F. Christiano, Christiano, Paul, Jonathan A. Kelner +7 · 7 citations
Computer Science · #Complexity and Algorithms in Graphs #Advanced Graph Theory Research #Optimization and Search Problems
- Model evaluation for extreme risks
2023/05/24 by Toby Shevlane, Shevlane, Toby, Sebastian Farquhar +39 · 16 citations
Computer Science · #Software Engineering Research #Software Reliability and Analysis Research #Information and Cyber Security
- Robust Cooperation in the Prisoner's Dilemma: Program Equilibrium via Provability Logic
2014/01/22 by Mihaly Barasz, Paul Christiano, Barasz, Mihaly +9 · 1 voice · 2 citations
Computer Science · #Computer Science and Game Theory (cs.GT) #F.4.1 #FOS: Computer and information sciences #Logic in Computer Science (cs.LO) #cs.GT #cs.LO
- A Cryptographic Test of Quantumness and Certifiable Randomness from a\n Single Quantum Device
2018/04/02 by Zvika Brakerski, Paul Christiano, Brakerski, Zvika +7 · 8 citations
Computer Science · #Computational Complexity (cs.CC) #Cryptographic Implementations and Security #Cryptography and Data Security #FOS: Computer and information sciences #FOS: Physical sciences #Quantum Computing Algorithms and Architecture #Quantum Physics (quant-ph)
- A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
2016/11/11 by Finn, Chelsea, Christiano, Paul, Abbeel, Pieter +1 · 7 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Quantum Money from Hidden Subspaces
2012/03/21 by Aaronson, Scott, Christiano, Paul · 5 citations
#Computational Complexity (cs.CC) #FOS: Computer and information sciences #FOS: Physical sciences #Quantum Physics (quant-ph)
- Evaluating Language-Model Agents on Realistic Autonomous Tasks
2023/12/18 by Kinniment, Megan, Sato, Lucas Jun Koba, Du, Haoxing +10 · 11 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model
2016/10/11 by Christiano, Paul, Shah, Zain, Mordatch, Igor +5 · 5 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Robotics (cs.RO) #Systems and Control (eess.SY) #electronic engineering #information engineering
- Theano: A Python framework for fast computation of mathematical expressions
2016/05/09 by The Theano Development Team, Al-Rfou, Rami, Alain, Guillaume +110 · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Mathematical Software (cs.MS) #Symbolic Computation (cs.SC)
- International Scientific Report on the Safety of Advanced AI (Interim Report)
2024/11/05 by Bengio, Yoshua, Mindermann, Sören, Privitera, Daniel +41 · 2 citations
#Artificial Intelligence (cs.AI) #Computers and Society (cs.CY) #FOS: Computer and information sciences
- Provably Manipulation-Resistant Reputation Systems
2014/11/05 by Paul F. Christiano, Christiano, Paul · 1 citation
Decision Sciences · #Auction Theory and Applications #Advanced Bandit Algorithms Research #Game Theory and Applications