default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Dario Amodei
@inproceedings{DBLP:conf/acl/PerezRLNCHPOKKJ23,
author = {Ethan Perez and
Sam Ringer and
Kamile Lukosiute and
Karina Nguyen and
Edwin Chen and
Scott Heiner and
Craig Pettit and
Catherine Olsson and
Sandipan Kundu and
Saurav Kadavath and
Andy Jones and
Anna Chen and
Benjamin Mann and
Brian Israel and
Bryan Seethor and
Cameron McKinnon and
Christopher Olah and
Da Yan and
Daniela Amodei and
Dario Amodei and
Dawn Drain and
Dustin Li and
Eli Tran{-}Johnson and
Guro Khundadze and
Jackson Kernion and
James Landis and
Jamie Kerr and
Jared Mueller and
Jeeyoon Hyun and
Joshua Landau and
Kamal Ndousse and
Landon Goldberg and
Liane Lovitt and
Martin Lucas and
Michael Sellitto and
Miranda Zhang and
Neerav Kingsland and
Nelson Elhage and
Nicholas Joseph and
Noem{\'{\i}} Mercado and
Nova DasSarma and
Oliver Rausch and
Robin Larson and
Sam McCandlish and
Scott Johnston and
Shauna Kravec and
Sheer El Showk and
Tamera Lanham and
Timothy Telleen{-}Lawton and
Tom Brown and
Tom Henighan and
Tristan Hume and
Yuntao Bai and
Zac Hatfield{-}Dodds and
Jack Clark and
Samuel R. Bowman and
Amanda Askell and
Roger Grosse and
Danny Hernandez and
Deep Ganguli and
Evan Hubinger and
Nicholas Schiefer and
Jared Kaplan},
editor = {Anna Rogers and
Jordan L. Boyd{-}Graber and
Naoaki Okazaki},
title = {Discovering Language Model Behaviors with Model-Written Evaluations},
booktitle = {Findings of the Association for Computational Linguistics: {ACL} 2023,
Toronto, Canada, July 9-14, 2023},
pages = {13387--13434},
publisher = {Association for Computational Linguistics},
year = {2023},
url = {https://doi.org/10.18653/v1/2023.findings-acl.847},
doi = {10.18653/V1/2023.FINDINGS-ACL.847},
timestamp = {Thu, 10 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acl/PerezRLNCHPOKKJ23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-07459,
author = {Deep Ganguli and
Amanda Askell and
Nicholas Schiefer and
Thomas I. Liao and
Kamile Lukosiute and
Anna Chen and
Anna Goldie and
Azalia Mirhoseini and
Catherine Olsson and
Danny Hernandez and
Dawn Drain and
Dustin Li and
Eli Tran{-}Johnson and
Ethan Perez and
Jackson Kernion and
Jamie Kerr and
Jared Mueller and
Joshua Landau and
Kamal Ndousse and
Karina Nguyen and
Liane Lovitt and
Michael Sellitto and
Nelson Elhage and
Noem{\'{\i}} Mercado and
Nova DasSarma and
Oliver Rausch and
Robert Lasenby and
Robin Larson and
Sam Ringer and
Sandipan Kundu and
Saurav Kadavath and
Scott Johnston and
Shauna Kravec and
Sheer El Showk and
Tamera Lanham and
Timothy Telleen{-}Lawton and
Tom Henighan and
Tristan Hume and
Yuntao Bai and
Zac Hatfield{-}Dodds and
Ben Mann and
Dario Amodei and
Nicholas Joseph and
Sam McCandlish and
Tom Brown and
Christopher Olah and
Jack Clark and
Samuel R. Bowman and
Jared Kaplan},
title = {The Capacity for Moral Self-Correction in Large Language Models},
journal = {CoRR},
volume = {abs/2302.07459},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.07459},
doi = {10.48550/ARXIV.2302.07459},
eprinttype = {arXiv},
eprint = {2302.07459},
timestamp = {Thu, 23 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-07459.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/fat/GanguliHLABCCDD22,
author = {Deep Ganguli and
Danny Hernandez and
Liane Lovitt and
Amanda Askell and
Yuntao Bai and
Anna Chen and
Tom Conerly and
Nova DasSarma and
Dawn Drain and
Nelson Elhage and
Sheer El Showk and
Stanislav Fort and
Zac Hatfield{-}Dodds and
Tom Henighan and
Scott Johnston and
Andy Jones and
Nicholas Joseph and
Jackson Kernian and
Shauna Kravec and
Ben Mann and
Neel Nanda and
Kamal Ndousse and
Catherine Olsson and
Daniela Amodei and
Tom B. Brown and
Jared Kaplan and
Sam McCandlish and
Christopher Olah and
Dario Amodei and
Jack Clark},
title = {Predictability and Surprise in Large Generative Models},
booktitle = {FAccT '22: 2022 {ACM} Conference on Fairness, Accountability, and
Transparency, Seoul, Republic of Korea, June 21 - 24, 2022},
pages = {1747--1764},
publisher = {{ACM}},
year = {2022},
url = {https://doi.org/10.1145/3531146.3533229},
doi = {10.1145/3531146.3533229},
timestamp = {Sat, 03 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/fat/GanguliHLABCCDD22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-07785,
author = {Deep Ganguli and
Danny Hernandez and
Liane Lovitt and
Nova DasSarma and
Tom Henighan and
Andy Jones and
Nicholas Joseph and
Jackson Kernion and
Benjamin Mann and
Amanda Askell and
Yuntao Bai and
Anna Chen and
Tom Conerly and
Dawn Drain and
Nelson Elhage and
Sheer El Showk and
Stanislav Fort and
Zac Hatfield{-}Dodds and
Scott Johnston and
Shauna Kravec and
Neel Nanda and
Kamal Ndousse and
Catherine Olsson and
Daniela Amodei and
Dario Amodei and
Tom B. Brown and
Jared Kaplan and
Sam McCandlish and
Chris Olah and
Jack Clark},
title = {Predictability and Surprise in Large Generative Models},
journal = {CoRR},
volume = {abs/2202.07785},
year = {2022},
url = {https://arxiv.org/abs/2202.07785},
eprinttype = {arXiv},
eprint = {2202.07785},
timestamp = {Tue, 01 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-07785.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-05862,
author = {Yuntao Bai and
Andy Jones and
Kamal Ndousse and
Amanda Askell and
Anna Chen and
Nova DasSarma and
Dawn Drain and
Stanislav Fort and
Deep Ganguli and
Tom Henighan and
Nicholas Joseph and
Saurav Kadavath and
Jackson Kernion and
Tom Conerly and
Sheer El Showk and
Nelson Elhage and
Zac Hatfield{-}Dodds and
Danny Hernandez and
Tristan Hume and
Scott Johnston and
Shauna Kravec and
Liane Lovitt and
Neel Nanda and
Catherine Olsson and
Dario Amodei and
Tom B. Brown and
Jack Clark and
Sam McCandlish and
Chris Olah and
Benjamin Mann and
Jared Kaplan},
title = {Training a Helpful and Harmless Assistant with Reinforcement Learning
from Human Feedback},
journal = {CoRR},
volume = {abs/2204.05862},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.05862},
doi = {10.48550/ARXIV.2204.05862},
eprinttype = {arXiv},
eprint = {2204.05862},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-05862.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-10487,
author = {Danny Hernandez and
Tom B. Brown and
Tom Conerly and
Nova DasSarma and
Dawn Drain and
Sheer El Showk and
Nelson Elhage and
Zac Hatfield{-}Dodds and
Tom Henighan and
Tristan Hume and
Scott Johnston and
Benjamin Mann and
Chris Olah and
Catherine Olsson and
Dario Amodei and
Nicholas Joseph and
Jared Kaplan and
Sam McCandlish},
title = {Scaling Laws and Interpretability of Learning from Repeated Data},
journal = {CoRR},
volume = {abs/2205.10487},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.10487},
doi = {10.48550/ARXIV.2205.10487},
eprinttype = {arXiv},
eprint = {2205.10487},
timestamp = {Mon, 30 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-10487.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-05221,
author = {Saurav Kadavath and
Tom Conerly and
Amanda Askell and
Tom Henighan and
Dawn Drain and
Ethan Perez and
Nicholas Schiefer and
Zac Hatfield{-}Dodds and
Nova DasSarma and
Eli Tran{-}Johnson and
Scott Johnston and
Sheer El Showk and
Andy Jones and
Nelson Elhage and
Tristan Hume and
Anna Chen and
Yuntao Bai and
Sam Bowman and
Stanislav Fort and
Deep Ganguli and
Danny Hernandez and
Josh Jacobson and
Jackson Kernion and
Shauna Kravec and
Liane Lovitt and
Kamal Ndousse and
Catherine Olsson and
Sam Ringer and
Dario Amodei and
Tom Brown and
Jack Clark and
Nicholas Joseph and
Ben Mann and
Sam McCandlish and
Chris Olah and
Jared Kaplan},
title = {Language Models (Mostly) Know What They Know},
journal = {CoRR},
volume = {abs/2207.05221},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2207.05221},
doi = {10.48550/ARXIV.2207.05221},
eprinttype = {arXiv},
eprint = {2207.05221},
timestamp = {Mon, 03 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2207-05221.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-07858,
author = {Deep Ganguli and
Liane Lovitt and
Jackson Kernion and
Amanda Askell and
Yuntao Bai and
Saurav Kadavath and
Ben Mann and
Ethan Perez and
Nicholas Schiefer and
Kamal Ndousse and
Andy Jones and
Sam Bowman and
Anna Chen and
Tom Conerly and
Nova DasSarma and
Dawn Drain and
Nelson Elhage and
Sheer El Showk and
Stanislav Fort and
Zac Hatfield{-}Dodds and
Tom Henighan and
Danny Hernandez and
Tristan Hume and
Josh Jacobson and
Scott Johnston and
Shauna Kravec and
Catherine Olsson and
Sam Ringer and
Eli Tran{-}Johnson and
Dario Amodei and
Tom Brown and
Nicholas Joseph and
Sam McCandlish and
Chris Olah and
Jared Kaplan and
Jack Clark},
title = {Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors,
and Lessons Learned},
journal = {CoRR},
volume = {abs/2209.07858},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.07858},
doi = {10.48550/ARXIV.2209.07858},
eprinttype = {arXiv},
eprint = {2209.07858},
timestamp = {Mon, 03 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-07858.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-10652,
author = {Nelson Elhage and
Tristan Hume and
Catherine Olsson and
Nicholas Schiefer and
Tom Henighan and
Shauna Kravec and
Zac Hatfield{-}Dodds and
Robert Lasenby and
Dawn Drain and
Carol Chen and
Roger Grosse and
Sam McCandlish and
Jared Kaplan and
Dario Amodei and
Martin Wattenberg and
Christopher Olah},
title = {Toy Models of Superposition},
journal = {CoRR},
volume = {abs/2209.10652},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.10652},
doi = {10.48550/ARXIV.2209.10652},
eprinttype = {arXiv},
eprint = {2209.10652},
timestamp = {Wed, 28 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-10652.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-11895,
author = {Catherine Olsson and
Nelson Elhage and
Neel Nanda and
Nicholas Joseph and
Nova DasSarma and
Tom Henighan and
Ben Mann and
Amanda Askell and
Yuntao Bai and
Anna Chen and
Tom Conerly and
Dawn Drain and
Deep Ganguli and
Zac Hatfield{-}Dodds and
Danny Hernandez and
Scott Johnston and
Andy Jones and
Jackson Kernion and
Liane Lovitt and
Kamal Ndousse and
Dario Amodei and
Tom Brown and
Jack Clark and
Jared Kaplan and
Sam McCandlish and
Chris Olah},
title = {In-context Learning and Induction Heads},
journal = {CoRR},
volume = {abs/2209.11895},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.11895},
doi = {10.48550/ARXIV.2209.11895},
eprinttype = {arXiv},
eprint = {2209.11895},
timestamp = {Wed, 05 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-11895.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-03540,
author = {Samuel R. Bowman and
Jeeyoon Hyun and
Ethan Perez and
Edwin Chen and
Craig Pettit and
Scott Heiner and
Kamile Lukosiute and
Amanda Askell and
Andy Jones and
Anna Chen and
Anna Goldie and
Azalia Mirhoseini and
Cameron McKinnon and
Christopher Olah and
Daniela Amodei and
Dario Amodei and
Dawn Drain and
Dustin Li and
Eli Tran{-}Johnson and
Jackson Kernion and
Jamie Kerr and
Jared Mueller and
Jeffrey Ladish and
Joshua Landau and
Kamal Ndousse and
Liane Lovitt and
Nelson Elhage and
Nicholas Schiefer and
Nicholas Joseph and
Noem{\'{\i}} Mercado and
Nova DasSarma and
Robin Larson and
Sam McCandlish and
Sandipan Kundu and
Scott Johnston and
Shauna Kravec and
Sheer El Showk and
Stanislav Fort and
Timothy Telleen{-}Lawton and
Tom Brown and
Tom Henighan and
Tristan Hume and
Yuntao Bai and
Zac Hatfield{-}Dodds and
Ben Mann and
Jared Kaplan},
title = {Measuring Progress on Scalable Oversight for Large Language Models},
journal = {CoRR},
volume = {abs/2211.03540},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.03540},
doi = {10.48550/ARXIV.2211.03540},
eprinttype = {arXiv},
eprint = {2211.03540},
timestamp = {Tue, 15 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-03540.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-08073,
author = {Yuntao Bai and
Saurav Kadavath and
Sandipan Kundu and
Amanda Askell and
Jackson Kernion and
Andy Jones and
Anna Chen and
Anna Goldie and
Azalia Mirhoseini and
Cameron McKinnon and
Carol Chen and
Catherine Olsson and
Christopher Olah and
Danny Hernandez and
Dawn Drain and
Deep Ganguli and
Dustin Li and
Eli Tran{-}Johnson and
Ethan Perez and
Jamie Kerr and
Jared Mueller and
Jeffrey Ladish and
Joshua Landau and
Kamal Ndousse and
Kamile Lukosiute and
Liane Lovitt and
Michael Sellitto and
Nelson Elhage and
Nicholas Schiefer and
Noem{\'{\i}} Mercado and
Nova DasSarma and
Robert Lasenby and
Robin Larson and
Sam Ringer and
Scott Johnston and
Shauna Kravec and
Sheer El Showk and
Stanislav Fort and
Tamera Lanham and
Timothy Telleen{-}Lawton and
Tom Conerly and
Tom Henighan and
Tristan Hume and
Samuel R. Bowman and
Zac Hatfield{-}Dodds and
Ben Mann and
Dario Amodei and
Nicholas Joseph and
Sam McCandlish and
Tom Brown and
Jared Kaplan},
title = {Constitutional {AI:} Harmlessness from {AI} Feedback},
journal = {CoRR},
volume = {abs/2212.08073},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.08073},
doi = {10.48550/ARXIV.2212.08073},
eprinttype = {arXiv},
eprint = {2212.08073},
timestamp = {Mon, 02 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-08073.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-09251,
author = {Ethan Perez and
Sam Ringer and
Kamile Lukosiute and
Karina Nguyen and
Edwin Chen and
Scott Heiner and
Craig Pettit and
Catherine Olsson and
Sandipan Kundu and
Saurav Kadavath and
Andy Jones and
Anna Chen and
Ben Mann and
Brian Israel and
Bryan Seethor and
Cameron McKinnon and
Christopher Olah and
Da Yan and
Daniela Amodei and
Dario Amodei and
Dawn Drain and
Dustin Li and
Eli Tran{-}Johnson and
Guro Khundadze and
Jackson Kernion and
James Landis and
Jamie Kerr and
Jared Mueller and
Jeeyoon Hyun and
Joshua Landau and
Kamal Ndousse and
Landon Goldberg and
Liane Lovitt and
Martin Lucas and
Michael Sellitto and
Miranda Zhang and
Neerav Kingsland and
Nelson Elhage and
Nicholas Joseph and
Noem{\'{\i}} Mercado and
Nova DasSarma and
Oliver Rausch and
Robin Larson and
Sam McCandlish and
Scott Johnston and
Shauna Kravec and
Sheer El Showk and
Tamera Lanham and
Timothy Telleen{-}Lawton and
Tom Brown and
Tom Henighan and
Tristan Hume and
Yuntao Bai and
Zac Hatfield{-}Dodds and
Jack Clark and
Samuel R. Bowman and
Amanda Askell and
Roger Grosse and
Danny Hernandez and
Deep Ganguli and
Evan Hubinger and
Nicholas Schiefer and
Jared Kaplan},
title = {Discovering Language Model Behaviors with Model-Written Evaluations},
journal = {CoRR},
volume = {abs/2212.09251},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.09251},
doi = {10.48550/ARXIV.2212.09251},
eprinttype = {arXiv},
eprint = {2212.09251},
timestamp = {Mon, 02 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-09251.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-03374,
author = {Mark Chen and
Jerry Tworek and
Heewoo Jun and
Qiming Yuan and
Henrique Pond{\'{e}} de Oliveira Pinto and
Jared Kaplan and
Harri Edwards and
Yuri Burda and
Nicholas Joseph and
Greg Brockman and
Alex Ray and
Raul Puri and
Gretchen Krueger and
Michael Petrov and
Heidy Khlaaf and
Girish Sastry and
Pamela Mishkin and
Brooke Chan and
Scott Gray and
Nick Ryder and
Mikhail Pavlov and
Alethea Power and
Lukasz Kaiser and
Mohammad Bavarian and
Clemens Winter and
Philippe Tillet and
Felipe Petroski Such and
Dave Cummings and
Matthias Plappert and
Fotios Chantzis and
Elizabeth Barnes and
Ariel Herbert{-}Voss and
William Hebgen Guss and
Alex Nichol and
Alex Paino and
Nikolas Tezak and
Jie Tang and
Igor Babuschkin and
Suchir Balaji and
Shantanu Jain and
William Saunders and
Christopher Hesse and
Andrew N. Carr and
Jan Leike and
Joshua Achiam and
Vedant Misra and
Evan Morikawa and
Alec Radford and
Matthew Knight and
Miles Brundage and
Mira Murati and
Katie Mayer and
Peter Welinder and
Bob McGrew and
Dario Amodei and
Sam McCandlish and
Ilya Sutskever and
Wojciech Zaremba},
title = {Evaluating Large Language Models Trained on Code},
journal = {CoRR},
volume = {abs/2107.03374},
year = {2021},
url = {https://arxiv.org/abs/2107.03374},
eprinttype = {arXiv},
eprint = {2107.03374},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-03374.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-00861,
author = {Amanda Askell and
Yuntao Bai and
Anna Chen and
Dawn Drain and
Deep Ganguli and
Tom Henighan and
Andy Jones and
Nicholas Joseph and
Benjamin Mann and
Nova DasSarma and
Nelson Elhage and
Zac Hatfield{-}Dodds and
Danny Hernandez and
Jackson Kernion and
Kamal Ndousse and
Catherine Olsson and
Dario Amodei and
Tom B. Brown and
Jack Clark and
Sam McCandlish and
Chris Olah and
Jared Kaplan},
title = {A General Language Assistant as a Laboratory for Alignment},
journal = {CoRR},
volume = {abs/2112.00861},
year = {2021},
url = {https://arxiv.org/abs/2112.00861},
eprinttype = {arXiv},
eprint = {2112.00861},
timestamp = {Tue, 07 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-00861.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BrownMRSKDNSSAA20,
author = {Tom B. Brown and
Benjamin Mann and
Nick Ryder and
Melanie Subbiah and
Jared Kaplan and
Prafulla Dhariwal and
Arvind Neelakantan and
Pranav Shyam and
Girish Sastry and
Amanda Askell and
Sandhini Agarwal and
Ariel Herbert{-}Voss and
Gretchen Krueger and
Tom Henighan and
Rewon Child and
Aditya Ramesh and
Daniel M. Ziegler and
Jeffrey Wu and
Clemens Winter and
Christopher Hesse and
Mark Chen and
Eric Sigler and
Mateusz Litwin and
Scott Gray and
Benjamin Chess and
Jack Clark and
Christopher Berner and
Sam McCandlish and
Alec Radford and
Ilya Sutskever and
Dario Amodei},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Language Models are Few-Shot Learners},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html},
timestamp = {Thu, 25 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/BrownMRSKDNSSAA20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/StiennonO0ZLVRA20,
author = {Nisan Stiennon and
Long Ouyang and
Jeffrey Wu and
Daniel M. Ziegler and
Ryan Lowe and
Chelsea Voss and
Alec Radford and
Dario Amodei and
Paul F. Christiano},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Learning to summarize with human feedback},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/1f89885d556929e98d3ef9b86448f951-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/StiennonO0ZLVRA20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2001-08361,
author = {Jared Kaplan and
Sam McCandlish and
Tom Henighan and
Tom B. Brown and
Benjamin Chess and
Rewon Child and
Scott Gray and
Alec Radford and
Jeffrey Wu and
Dario Amodei},
title = {Scaling Laws for Neural Language Models},
journal = {CoRR},
volume = {abs/2001.08361},
year = {2020},
url = {https://arxiv.org/abs/2001.08361},
eprinttype = {arXiv},
eprint = {2001.08361},
timestamp = {Wed, 03 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2001-08361.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-14165,
author = {Tom B. Brown and
Benjamin Mann and
Nick Ryder and
Melanie Subbiah and
Jared Kaplan and
Prafulla Dhariwal and
Arvind Neelakantan and
Pranav Shyam and
Girish Sastry and
Amanda Askell and
Sandhini Agarwal and
Ariel Herbert{-}Voss and
Gretchen Krueger and
Tom Henighan and
Rewon Child and
Aditya Ramesh and
Daniel M. Ziegler and
Jeffrey Wu and
Clemens Winter and
Christopher Hesse and
Mark Chen and
Eric Sigler and
Mateusz Litwin and
Scott Gray and
Benjamin Chess and
Jack Clark and
Christopher Berner and
Sam McCandlish and
Alec Radford and
Ilya Sutskever and
Dario Amodei},
title = {Language Models are Few-Shot Learners},
journal = {CoRR},
volume = {abs/2005.14165},
year = {2020},
url = {https://arxiv.org/abs/2005.14165},
eprinttype = {arXiv},
eprint = {2005.14165},
timestamp = {Thu, 25 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-14165.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2009-01325,
author = {Nisan Stiennon and
Long Ouyang and
Jeff Wu and
Daniel M. Ziegler and
Ryan Lowe and
Chelsea Voss and
Alec Radford and
Dario Amodei and
Paul F. Christiano},
title = {Learning to summarize from human feedback},
journal = {CoRR},
volume = {abs/2009.01325},
year = {2020},
url = {https://arxiv.org/abs/2009.01325},
eprinttype = {arXiv},
eprint = {2009.01325},
timestamp = {Thu, 01 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2009-01325.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-14701,
author = {Tom Henighan and
Jared Kaplan and
Mor Katz and
Mark Chen and
Christopher Hesse and
Jacob Jackson and
Heewoo Jun and
Tom B. Brown and
Prafulla Dhariwal and
Scott Gray and
Chris Hallacy and
Benjamin Mann and
Alec Radford and
Aditya Ramesh and
Nick Ryder and
Daniel M. Ziegler and
John Schulman and
Dario Amodei and
Sam McCandlish},
title = {Scaling Laws for Autoregressive Generative Modeling},
journal = {CoRR},
volume = {abs/2010.14701},
year = {2020},
url = {https://arxiv.org/abs/2010.14701},
eprinttype = {arXiv},
eprint = {2010.14701},
timestamp = {Thu, 25 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-14701.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-08593,
author = {Daniel M. Ziegler and
Nisan Stiennon and
Jeffrey Wu and
Tom B. Brown and
Alec Radford and
Dario Amodei and
Paul F. Christiano and
Geoffrey Irving},
title = {Fine-Tuning Language Models from Human Preferences},
journal = {CoRR},
volume = {abs/1909.08593},
year = {2019},
url = {http://arxiv.org/abs/1909.08593},
eprinttype = {arXiv},
eprint = {1909.08593},
timestamp = {Thu, 01 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-08593.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/IbarzLPILA18,
author = {Borja Ibarz and
Jan Leike and
Tobias Pohlen and
Geoffrey Irving and
Shane Legg and
Dario Amodei},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {Reward learning from human preferences and demonstrations in Atari},
booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference
on Neural Information Processing Systems 2018, NeurIPS 2018, December
3-8, 2018, Montr{\'{e}}al, Canada},
pages = {8022--8034},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/8cbe9ce23f42628c98f80fa0fac8b19a-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/IbarzLPILA18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-07228,
author = {Miles Brundage and
Shahar Avin and
Jack Clark and
Helen Toner and
Peter Eckersley and
Ben Garfinkel and
Allan Dafoe and
Paul Scharre and
Thomas Zeitzoff and
Bobby Filar and
Hyrum S. Anderson and
Heather Roff and
Gregory C. Allen and
Jacob Steinhardt and
Carrick Flynn and
Se{\'{a}}n {\'{O}} h{\'{E}}igeartaigh and
Simon Beard and
Haydn Belfield and
Sebastian Farquhar and
Clare Lyle and
Rebecca Crootof and
Owain Evans and
Michael Page and
Joanna Bryson and
Roman Yampolskiy and
Dario Amodei},
title = {The Malicious Use of Artificial Intelligence: Forecasting, Prevention,
and Mitigation},
journal = {CoRR},
volume = {abs/1802.07228},
year = {2018},
url = {http://arxiv.org/abs/1802.07228},
eprinttype = {arXiv},
eprint = {1802.07228},
timestamp = {Sat, 23 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1802-07228.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-00899,
author = {Geoffrey Irving and
Paul F. Christiano and
Dario Amodei},
title = {{AI} safety via debate},
journal = {CoRR},
volume = {abs/1805.00899},
year = {2018},
url = {http://arxiv.org/abs/1805.00899},
eprinttype = {arXiv},
eprint = {1805.00899},
timestamp = {Thu, 01 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1805-00899.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1807-10299,
author = {Joshua Achiam and
Harrison Edwards and
Dario Amodei and
Pieter Abbeel},
title = {Variational Option Discovery Algorithms},
journal = {CoRR},
volume = {abs/1807.10299},
year = {2018},
url = {http://arxiv.org/abs/1807.10299},
eprinttype = {arXiv},
eprint = {1807.10299},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1807-10299.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1810-08575,
author = {Paul F. Christiano and
Buck Shlegeris and
Dario Amodei},
title = {Supervising strong learners by amplifying weak experts},
journal = {CoRR},
volume = {abs/1810.08575},
year = {2018},
url = {http://arxiv.org/abs/1810.08575},
eprinttype = {arXiv},
eprint = {1810.08575},
timestamp = {Thu, 01 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1810-08575.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-06521,
author = {Borja Ibarz and
Jan Leike and
Tobias Pohlen and
Geoffrey Irving and
Shane Legg and
Dario Amodei},
title = {Reward learning from human preferences and demonstrations in Atari},
journal = {CoRR},
volume = {abs/1811.06521},
year = {2018},
url = {http://arxiv.org/abs/1811.06521},
eprinttype = {arXiv},
eprint = {1811.06521},
timestamp = {Sun, 25 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-06521.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-06162,
author = {Sam McCandlish and
Jared Kaplan and
Dario Amodei and
OpenAI Dota Team},
title = {An Empirical Model of Large-Batch Training},
journal = {CoRR},
volume = {abs/1812.06162},
year = {2018},
url = {http://arxiv.org/abs/1812.06162},
eprinttype = {arXiv},
eprint = {1812.06162},
timestamp = {Tue, 01 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-06162.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/NeelakantanLAMA17,
author = {Arvind Neelakantan and
Quoc V. Le and
Mart{\'{\i}}n Abadi and
Andrew McCallum and
Dario Amodei},
title = {Learning a Natural Language Interface with Neural Programmer},
booktitle = {5th International Conference on Learning Representations, {ICLR} 2017,
Toulon, France, April 24-26, 2017, Conference Track Proceedings},
publisher = {OpenReview.net},
year = {2017},
url = {https://openreview.net/forum?id=ry2YOrcge},
timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/NeelakantanLAMA17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ChristianoLBMLA17,
author = {Paul F. Christiano and
Jan Leike and
Tom B. Brown and
Miljan Martic and
Shane Legg and
Dario Amodei},
editor = {Isabelle Guyon and
Ulrike von Luxburg and
Samy Bengio and
Hanna M. Wallach and
Rob Fergus and
S. V. N. Vishwanathan and
Roman Garnett},
title = {Deep Reinforcement Learning from Human Preferences},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, December 4-9, 2017,
Long Beach, CA, {USA}},
pages = {4299--4307},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/d5e2c0adad503c91f91df240d0cd4e49-Abstract.html},
timestamp = {Thu, 21 Jan 2021 13:58:27 +0100},
biburl = {https://dblp.org/rec/conf/nips/ChristianoLBMLA17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1706-03741,
author = {Paul F. Christiano and
Jan Leike and
Tom B. Brown and
Miljan Martic and
Shane Legg and
Dario Amodei},
title = {Deep reinforcement learning from human preferences},
journal = {CoRR},
volume = {abs/1706.03741},
year = {2017},
url = {http://arxiv.org/abs/1706.03741},
eprinttype = {arXiv},
eprint = {1706.03741},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1706-03741.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AmodeiABCCCCCCD16,
author = {Dario Amodei and
Sundaram Ananthanarayanan and
Rishita Anubhai and
Jingliang Bai and
Eric Battenberg and
Carl Case and
Jared Casper and
Bryan Catanzaro and
Jingdong Chen and
Mike Chrzanowski and
Adam Coates and
Greg Diamos and
Erich Elsen and
Jesse H. Engel and
Linxi Fan and
Christopher Fougner and
Awni Y. Hannun and
Billy Jun and
Tony Han and
Patrick LeGresley and
Xiangang Li and
Libby Lin and
Sharan Narang and
Andrew Y. Ng and
Sherjil Ozair and
Ryan Prenger and
Sheng Qian and
Jonathan Raiman and
Sanjeev Satheesh and
David Seetapun and
Shubho Sengupta and
Chong Wang and
Yi Wang and
Zhiqian Wang and
Bo Xiao and
Yan Xie and
Dani Yogatama and
Jun Zhan and
Zhenyao Zhu},
editor = {Maria{-}Florina Balcan and
Kilian Q. Weinberger},
title = {Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin},
booktitle = {Proceedings of the 33nd International Conference on Machine Learning,
{ICML} 2016, New York City, NY, USA, June 19-24, 2016},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {48},
pages = {173--182},
publisher = {JMLR.org},
year = {2016},
url = {http://proceedings.mlr.press/v48/amodei16.html},
timestamp = {Mon, 23 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/AmodeiABCCCCCCD16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AmodeiOSCSM16,
author = {Dario Amodei and
Chris Olah and
Jacob Steinhardt and
Paul F. Christiano and
John Schulman and
Dan Man{\'{e}}},
title = {Concrete Problems in {AI} Safety},
journal = {CoRR},
volume = {abs/1606.06565},
year = {2016},
url = {http://arxiv.org/abs/1606.06565},
eprinttype = {arXiv},
eprint = {1606.06565},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AmodeiOSCSM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/NeelakantanLAMA16,
author = {Arvind Neelakantan and
Quoc V. Le and
Mart{\'{\i}}n Abadi and
Andrew McCallum and
Dario Amodei},
title = {Learning a Natural Language Interface with Neural Programmer},
journal = {CoRR},
volume = {abs/1611.08945},
year = {2016},
url = {http://arxiv.org/abs/1611.08945},
eprinttype = {arXiv},
eprint = {1611.08945},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/NeelakantanLAMA16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AmodeiABCCCCCCD15,
author = {Dario Amodei and
Rishita Anubhai and
Eric Battenberg and
Carl Case and
Jared Casper and
Bryan Catanzaro and
Jingdong Chen and
Mike Chrzanowski and
Adam Coates and
Greg Diamos and
Erich Elsen and
Jesse H. Engel and
Linxi Fan and
Christopher Fougner and
Tony Han and
Awni Y. Hannun and
Billy Jun and
Patrick LeGresley and
Libby Lin and
Sharan Narang and
Andrew Y. Ng and
Sherjil Ozair and
Ryan Prenger and
Jonathan Raiman and
Sanjeev Satheesh and
David Seetapun and
Shubho Sengupta and
Yi Wang and
Zhiqian Wang and
Chong Wang and
Bo Xiao and
Dani Yogatama and
Jun Zhan and
Zhenyao Zhu},
title = {Deep Speech 2: End-to-End Speech Recognition in English and Mandarin},
journal = {CoRR},
volume = {abs/1512.02595},
year = {2015},
url = {http://arxiv.org/abs/1512.02595},
eprinttype = {arXiv},
eprint = {1512.02595},
timestamp = {Mon, 23 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/AmodeiABCCCCCCD15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ploscb/TkacikMASBB14,
author = {Gasper Tkacik and
Olivier Marre and
Dario Amodei and
Elad Schneidman and
William Bialek and
Michael J. Berry II},
title = {Searching for Collective Behavior in a Large Network of Sensory Neurons},
journal = {PLoS Comput. Biol.},
volume = {10},
number = {1},
year = {2014},
url = {https://doi.org/10.1371/journal.pcbi.1003408},
doi = {10.1371/JOURNAL.PCBI.1003408},
timestamp = {Thu, 10 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ploscb/TkacikMASBB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ficn/MarblestoneZMSCGASKDSAMCRBCK13,
author = {Adam H. Marblestone and
Bradley M. Zamft and
Yael Maguire and
Mikhail G. Shapiro and
Thaddeus Cybulski and
Joshua I. Glaser and
Dario Amodei and
P. Benjamin Stranges and
Reza Kalhor and
David Dalrymple and
Dongjin Seo and
Elad Alon and
Michel M. Maharbiz and
Jose M. Carmena and
Jan M. Rabaey and
Edward S. Boyden III and
George M. Church and
Konrad P. K{\"{o}}rding},
title = {Physical principles for scalable neural recording},
journal = {Frontiers Comput. Neurosci.},
volume = {7},
pages = {137},
year = {2013},
url = {https://doi.org/10.3389/fncom.2013.00137},
doi = {10.3389/FNCOM.2013.00137},
timestamp = {Sat, 23 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ficn/MarblestoneZMSCGASKDSAMCRBCK13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-08-21 21:29 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
