Sotabase

Career

· Chief Scientist, AI Security Institute2024–
· Director, DeepMind2019–2023
· Founder, Eddy Systems2014–2015
· PhD in Computer Science, Stanford University2003–2007
· B.Sc. in Mathematics and Computer Science, California Institute of Technology1999–2003
· D. E. Shaw Research
· Software Engineer, Google Brain
· Research Scientist, OpenAI
· Otherlab
· Pixar
· Weta Digital

Publications (47)

This Paper Is Included in the Proceedings of the 12th Usenix Symposium on Operating Systems Design and Implementation (osdi '16). Tensorflow: a System for Large-scale Machine Learning Tensorflow: a System for Large-scale Machine Learning
19,241
cited
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
arXiv.org · 2016
11,560
cited
Fine-Tuning Language Models from Human Preferences
arXiv.org · 2019
2,248
cited
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
arXiv.org · 2021
1,531
cited
Improving language models by retrieving from trillions of tokens
International Conference on Machine Learning · 2021
1,460
cited
Ethical and social risks of harm from Language Models
arXiv.org · 2021
1,335
cited
Red Teaming Language Models with Language Models
Conference on Empirical Methods in Natural Language Processing · 2022
895
cited
Taxonomy of Risks posed by Language Models
Conference on Fairness, Accountability and Transparency · 2022
804
cited
Accelerating Large Language Model Decoding with Speculative Sampling
arXiv.org · 2023
688
cited
Improving alignment of dialogue agents via targeted human judgements
arXiv.org · 2022
638
cited
Solving math word problems with process- and outcome-based feedback
arXiv.org · 2022
572
cited
Reward learning from human preferences and demonstrations in Atari
Neural Information Processing Systems · 2018
447
cited
Invertible finite elements for robust simulation of large deformation
Symposium on Computer Animation · 2004
442
cited
AI safety via debate
arXiv.org · 2018
315
cited
Teaching language models to support answers with verified quotes
arXiv.org · 2022
309
cited
Robust quasistatic finite elements and flesh simulation
Symposium on Computer Animation · 2005
288
cited
DeepMath - Deep Sequence Models for Premise Selection
Neural Information Processing Systems · 2016
250
cited
Alignment of Language Agents
arXiv.org · 2021
208
cited
Efficient simulation of large bodies of water by coupling two and three dimensional techniques
ACM Transactions on Graphics · 2006
182
cited
Deep Network Guided Proof Search
Logic Programming and Automated Reasoning · 2017
166
cited
Sotabase
Geoffrey Irving | Researcher Profile | Sotabase | Sotabase