{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T07:49:39Z","timestamp":1777535379848,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":203,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T00:00:00Z","timestamp":1686528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000275","name":"Leverhulme Trust","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000275","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EPSRC"},{"DOI":"10.13039\/100014895","name":"Open Philanthropy Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014895","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,12]]},"DOI":"10.1145\/3593013.3594033","type":"proceedings-article","created":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T14:40:46Z","timestamp":1686580846000},"page":"651-666","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":92,"title":["Harms from Increasingly Agentic Algorithmic Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7547-3951","authenticated-orcid":false,"given":"Alan","family":"Chan","sequence":"first","affiliation":[{"name":"Mila, Universit\u00e9 de Montr\u00e9al, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9273-8780","authenticated-orcid":false,"given":"Rebecca","family":"Salganik","sequence":"additional","affiliation":[{"name":"Mila, Universit\u00e9 de Montr\u00e9al, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4580-9997","authenticated-orcid":false,"given":"Alva","family":"Markelius","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1061-307X","authenticated-orcid":false,"given":"Chris","family":"Pang","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8991-0881","authenticated-orcid":false,"given":"Nitarshan","family":"Rajkumar","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4387-8407","authenticated-orcid":false,"given":"Dmitrii","family":"Krasheninnikov","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6868-5304","authenticated-orcid":false,"given":"Lauro","family":"Langosco","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5831-8885","authenticated-orcid":false,"given":"Zhonghao","family":"He","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5124-1192","authenticated-orcid":false,"given":"Yawen","family":"Duan","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0716-8071","authenticated-orcid":false,"given":"Micah","family":"Carroll","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4476-5558","authenticated-orcid":false,"given":"Michelle","family":"Lin","sequence":"additional","affiliation":[{"name":"McGill University, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2125-9383","authenticated-orcid":false,"given":"Alex","family":"Mayhew","sequence":"additional","affiliation":[{"name":"University of Western Ontario, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7032-716X","authenticated-orcid":false,"given":"Katherine","family":"Collins","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9715-5442","authenticated-orcid":false,"given":"Maryam","family":"Molamohammadi","sequence":"additional","affiliation":[{"name":"Mila, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7526-0753","authenticated-orcid":false,"given":"John","family":"Burden","sequence":"additional","affiliation":[{"name":"Center for the Study of Existential Risk, University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5390-0585","authenticated-orcid":false,"given":"Wanru","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5281-2428","authenticated-orcid":false,"given":"Shalaleh","family":"Rismani","sequence":"additional","affiliation":[{"name":"McGill University, Mila, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8453-3557","authenticated-orcid":false,"given":"Konstantinos","family":"Voudouris","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4611-1668","authenticated-orcid":false,"given":"Umang","family":"Bhatt","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1915-7158","authenticated-orcid":false,"given":"Adrian","family":"Weller","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7256-0937","authenticated-orcid":false,"given":"David","family":"Krueger","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7370-0978","authenticated-orcid":false,"given":"Tegan","family":"Maharaj","sequence":"additional","affiliation":[{"name":"University of Toronto, Canada"}]}],"member":"320","published-online":{"date-parts":[[2023,6,12]]},"reference":[{"key":"e_1_3_2_1_2_1","unstructured":"2022. Establishing a pro-innovation approach to regulating AI. Technical Report. Office for Artificial Intelligence. https:\/\/www.gov.uk\/government\/publications\/establishing-a-pro-innovation-approach-to-regulating-ai\/establishing-a-pro-innovation-approach-to-regulating-ai-policy-statement"},{"key":"e_1_3_2_1_3_1","unstructured":"2023. Auto-GPT: An Autonomous GPT-4 Experiment. https:\/\/github.com\/Significant-Gravitas\/Auto-GPT original-date: 2023-03-16T09:21:07Z."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462563"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372871"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3284751.3284761"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462624"},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=xNOVfCCvDpM","author":"Adebayo Julius","year":"2022","unstructured":"Julius Adebayo, Michael Muelly, Harold Abelson, and Been Kim. 2022. Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=xNOVfCCvDpM"},{"key":"e_1_3_2_1_9_1","unstructured":"Adept. 2022. ACT-1: Transformer for Actions. https:\/\/www.adept.ai\/act"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","unstructured":"M. Mehdi Afsar Trafford Crump and Behrouz Far. 2022. Reinforcement learning based recommender systems: A survey. https:\/\/doi.org\/10.48550\/arXiv.2101.06286 arXiv:2101.06286 [cs].","DOI":"10.48550\/arXiv.2101.06286"},{"key":"e_1_3_2_1_11_1","volume-title":"Using Large Language Models to Simulate Multiple Humans. arXiv preprint arXiv:2208.10264","author":"Aher Gati","year":"2022","unstructured":"Gati Aher, Rosa I Arriaga, and Adam Tauman Kalai. 2022. Using Large Language Models to Simulate Multiple Humans. arXiv preprint arXiv:2208.10264 (2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katie Millican Malcolm Reynolds Roman Ring Eliza Rutherford Serkan Cabi Tengda Han Zhitao Gong Sina Samangooei Marianne Monteiro Jacob Menick Sebastian Borgeaud Andrew Brock Aida Nematzadeh Sahand Sharifzadeh Mikolaj Binkowski Ricardo Barreira Oriol Vinyals Andrew Zisserman and Karen Simonyan. 2022. Flamingo: a Visual Language Model for Few-Shot Learning. https:\/\/doi.org\/10.48550\/arXiv.2204.14198 arXiv:2204.14198 [cs].","DOI":"10.48550\/arXiv.2204.14198"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1257\/jep.31.2.211"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Jacob Andreas. 2022. Language Models as Agent Models. https:\/\/doi.org\/10.48550\/arXiv.2212.01681 arXiv:2212.01681 [cs].","DOI":"10.48550\/arXiv.2212.01681"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1093\/jla"},{"key":"e_1_3_2_1_16_1","unstructured":"Association for Computing Machinery (ACM). 2019. \"Reinforcement Learning for Recommender Systems: A Case Study on Youtube \" by Minmin Chen. https:\/\/www.youtube.com\/watch?v=HEqQ2_1XRTs"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade9097"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372859"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 1st Conference on Fairness, Accountability and Transparency(Proceedings of Machine Learning Research","volume":"76","author":"Barabas Chelsea","year":"2018","unstructured":"Chelsea Barabas, Madars Virza, Karthik Dinakar, Joichi Ito, and Jonathan Zittrain. 2018. Interventions over Predictions: Reframing the Ethical Debate for Actuarial Risk Assessment. In Proceedings of the 1st Conference on Fairness, Accountability and Transparency(Proceedings of Machine Learning Research, Vol. 81), Sorelle A. Friedler and Christo Wilson (Eds.). PMLR, 62\u201376. https:\/\/proceedings.mlr.press\/v81\/barabas18a.html"},{"key":"e_1_3_2_1_20_1","volume-title":"Emerging Technologies, Prestige Motivations and the Dynamics of International Competition. (Jan","author":"Barnhart Joslyn","year":"2022","unstructured":"Joslyn Barnhart. 2022. Emerging Technologies, Prestige Motivations and the Dynamics of International Competition. (Jan. 2022). https:\/\/www.governance.ai\/research-paper\/emerging-technologies-prestige-motivations-and-the-dynamics-of-international-competition"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.08028"},{"key":"e_1_3_2_1_22_1","volume-title":"Autonomous Robots: From Biological Inspiration to Implementation and Control","author":"Bekey G.A.","year":"2005","unstructured":"G.A. Bekey. 2005. Autonomous Robots: From Biological Inspiration to Implementation and Control. MIT Press. https:\/\/books.google.ca\/books?id=3xwfia2DpmoC"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_25_1","unstructured":"Sarah Bird Solon Barocas Kate Crawford Fernando Diaz and Hanna Wallach. 2016. Exploring or Exploiting? Social and Ethical Implications of Autonomous Experimentation in AI. https:\/\/papers.ssrn.com\/abstract=2846909"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533157"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533204"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533111"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Rishi Bommasani Drew A. Hudson Ehsan Adeli Russ Altman Simran Arora Sydney von Arx Michael S. Bernstein Jeannette Bohg Antoine Bosselut Emma Brunskill Erik Brynjolfsson Shyamal Buch Dallas Card Rodrigo Castellon Niladri Chatterji Annie Chen Kathleen Creel Jared Quincy Davis Dora Demszky Chris Donahue Moussa Doumbouya Esin Durmus Stefano Ermon John Etchemendy Kawin Ethayarajh Li Fei-Fei Chelsea Finn Trevor Gale Lauren Gillespie Karan Goel Noah Goodman Shelby Grossman Neel Guha Tatsunori Hashimoto Peter Henderson John Hewitt Daniel E. Ho Jenny Hong Kyle Hsu Jing Huang Thomas Icard Saahil Jain Dan Jurafsky Pratyusha Kalluri Siddharth Karamcheti Geoff Keeling Fereshte Khani Omar Khattab Pang Wei Koh Mark Krass Ranjay Krishna Rohith Kuditipudi Ananya Kumar Faisal Ladhak Mina Lee Tony Lee Jure Leskovec Isabelle Levent Xiang Lisa Li Xuechen Li Tengyu Ma Ali Malik Christopher D. Manning Suvir Mirchandani Eric Mitchell Zanele Munyikwa Suraj Nair Avanika Narayan Deepak Narayanan Ben Newman Allen Nie Juan Carlos Niebles Hamed Nilforoshan Julian Nyarko Giray Ogut Laurel Orr Isabel Papadimitriou Joon Sung Park Chris Piech Eva Portelance Christopher Potts Aditi Raghunathan Rob Reich Hongyu Ren Frieda Rong Yusuf Roohani Camilo Ruiz Jack Ryan Christopher R\u00e9 Dorsa Sadigh Shiori Sagawa Keshav Santhanam Andy Shih Krishnan Srinivasan Alex Tamkin Rohan Taori Armin W. Thomas Florian Tram\u00e8r Rose E. Wang William Wang Bohan Wu Jiajun Wu Yuhuai Wu Sang Michael Xie Michihiro Yasunaga Jiaxuan You Matei Zaharia Michael Zhang Tianyi Zhang Xikun Zhang Yuhui Zhang Lucia Zheng Kaitlyn Zhou and Percy Liang. 2022. On the Opportunities and Risks of Foundation Models. https:\/\/doi.org\/10.48550\/arXiv.2108.07258 arXiv:2108.07258 [cs].","DOI":"10.48550\/arXiv.2108.07258"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1706588114"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1377\/hlthaff.2021.01394"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1177\/1077699019859901"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"key":"e_1_3_2_1_36_1","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, Vol. 33. Curran Associates, Inc., 1877\u20131901. https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","unstructured":"Miles Brundage Shahar Avin Jasmine Wang Haydn Belfield Gretchen Krueger Gillian Hadfield Heidy Khlaaf Jingying Yang Helen Toner Ruth Fong Tegan Maharaj Pang Wei Koh Sara Hooker Jade Leung Andrew Trask Emma Bluemke Jonathan Lebensold Cullen O\u2019Keefe Mark Koren Th\u00e9o Ryffel J. B. Rubinovitz Tamay Besiroglu Federica Carugati Jack Clark Peter Eckersley Sarah de Haas Maritza Johnson Ben Laurie Alex Ingerman Igor Krawczuk Amanda Askell Rosario Cammarota Andrew Lohn David Krueger Charlotte Stix Peter Henderson Logan Graham Carina Prunkl Bianca Martin Elizabeth Seger Noa Zilberman Se\u00e1n \u00d3 h\u00c9igeartaigh Frens Kroeger Girish Sastry Rebecca Kagan Adrian Weller Brian Tse Elizabeth Barnes Allan Dafoe Paul Scharre Ariel Herbert-Voss Martijn Rasser Shagun Sodhani Carrick Flynn Thomas Krendl Gilbert Lisa Dyer Saif Khan Yoshua Bengio and Markus Anderljung. 2020. Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims. https:\/\/doi.org\/10.48550\/arXiv.2004.07213 arXiv:2004.07213 [cs].","DOI":"10.48550\/arXiv.2004.07213"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the 1st Conference on Fairness, Accountability and Transparency(Proceedings of Machine Learning Research","volume":"91","author":"Buolamwini Joy","year":"2018","unstructured":"Joy Buolamwini and Timnit Gebru. 2018. Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification. In Proceedings of the 1st Conference on Fairness, Accountability and Transparency(Proceedings of Machine Learning Research, Vol. 81), Sorelle A. Friedler and Christo Wilson (Eds.). PMLR, 77\u201391. https:\/\/proceedings.mlr.press\/v81\/buolamwini18a.html"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-soc-090820-020800"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","unstructured":"Ethan Caballero Kshitij Gupta Irina Rish and David Krueger. 2023. Broken Neural Scaling Laws. https:\/\/doi.org\/10.48550\/arXiv.2210.14891 arXiv:2210.14891 [cs].","DOI":"10.48550\/arXiv.2210.14891"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.17351\/ests2020.277"},{"key":"e_1_3_2_1_42_1","first-page":"2640","volume-title":"Proceedings of the 39th International Conference on Machine Learning. PMLR, 2686\u20132708","author":"Carroll Micah D.","year":"2022","unstructured":"Micah D. Carroll, Anca Dragan, Stuart Russell, and Dylan Hadfield-Menell. 2022. Estimating and Penalizing Induced Preference Shifts in Recommender Systems. In Proceedings of the 39th International Conference on Machine Learning. PMLR, 2686\u20132708. https:\/\/proceedings.mlr.press\/v162\/carroll22a.html ISSN: 2640-3498."},{"key":"e_1_3_2_1_43_1","unstructured":"Harrison Chase. 2022. LangChain 0.0.77 Docs. https:\/\/langchain.readthedocs.io\/en\/latest\/modules\/agents\/getting_started.html"},{"key":"e_1_3_2_1_44_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Chen Lili","year":"2021","unstructured":"Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Misha Laskin, Pieter Abbeel, Aravind Srinivas, and Igor Mordatch. 2021. Decision Transformer: Reinforcement Learning via Sequence Modeling. In Advances in Neural Information Processing Systems, Vol. 34. Curran Associates, Inc., 15084\u201315097. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/7f489f642a0ddb10272b5c31057f0663-Abstract.html"},{"key":"e_1_3_2_1_45_1","volume-title":"The Stanford Encyclopedia of Philosophy (spring 2022 ed.), Edward N","author":"Christiano Tom","year":"2022","unstructured":"Tom Christiano and Sameer Bajaj. 2022. Democracy. In The Stanford Encyclopedia of Philosophy (spring 2022 ed.), Edward N. Zalta (Ed.). Metaphysics Research Lab, Stanford University. https:\/\/plato.stanford.edu\/archives\/spr2022\/entries\/democracy\/"},{"key":"e_1_3_2_1_46_1","unstructured":"Jack Clark and Dario Amodei. 2016. Faulty Reward Functions in the Wild. https:\/\/openai.com\/blog\/faulty-reward-functions\/"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.05718"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533150"},{"key":"e_1_3_2_1_49_1","volume-title":"Reinforcement Learning Using Neural Networks, with Applications to Motor Control. (June","author":"Coulom R\u00e9mi","year":"2002","unstructured":"R\u00e9mi Coulom. 2002. Reinforcement Learning Using Neural Networks, with Applications to Motor Control. (June 2002)."},{"key":"e_1_3_2_1_50_1","volume-title":"Democratising Risk: In Search of a Methodology to Study Existential Risk. https:\/\/papers.ssrn.com\/abstract=3995225","author":"Cremer Carla Zoe","year":"2021","unstructured":"Carla Zoe Cremer and Luke Kemp. 2021. Democratising Risk: In Search of a Methodology to Study Existential Risk. https:\/\/papers.ssrn.com\/abstract=3995225"},{"key":"e_1_3_2_1_51_1","volume-title":"AI Governance: A Research Agenda. (Aug","author":"Dafoe Allan","year":"2018","unstructured":"Allan Dafoe. 2018. AI Governance: A Research Agenda. (Aug. 2018). https:\/\/www.fhi.ox.ac.uk\/wp-content\/uploads\/GovAI-Agenda.pdf"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","unstructured":"Allan Dafoe Edward Hughes Yoram Bachrach Tantum Collins Kevin R. McKee Joel Z. Leibo Kate Larson and Thore Graepel. 2020. Open Problems in Cooperative AI. https:\/\/doi.org\/10.48550\/arXiv.2012.08630 arXiv:2012.08630 [cs].","DOI":"10.48550\/arXiv.2012.08630"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","unstructured":"Alexander D\u2019Amour Katherine Heller Dan Moldovan Ben Adlam Babak Alipanahi Alex Beutel Christina Chen Jonathan Deaton Jacob Eisenstein Matthew D. Hoffman Farhad Hormozdiari Neil Houlsby Shaobo Hou Ghassen Jerfel Alan Karthikesalingam Mario Lucic Yian Ma Cory McLean Diana Mincu Akinori Mitani Andrea Montanari Zachary Nado Vivek Natarajan Christopher Nielson Thomas F. Osborne Rajiv Raman Kim Ramasamy Rory Sayres Jessica Schrouff Martin Seneviratne Shannon Sequeira Harini Suresh Victor Veitch Max Vladymyrov Xuezhi Wang Kellie Webster Steve Yadlowsky Taedong Yun Xiaohua Zhai and D. Sculley. 2020. Underspecification Presents Challenges for Credibility in Modern Machine Learning. https:\/\/doi.org\/10.48550\/arXiv.2011.03395 arXiv:2011.03395 [cs stat].","DOI":"10.48550\/arXiv.2011.03395"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372878"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","unstructured":"Mostafa Dehghani Yi Tay Alexey A. Gritsenko Zhe Zhao Neil Houlsby Fernando Diaz Donald Metzler and Oriol Vinyals. 2021. The Benchmark Lottery. https:\/\/doi.org\/10.48550\/arXiv.2107.07002 arXiv:2107.07002 [cs].","DOI":"10.48550\/arXiv.2107.07002"},{"key":"e_1_3_2_1_56_1","volume-title":"The Intentional Stance","author":"Dennett Daniel Clement","unstructured":"Daniel Clement Dennett. 1981. The Intentional Stance. MIT Press."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","unstructured":"Qingxiu Dong Lei Li Damai Dai Ce Zheng Zhiyong Wu Baobao Chang Xu Sun Jingjing Xu Lei Li and Zhifang Sui. 2022. A Survey for In-context Learning. https:\/\/doi.org\/10.48550\/arXiv.2301.00234 arXiv:2301.00234 [cs].","DOI":"10.48550\/arXiv.2301.00234"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533186"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.2307\/258191"},{"key":"e_1_3_2_1_62_1","volume-title":"Proceedings of the 1st Conference on Fairness, Accountability and Transparency(Proceedings of Machine Learning Research","volume":"186","author":"Ekstrand Michael D.","year":"2018","unstructured":"Michael D. Ekstrand, Mucun Tian, Ion Madrazo Azpiazu, Jennifer D. Ekstrand, Oghenemaro Anuyah, David McNeill, and Maria Soledad Pera. 2018. All The Cool Kids, How Do They Fit In?: Popularity and Demographic Biases in Recommender Evaluation and Effectiveness. In Proceedings of the 1st Conference on Fairness, Accountability and Transparency(Proceedings of Machine Learning Research, Vol. 81), Sorelle A. Friedler and Christo Wilson (Eds.). PMLR, 172\u2013186. https:\/\/proceedings.mlr.press\/v81\/ekstrand18b.html"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372842"},{"key":"e_1_3_2_1_64_1","volume-title":"What is Agency?American journal of sociology 103, 4","author":"Emirbayer Mustafa","year":"1998","unstructured":"Mustafa Emirbayer and Ann Mische. 1998. What is Agency?American journal of sociology 103, 4 (1998), 962\u20131023. Publisher: The University of Chicago Press."},{"key":"e_1_3_2_1_65_1","unstructured":"Spotify Engineering. 2021. Shifting Consumption towards Diverse content via Reinforcement Learning. https:\/\/research.atspotify.com\/2021\/03\/shifting-consumption-towards-diverse-content-via-reinforcement-learning\/ Section: Algorithmic Responsibility."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","unstructured":"Charles Evans and Atoosa Kasirzadeh. 2022. User Tampering in Reinforcement Learning Recommender Systems. https:\/\/doi.org\/10.48550\/arXiv.2109.04083 arXiv:2109.04083 [cs].","DOI":"10.48550\/arXiv.2109.04083"},{"key":"e_1_3_2_1_67_1","unstructured":"Richard Evans and Jim Gao. 2016. DeepMind AI Reduces Google Data Centre Cooling Bill by 40%. https:\/\/www.deepmind.com\/blog\/deepmind-ai-reduces-google-data-centre-cooling-bill-by-40"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17368"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","unstructured":"Sebastian Farquhar Ryan Carey and Tom Everitt. 2022. Path-Specific Objectives for Safer Agent Incentives. https:\/\/doi.org\/10.48550\/arXiv.2204.10018 arXiv:2204.10018 [cs stat].","DOI":"10.48550\/arXiv.2204.10018"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533193"},{"key":"e_1_3_2_1_71_1","unstructured":"Coalition for Critical Technology. 2020. Abolish the #TechToPrisonPipeline. https:\/\/medium.com\/@CoalitionForCriticalTechnology\/abolish-the-techtoprisonpipeline-9b5b14366b16"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533229"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","unstructured":"Leo Gao John Schulman and Jacob Hilton. 2022. Scaling Laws for Reward Model Overoptimization. https:\/\/doi.org\/10.48550\/arXiv.2210.10760 arXiv:2210.10760 [cs stat].","DOI":"10.48550\/arXiv.2210.10760"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1811.00260"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458723"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_77_1","volume-title":"Fair Use, Scholarly Communication, etc. (Jan.","author":"Gesley Jenny","year":"2019","unstructured":"Jenny Gesley, Tariq Ahmad, Edouardo Soares, Ruth Levush, Gustavo Guerra, James Martin, Kelly Buchanan, Laney Zhang, Sayuri Umeda, Astghik Grigoryan, Nicolas Boring, Elin Hofverberg, Clare Feikhert-Ahalt, Graciela Rodriguez-Ferrand, George Sadek, and Hanibal Goitom. 2019. Regulation of Artificial Intelligence in Selected Jurisdictions. Copyright, Fair Use, Scholarly Communication, etc. (Jan. 2019). https:\/\/digitalcommons.unl.edu\/scholcom\/177"},{"key":"e_1_3_2_1_78_1","volume-title":"Artificial Intelligence. Our World in Data","author":"Giattino Charlie","year":"2022","unstructured":"Charlie Giattino, Edouard Mathieu, Julia Broden, and Max Roser. 2022. Artificial Intelligence. Our World in Data (2022)."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","unstructured":"Thomas Krendl Gilbert Sarah Dean Nathan Lambert Tom Zick and Aaron Snoswell. 2022. Reward Reports for Reinforcement Learning. https:\/\/doi.org\/10.48550\/arXiv.2204.10817 arXiv:2204.10817 [cs].","DOI":"10.48550\/arXiv.2204.10817"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533106"},{"key":"e_1_3_2_1_81_1","volume-title":"Problems of monetary management: the UK experience in papers in monetary economics. Monetary Economics 1","author":"Goodhart Charles","year":"1975","unstructured":"Charles Goodhart. 1975. Problems of monetary management: the UK experience in papers in monetary economics. Monetary Economics 1 (1975)."},{"key":"e_1_3_2_1_82_1","volume-title":"Gray and Siddharth Suri","author":"Mary","year":"2019","unstructured":"Mary L. Gray and Siddharth Suri. 2019. Ghost work: how to stop Silicon Valley from building a new global underclass. Houghton Mifflin Harcourt, Boston."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372869"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287563"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462552"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314250"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","unstructured":"Danijar Hafner Jurgis Pasukonis Jimmy Ba and Timothy Lillicrap. 2023. Mastering Diverse Domains through World Models. https:\/\/doi.org\/10.48550\/arXiv.2301.04104 arXiv:2301.04104 [cs stat].","DOI":"10.48550\/arXiv.2301.04104"},{"key":"e_1_3_2_1_88_1","first-page":"1001","article-title":"Employer Liability of Negligent Hiring of Ex-Offenders","volume":"55","author":"Hickox Stacy A.","year":"2010","unstructured":"Stacy A. Hickox. 2010. Employer Liability of Negligent Hiring of Ex-Offenders. Saint Louis University Law Journal 55, 3 (2010), 1001\u20131046. https:\/\/heinonline.org\/HOL\/P?h=hein.journals\/stlulj55&i=1029","journal-title":"Saint Louis University Law Journal"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","unstructured":"Jacob Hilton Jie Tang and John Schulman. 2023. Scaling laws for single-agent reinforcement learning. https:\/\/doi.org\/10.48550\/arXiv.2301.13442 arXiv:2301.13442 [cs stat].","DOI":"10.48550\/arXiv.2301.13442"},{"key":"e_1_3_2_1_90_1","unstructured":"Jordan Hoffmann Sebastian Borgeaud Arthur Mensch Elena Buchatskaya Trevor Cai Eliza Rutherford Diego de las Casas Lisa Anne Hendricks Johannes Welbl Aidan Clark Tom Hennigan Eric Noland Katherine Millican George van den Driessche Bogdan Damoc Aurelia Guy Simon Osindero Karen Simonyan Erich Elsen Oriol Vinyals Jack William Rae and Laurent Sifre. 2022. An empirical analysis of compute-optimal large language model training. In Advances in Neural Information Processing Systems Alice H. Oh Alekh Agarwal Danielle Belgrave and Kyunghyun Cho (Eds.). https:\/\/openreview.net\/forum?id=iBBcRUlOAPR"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.5817\/CP2019-1-4"},{"key":"e_1_3_2_1_92_1","unstructured":"Saffron Huang and Divya Siddarth. 2023. Generative AI and the Digital Commons. https:\/\/cip.org\/research\/generative-ai-digital-commons"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.05608"},{"key":"e_1_3_2_1_94_1","first-page":"2640","volume-title":"Proceedings of the 34th International Conference on Machine Learning. PMLR, 1617\u20131626","author":"Jabbari Shahin","year":"2017","unstructured":"Shahin Jabbari, Matthew Joseph, Michael Kearns, Jamie Morgenstern, and Aaron Roth. 2017. Fairness in Reinforcement Learning. In Proceedings of the 34th International Conference on Machine Learning. PMLR, 1617\u20131626. https:\/\/proceedings.mlr.press\/v70\/jabbari17a.html ISSN: 2640-3498."},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445901"},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1016\/0304-405X(76)90026-X"},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3534637"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314288"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-017-9417-6"},{"key":"e_1_3_2_1_101_1","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Joseph Matthew","year":"2016","unstructured":"Matthew Joseph, Michael Kearns, Jamie H Morgenstern, and Aaron Roth. 2016. Fairness in Learning: Classic and Contextual Bandits. In Advances in Neural Information Processing Systems, Vol. 29. Curran Associates, Inc.https:\/\/papers.nips.cc\/paper\/2016\/hash\/eb163727917cbba1eea208541a643e74-Abstract.html"},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom B. Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling Laws for Neural Language Models. https:\/\/doi.org\/10.48550\/arXiv.2001.08361 arXiv:2001.08361 [cs stat].","DOI":"10.48550\/arXiv.2001.08361"},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445919"},{"key":"e_1_3_2_1_105_1","unstructured":"Joe Kava. 2014. Better data centers through machine learning. https:\/\/blog.google\/inside-google\/infrastructure\/better-data-centers-through-machine\/"},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1080\/02673843.2019.1590851"},{"key":"e_1_3_2_1_107_1","volume-title":"Alignment of Language Agents. arXiv:2103.14659 [cs] (March","author":"Kenton Zachary","year":"2021","unstructured":"Zachary Kenton, Tom Everitt, Laura Weidinger, Iason Gabriel, Vladimir Mikulik, and Geoffrey Irving. 2021. Alignment of Language Agents. arXiv:2103.14659 [cs] (March 2021). http:\/\/arxiv.org\/abs\/2103.14659 arXiv:2103.14659."},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","unstructured":"Zachary Kenton Ramana Kumar Sebastian Farquhar Jonathan Richens Matt MacDermott and Tom Everitt. 2022. Discovering Agents. https:\/\/doi.org\/10.48550\/arXiv.2208.08345 arXiv:2208.08345 [cs].","DOI":"10.48550\/arXiv.2208.08345"},{"key":"e_1_3_2_1_109_1","volume-title":"The Doomsday Invention. The New Yorker (Nov","author":"Khatchadourian Raffi","year":"2015","unstructured":"Raffi Khatchadourian. 2015. The Doomsday Invention. The New Yorker (Nov. 2015). https:\/\/www.newyorker.com\/magazine\/2015\/11\/23\/doomsday-invention-artificial-intelligence-nick-bostrom"},{"key":"e_1_3_2_1_110_1","volume-title":"Specification gaming: the flip side of AI ingenuity. DeepMind Blog","author":"Krakovna Victoria","year":"2020","unstructured":"Victoria Krakovna, Jonathan Uesato, Vladimir Mikulik, Matthew Rahtz, Tom Everitt, Ramana Kumar, Zac Kenton, Jan Leike, and Shane Legg. 2020. Specification gaming: the flip side of AI ingenuity. DeepMind Blog (2020)."},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","unstructured":"David Krueger Tegan Maharaj and Jan Leike. 2020. Hidden Incentives for Auto-Induced Distributional Shift. https:\/\/doi.org\/10.48550\/arXiv.2009.09153 arXiv:2009.09153 [cs stat].","DOI":"10.48550\/arXiv.2009.09153"},{"key":"e_1_3_2_1_112_1","unstructured":"T.S. Kuhn and I. Hacking. 2012. The Structure of Scientific Revolutions. University of Chicago Press. https:\/\/books.google.co.uk\/books?id=3eP5Y_OOuzwC"},{"key":"e_1_3_2_1_113_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"e_1_3_2_1_114_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research","volume":"12019","author":"Di Langosco Lauro Langosco","year":"2022","unstructured":"Lauro Langosco Di Langosco, Jack Koch, Lee D Sharkey, Jacob Pfau, and David Krueger. 2022. Goal Misgeneralization in Deep Reinforcement Learning. In Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 12004\u201312019. https:\/\/proceedings.mlr.press\/v162\/langosco22a.html"},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","unstructured":"Seth Lazar. 2022. Legitimacy Authority and the Political Value of Explanations. https:\/\/doi.org\/10.48550\/arXiv.2208.08628 arXiv:2208.08628 [cs].","DOI":"10.48550\/arXiv.2208.08628"},{"key":"e_1_3_2_1_116_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2020.100124"},{"key":"e_1_3_2_1_117_1","unstructured":"Gideon Lewis-Kraus. 2022. How harmful is social media?https:\/\/www.newyorker.com\/culture\/annals-of-inquiry\/we-know-less-about-social-media-than-we-think Publication Title: The New Yorker."},{"key":"e_1_3_2_1_118_1","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1601885"},{"key":"e_1_3_2_1_119_1","doi-asserted-by":"publisher","unstructured":"Yunqi Li Hanxiong Chen Shuyuan Xu Yingqiang Ge Juntao Tan Shuchang Liu and Yongfeng Zhang. 2022. Fairness in Recommendation: A Survey. https:\/\/doi.org\/10.48550\/arXiv.2205.13619 arXiv:2205.13619 [cs].","DOI":"10.48550\/arXiv.2205.13619"},{"key":"e_1_3_2_1_120_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"e_1_3_2_1_121_1","volume-title":"International Conference on Machine Learning. PMLR, 3150\u20133158","author":"Liu Lydia T","year":"2018","unstructured":"Lydia T Liu, Sarah Dean, Esther Rolf, Max Simchowitz, and Moritz Hardt. 2018. Delayed impact of fair machine learning. In International Conference on Machine Learning. PMLR, 3150\u20133158."},{"key":"e_1_3_2_1_122_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462631"},{"key":"e_1_3_2_1_123_1","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780190604981.001.0001"},{"key":"e_1_3_2_1_124_1","unstructured":"maraoz. 2021. Interviewing Albert Einstein via GPT-3. https:\/\/maraoz.substack.com\/embed"},{"key":"e_1_3_2_1_125_1","doi-asserted-by":"publisher","unstructured":"Jacob Menick Maja Trebacz Vladimir Mikulik John Aslanides Francis Song Martin Chadwick Mia Glaese Susannah Young Lucy Campbell-Gillingham Geoffrey Irving and Nat McAleese. 2022. Teaching language models to support answers with verified quotes. https:\/\/doi.org\/10.48550\/arXiv.2203.11147 arXiv:2203.11147 [cs].","DOI":"10.48550\/arXiv.2203.11147"},{"key":"e_1_3_2_1_126_1","doi-asserted-by":"crossref","unstructured":"Meta. 2023. Meta Reports Fourth Quarter and Full Year 2022 Results. https:\/\/investor.fb.com\/investor-news\/press-release-details\/2023\/Meta-Reports-Fourth-Quarter-and-Full-Year-2022-Results\/default.aspx","DOI":"10.1016\/j.fopow.2023.02.013"},{"key":"e_1_3_2_1_127_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-020-00950-y"},{"key":"e_1_3_2_1_128_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287596"},{"key":"e_1_3_2_1_129_1","doi-asserted-by":"publisher","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. https:\/\/doi.org\/10.48550\/arXiv.1312.5602 arXiv:1312.5602 [cs].","DOI":"10.48550\/arXiv.1312.5602"},{"key":"e_1_3_2_1_130_1","unstructured":"AI Myths. [n. d.]. Myth: AI has agency. https:\/\/www.aimyths.org\/ai-has-agency"},{"key":"e_1_3_2_1_131_1","doi-asserted-by":"publisher","unstructured":"Reiichiro Nakano Jacob Hilton Suchir Balaji Jeff Wu Long Ouyang Christina Kim Christopher Hesse Shantanu Jain Vineet Kosaraju William Saunders Xu Jiang Karl Cobbe Tyna Eloundou Gretchen Krueger Kevin Button Matthew Knight Benjamin Chess and John Schulman. 2022. WebGPT: Browser-assisted question-answering with human feedback. https:\/\/doi.org\/10.48550\/arXiv.2112.09332 arXiv:2112.09332 [cs].","DOI":"10.48550\/arXiv.2112.09332"},{"key":"e_1_3_2_1_132_1","doi-asserted-by":"publisher","DOI":"10.1177\/1354856517715164"},{"key":"e_1_3_2_1_133_1","unstructured":"Pandu Nayak. 2019. Understanding searches better than ever before. https:\/\/blog.google\/products\/search\/search-language-understanding-bert\/"},{"key":"e_1_3_2_1_134_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02639315"},{"key":"e_1_3_2_1_135_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287593"},{"key":"e_1_3_2_1_136_1","volume-title":"In-context Learning and Induction Heads. Transformer Circuits Thread","author":"Olsson Catherine","year":"2022","unstructured":"Catherine Olsson, Nelson Elhage, Neel Nanda, Nicholas Joseph, Nova DasSarma, Tom Henighan, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Dawn Drain, Deep Ganguli, Zac Hatfield-Dodds, Danny Hernandez, Scott Johnston, Andy Jones, Jackson Kernion, Liane Lovitt, Kamal Ndousse, Dario Amodei, Tom Brown, Jack Clark, Jared Kaplan, Sam McCandlish, and Chris Olah. 2022. In-context Learning and Induction Heads. Transformer Circuits Thread (2022)."},{"key":"e_1_3_2_1_137_1","first-page":"483","article-title":"The Basic AI Drives","volume":"171","author":"Omohundro Stephen M","year":"2008","unstructured":"Stephen M Omohundro. 2008. The Basic AI Drives. In AGI, Vol. 171. 483\u2013492.","journal-title":"AGI"},{"key":"e_1_3_2_1_138_1","unstructured":"OpenAI. 2022. ChatGPT: Optimizing Language Models for Dialogue. https:\/\/openai.com\/blog\/chatgpt\/"},{"key":"e_1_3_2_1_139_1","unstructured":"OpenAI. 2023. ChatGPT plugins. https:\/\/openai.com\/blog\/chatgpt-plugins"},{"key":"e_1_3_2_1_140_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1805.12387"},{"key":"e_1_3_2_1_141_1","volume-title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=JYtwGwIL7ye","author":"Pan Alexander","year":"2022","unstructured":"Alexander Pan, Kush Bhatia, and Jacob Steinhardt. 2022. The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=JYtwGwIL7ye"},{"key":"e_1_3_2_1_142_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.03279"},{"key":"e_1_3_2_1_143_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545616"},{"key":"e_1_3_2_1_144_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-020-01097-6"},{"key":"e_1_3_2_1_145_1","doi-asserted-by":"publisher","unstructured":"Ethan Perez Sam Ringer Kamil\u0117 Luko\u0161i\u016bt\u0117 Karina Nguyen Edwin Chen Scott Heiner Craig Pettit Catherine Olsson Sandipan Kundu Saurav Kadavath Andy Jones Anna Chen Ben Mann Brian Israel Bryan Seethor Cameron McKinnon Christopher Olah Da Yan Daniela Amodei Dario Amodei Dawn Drain Dustin Li Eli Tran-Johnson Guro Khundadze Jackson Kernion James Landis Jamie Kerr Jared Mueller Jeeyoon Hyun Joshua Landau Kamal Ndousse Landon Goldberg Liane Lovitt Martin Lucas Michael Sellitto Miranda Zhang Neerav Kingsland Nelson Elhage Nicholas Joseph Noem\u00ed Mercado Nova DasSarma Oliver Rausch Robin Larson Sam McCandlish Scott Johnston Shauna Kravec Sheer El Showk Tamera Lanham Timothy Telleen-Lawton Tom Brown Tom Henighan Tristan Hume Yuntao Bai Zac Hatfield-Dodds Jack Clark Samuel R. Bowman Amanda Askell Roger Grosse Danny Hernandez Deep Ganguli Evan Hubinger Nicholas Schiefer and Jared Kaplan. 2022. Discovering Language Model Behaviors with Model-Written Evaluations. https:\/\/doi.org\/10.48550\/arXiv.2212.09251 arXiv:2212.09251 [cs].","DOI":"10.48550\/arXiv.2212.09251"},{"key":"e_1_3_2_1_146_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"key":"e_1_3_2_1_147_1","volume-title":"Exclusive: The $2 Per Hour Workers Who Made ChatGPT Safer. Time (Jan.","author":"Perrigo Billy","year":"2023","unstructured":"Billy Perrigo. 2023. Exclusive: The $2 Per Hour Workers Who Made ChatGPT Safer. Time (Jan. 2023). https:\/\/time.com\/6247678\/openai-chatgpt-kenya-workers\/"},{"key":"e_1_3_2_1_148_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2208.02957"},{"key":"e_1_3_2_1_149_1","first-page":"169","article-title":"World view","volume":"583","author":"Pratyusha By","year":"2020","unstructured":"By Pratyusha. 2020. World view. Nature 583 (2020), 169.","journal-title":"Nature"},{"key":"e_1_3_2_1_150_1","doi-asserted-by":"publisher","unstructured":"Jack W. Rae Sebastian Borgeaud Trevor Cai Katie Millican Jordan Hoffmann Francis Song John Aslanides Sarah Henderson Roman Ring Susannah Young Eliza Rutherford Tom Hennigan Jacob Menick Albin Cassirer Richard Powell George van den Driessche Lisa Anne Hendricks Maribeth Rauh Po-Sen Huang Amelia Glaese Johannes Welbl Sumanth Dathathri Saffron Huang Jonathan Uesato John Mellor Irina Higgins Antonia Creswell Nat McAleese Amy Wu Erich Elsen Siddhant Jayakumar Elena Buchatskaya David Budden Esme Sutherland Karen Simonyan Michela Paganini Laurent Sifre Lena Martens Xiang Lorraine Li Adhiguna Kuncoro Aida Nematzadeh Elena Gribovskaya Domenic Donato Angeliki Lazaridou Arthur Mensch Jean-Baptiste Lespiau Maria Tsimpoukelli Nikolai Grigorev Doug Fritz Thibault Sottiaux Mantas Pajarskas Toby Pohlen Zhitao Gong Daniel Toyama Cyprien de Masson d\u2019Autume Yujia Li Tayfun Terzi Vladimir Mikulik Igor Babuschkin Aidan Clark Diego de Las Casas Aurelia Guy Chris Jones James Bradbury Matthew Johnson Blake Hechtman Laura Weidinger Iason Gabriel William Isaac Ed Lockhart Simon Osindero Laura Rimell Chris Dyer Oriol Vinyals Kareem Ayoub Jeff Stanway Lorrayne Bennett Demis Hassabis Koray Kavukcuoglu and Geoffrey Irving. 2022. Scaling Language Models: Methods Analysis & Insights from Training Gopher. https:\/\/doi.org\/10.48550\/arXiv.2112.11446 arXiv:2112.11446 [cs].","DOI":"10.48550\/arXiv.2112.11446"},{"key":"e_1_3_2_1_151_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1 (Dec. 2021","author":"Raji Deborah","year":"2021","unstructured":"Deborah Raji, Emily Denton, Emily M. Bender, Alex Hanna, and Amandalynne Paullada. 2021. AI and the Everything in the Whole Wide World Benchmark. Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1 (Dec. 2021). https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper\/2021\/hash\/084b6fbb10729ed4da8c3d3f5a3ae7c9-Abstract-round2.html"},{"key":"e_1_3_2_1_152_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314244"},{"key":"e_1_3_2_1_153_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533158"},{"key":"e_1_3_2_1_154_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372873"},{"key":"e_1_3_2_1_155_1","unstructured":"Scott Reed Konrad Zolna Emilio Parisotto Sergio G\u00f3mez Colmenarejo Alexander Novikov Gabriel Barth-maron Mai Gim\u00e9nez Yury Sulsky Jackie Kay Jost Tobias Springenberg Tom Eccles Jake Bruce Ali Razavi Ashley Edwards Nicolas Heess Yutian Chen Raia Hadsell Oriol Vinyals Mahyar Bordbar and Nando de Freitas. 2022. A Generalist Agent. Transactions on Machine Learning Research (2022). https:\/\/openreview.net\/forum?id=1ikK0kHjvj"},{"key":"e_1_3_2_1_156_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372879"},{"key":"e_1_3_2_1_157_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2016.7451740"},{"key":"e_1_3_2_1_158_1","volume-title":"Russell and Peter Norvig","author":"Stuart","year":"2021","unstructured":"Stuart J. Russell and Peter Norvig. 2021. Artificial Intelligence: A Modern Approach (4 ed.)."},{"key":"e_1_3_2_1_159_1","volume-title":"The Stanford Encyclopedia of Philosophy (winter 2019 ed.), Edward N","author":"Schlosser Markus","year":"2019","unstructured":"Markus Schlosser. 2019. Agency. In The Stanford Encyclopedia of Philosophy (winter 2019 ed.), Edward N. Zalta (Ed.). Metaphysics Research Lab, Stanford University. https:\/\/plato.stanford.edu\/archives\/win2019\/entries\/agency\/"},{"key":"e_1_3_2_1_160_1","volume-title":"Amazon Dives Deep into Reinforcement Learning. Forbes (June","author":"Schmelzer Ron","year":"2019","unstructured":"Ron Schmelzer. 2019. Amazon Dives Deep into Reinforcement Learning. Forbes (June 2019). https:\/\/www.forbes.com\/sites\/cognitiveworld\/2019\/06\/14\/amazon-dives-deep-into-reinforcement-learning\/"},{"key":"e_1_3_2_1_161_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"e_1_3_2_1_162_1","volume-title":"or Industry Experts? Academic Sourcing in News Coverage of AI. (2019)","author":"Schulz Anne","unstructured":"Anne Schulz, P Howard, and R Nielsen. 2019. Industry, Experts, or Industry Experts? Academic Sourcing in News Coverage of AI. (2019). Publisher: Reuters Institute for the Study of Journalism."},{"key":"e_1_3_2_1_163_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287598"},{"key":"e_1_3_2_1_164_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372827"},{"key":"e_1_3_2_1_165_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.01790"},{"key":"e_1_3_2_1_166_1","doi-asserted-by":"publisher","unstructured":"Yonadav Shavit. 2023. What does it take to catch a Chinchilla? Verifying Rules on Large-Scale Neural Network Training via Compute Monitoring. https:\/\/doi.org\/10.48550\/arXiv.2303.11341 arXiv:2303.11341 [cs].","DOI":"10.48550\/arXiv.2303.11341"},{"key":"e_1_3_2_1_167_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.05791"},{"key":"e_1_3_2_1_168_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"e_1_3_2_1_169_1","doi-asserted-by":"publisher","unstructured":"David Silver Thomas Hubert Julian Schrittwieser Ioannis Antonoglou Matthew Lai Arthur Guez Marc Lanctot Laurent Sifre Dharshan Kumaran Thore Graepel Timothy Lillicrap Karen Simonyan and Demis Hassabis. 2017. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm. https:\/\/doi.org\/10.48550\/arXiv.1712.01815 arXiv:1712.01815 [cs].","DOI":"10.48550\/arXiv.1712.01815"},{"key":"e_1_3_2_1_170_1","unstructured":"Joar Max Viktor Skalse Nikolaus H. R. Howe Dmitrii Krasheninnikov and David Krueger. 2022. Defining and Characterizing Reward Hacking. In Advances in Neural Information Processing Systems Alice H. Oh Alekh Agarwal Danielle Belgrave and Kyunghyun Cho (Eds.). https:\/\/arxiv.org\/abs\/2209.13085"},{"key":"e_1_3_2_1_171_1","volume-title":"Core knowledge. Developmental science 10, 1","author":"Spelke Elizabeth S","year":"2007","unstructured":"Elizabeth S Spelke and Katherine D Kinzler. 2007. Core knowledge. Developmental science 10, 1 (2007), 89\u201396. Publisher: Wiley Online Library."},{"key":"e_1_3_2_1_172_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2206.04615"},{"key":"e_1_3_2_1_173_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533177"},{"key":"e_1_3_2_1_174_1","volume-title":"piantadosi [@spiantado]","year":"2022","unstructured":"steven t. piantadosi [@spiantado]. 2022. Yes, ChatGPT is amazing and impressive. No, @OpenAI has not come close to addressing the problem of bias. Filters appear to be bypassed with simple tricks, and superficially masked. And what is lurking inside is egregious. @Abebab @sama tw racism, sexism. https:\/\/t.co\/V4fw1fY9dY. https:\/\/twitter.com\/spiantado\/status\/1599462375887114240"},{"key":"e_1_3_2_1_175_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.01.021"},{"key":"e_1_3_2_1_176_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10551-022-05053-w"},{"key":"e_1_3_2_1_177_1","unstructured":"[177] Richard Sutton. 2022. https:\/\/twitter.com\/richardssutton\/status\/1575619651563708418"},{"key":"e_1_3_2_1_178_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","unstructured":"Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_1_179_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2208.11173"},{"key":"e_1_3_2_1_180_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462602"},{"key":"e_1_3_2_1_181_1","doi-asserted-by":"publisher","unstructured":"Adaptive Agent Team Jakob Bauer Kate Baumli Satinder Baveja Feryal Behbahani Avishkar Bhoopchand Nathalie Bradley-Schmieg Michael Chang Natalie Clay Adrian Collister Vibhavari Dasagi Lucy Gonzalez Karol Gregor Edward Hughes Sheleem Kashem Maria Loks-Thompson Hannah Openshaw Jack Parker-Holder Shreya Pathak Nicolas Perez-Nieves Nemanja Rakicevic Tim Rockt\u00e4schel Yannick Schroecker Jakub Sygnowski Karl Tuyls Sarah York Alexander Zacherl and Lei Zhang. 2023. Human-Timescale Adaptation in an Open-Ended Task Space. https:\/\/doi.org\/10.48550\/arXiv.2301.07608 arXiv:2301.07608 [cs].","DOI":"10.48550\/arXiv.2301.07608"},{"key":"e_1_3_2_1_182_1","volume-title":"Superforecasting: The Art and Science of Prediction","author":"Tetlock Philip E","year":"2016","unstructured":"Philip E Tetlock and Dan Gardner. 2016. Superforecasting: The Art and Science of Prediction. Random House."},{"key":"e_1_3_2_1_183_1","volume-title":"Deliberating Autonomous Weapons. Issues in Science and Technology XXXVIII, 4","author":"Trager Robert","year":"2022","unstructured":"Robert Trager. 2022. Deliberating Autonomous Weapons. Issues in Science and Technology XXXVIII, 4 (2022). https:\/\/issues.org\/autonomous-weapons-russell-forum\/"},{"key":"e_1_3_2_1_184_1","first-page":"83","article-title":"An FDA for Algorithms","volume":"69","author":"Tutt Andrew","year":"2017","unstructured":"Andrew Tutt. 2017. An FDA for Algorithms. Administrative Law Review 69, 1 (2017), 83\u2013124. https:\/\/heinonline.org\/HOL\/P?h=hein.journals\/admin69&i=95","journal-title":"Administrative Law Review"},{"key":"e_1_3_2_1_185_1","doi-asserted-by":"publisher","unstructured":"Karthik Valmeekam Alberto Olmo Sarath Sreedharan and Subbarao Kambhampati. 2022. Large Language Models Still Can\u2019t Plan (A Benchmark for LLMs on Planning and Reasoning about Change). https:\/\/doi.org\/10.48550\/arXiv.2206.10498 arXiv:2206.10498 [cs].","DOI":"10.48550\/arXiv.2206.10498"},{"key":"e_1_3_2_1_186_1","doi-asserted-by":"publisher","unstructured":"Agnes Schim van der Loeff Iggy Bassi Sachin Kapila and Jevgenij Gamper. 2019. AI Ethics for Systemic Issues: A Structural Approach. https:\/\/doi.org\/10.48550\/arXiv.1911.03216 arXiv:1911.03216 [cs].","DOI":"10.48550\/arXiv.1911.03216"},{"key":"e_1_3_2_1_187_1","unstructured":"Lee Vinsel. 2021. You\u2019re Doing It Wrong: Notes on Criticism and Technology Hype. https:\/\/sts-news.medium.com\/youre-doing-it-wrong-notes-on-criticism-and-technology-hype-18b08b4307e5"},{"key":"e_1_3_2_1_188_1","unstructured":"Heather Vogell Haru Coryne and Ryan Little. 2022. How a secret rent algorithm pushes rents higher. https:\/\/www.propublica.org\/article\/yieldstar-rent-increase-realpage-rent Publication Title: ProPublica."},{"key":"e_1_3_2_1_189_1","volume-title":"Scenario planning in public policy: Understanding use, impacts and the role of institutional context factors. Technological forecasting and social change 76, 9","author":"Volkery Axel","year":"2009","unstructured":"Axel Volkery and Teresa Ribeiro. 2009. Scenario planning in public policy: Understanding use, impacts and the role of institutional context factors. Technological forecasting and social change 76, 9 (2009), 1198\u20131207. Publisher: Elsevier."},{"key":"e_1_3_2_1_190_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_191_1","volume-title":"Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022. Emergent Abilities of Large Language Models. Transactions on Machine Learning Research (2022). https:\/\/openreview.net\/forum?id=yzkSU5zdwD"},{"key":"e_1_3_2_1_192_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.11903"},{"key":"e_1_3_2_1_193_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533088"},{"key":"e_1_3_2_1_194_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314295"},{"key":"e_1_3_2_1_195_1","doi-asserted-by":"publisher","DOI":"10.14763\/2021.2.1565"},{"key":"e_1_3_2_1_196_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372833"},{"key":"e_1_3_2_1_197_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534136"},{"key":"e_1_3_2_1_198_1","volume-title":"Technological determinism is dead","author":"Wyatt S.","unstructured":"S. Wyatt. 2008. Technological determinism is dead; Long live technological determinism. In Handbook of Science and Technology Studies, E. Hackett, O. Amsterdamska, M. Lynch, and J. Wajcman (Eds.). MIT Press, Cambridge, 165\u2013180."},{"key":"e_1_3_2_1_199_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Ye Weirui","year":"2021","unstructured":"Weirui Ye, Shaohuai Liu, Thanard Kurutach, Pieter Abbeel, and Yang Gao. 2021. Mastering Atari Games with Limited Data. In Advances in Neural Information Processing Systems, Vol. 34. Curran Associates, Inc., 25476\u201325488. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/d5eca8dc3820cad9fe56a3bafda65ca1-Abstract.html"},{"key":"e_1_3_2_1_200_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2019.01.026"},{"key":"e_1_3_2_1_201_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533194"},{"key":"e_1_3_2_1_202_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2204.00598"},{"key":"e_1_3_2_1_203_1","unstructured":"Xueru Zhang and M. Liu. 2020. Fairness in Learning-Based Sequential Decision Algorithms: A Survey. ArXiv abs\/2001.04861 (2020)."},{"key":"e_1_3_2_1_204_1","doi-asserted-by":"publisher","unstructured":"Stephan Zheng Alexander Trott Sunil Srinivasa David C. Parkes and Richard Socher. 2021. The AI Economist: Optimal Economic Policy Design via Two-level Deep Reinforcement Learning. https:\/\/doi.org\/10.48550\/arXiv.2108.02755 arXiv:2108.02755 [cs econ q-fin].","DOI":"10.48550\/arXiv.2108.02755"},{"key":"e_1_3_2_1_205_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534200"},{"key":"e_1_3_2_1_206_1","first-page":"2019","article-title":"Thinking about risks from AI: Accidents, misuse and structure","volume":"11","author":"Zwetsloot Remco","year":"2019","unstructured":"Remco Zwetsloot and Allan Dafoe. 2019. Thinking about risks from AI: Accidents, misuse and structure. Lawfare. February 11 (2019), 2019.","journal-title":"Lawfare"}],"event":{"name":"FAccT '23: the 2023 ACM Conference on Fairness, Accountability, and Transparency","location":"Chicago IL USA","acronym":"FAccT '23"},"container-title":["2023 ACM Conference on Fairness Accountability and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3593013.3594033","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3593013.3594033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:48:04Z","timestamp":1750178884000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3593013.3594033"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,12]]},"references-count":203,"alternative-id":["10.1145\/3593013.3594033","10.1145\/3593013"],"URL":"https:\/\/doi.org\/10.1145\/3593013.3594033","relation":{},"subject":[],"published":{"date-parts":[[2023,6,12]]},"assertion":[{"value":"2023-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}