Paul Christiano

Identifiers

• name variant Paul Christiano 0.60 · backfill

Papers (19)

1. Estimating the expected output of wide random MLPs more efficiently than sampling cs.LG · 2026 · author #6
2. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training cs.CR · 2024 · author #31
3. Training language models to follow instructions with human feedback cs.CL · 2022 · author #18
4. Recursively Summarizing Books with Human Feedback cs.CL · 2021 · author #7
5. Learning to summarize from human feedback cs.CL · 2020 · author #9
6. Fine-Tuning Language Models from Human Preferences cs.CL · 2019 · author #7
7. Supervising strong learners by amplifying weak experts cs.LG · 2018 · author #1
8. Unrestricted Adversarial Examples stat.ML · 2018 · author #5
9. AI safety via debate stat.ML · 2018 · author #2
10. Deep reinforcement learning from human preferences stat.ML · 2017 · author #1
11. A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models cs.LG · 2016 · author #2
12. Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model cs.RO · 2016 · author #1
13. Concrete Problems in AI Safety cs.AI · 2016 · author #4
14. Theano: A Python framework for fast computation of mathematical expressions cs.SC · 2016 · author #24
15. Collaborative prediction with expert advice cs.LG · 2016 · author #1
16. Provably Manipulation-Resistant Reputation Systems cs.GT · 2014 · author #1
17. Online Local Learning via Semidefinite Programming cs.LG · 2014 · author #1
18. Quantum Money from Hidden Subspaces quant-ph · 2012 · author #2
19. Electrical Flows, Laplacian Systems, and Faster Approximation of Maximum Flow in Undirected Graphs cs.DS · 2010 · author #1

Mentions

• 1203.4740 #2 · backfill · confidence 0.70 Paul Christiano
• 2605.05179 #6 · arxiv_oai · confidence 0.70 Paul Christiano
• 1010.2921 #1 · backfill · confidence 0.70 Paul Christiano
• 2009.01325 #9 · arxiv_oai · confidence 0.70 Paul Christiano
• 2109.10862 #7 · arxiv_oai · confidence 0.70 Paul Christiano
• 1706.03741 #1 · arxiv_oai · confidence 0.70 Paul Christiano

Frequent Coauthors

• Dario Amodei 6 shared papers
• Daniel M. Ziegler 4 shared papers
• Jan Leike 3 shared papers
• Jeff Wu 3 shared papers
• John Schulman 3 shared papers
• Long Ouyang 3 shared papers
• Nisan Stiennon 3 shared papers
• Ryan Lowe 3 shared papers
• Tom B. Brown 3 shared papers
• Alec Radford 2 shared papers
• Amanda Askell 2 shared papers
• Buck Shlegeris 2 shared papers
• Geoffrey Irving 2 shared papers
• Ian Goodfellow 2 shared papers
• Jacob Hilton 2 shared papers
• Pieter Abbeel 2 shared papers
• Aaron Courville 1 shared papers
• Adam Jermyn 1 shared papers
• Adriana Romero 1 shared papers
• Alberto Orlandi 1 shared papers