{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T11:57:51Z","timestamp":1778587071714,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":176,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,3]]},"DOI":"10.1145\/3630106.3658948","type":"proceedings-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T13:14:21Z","timestamp":1717593261000},"page":"958-973","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":51,"title":["Visibility into AI Agents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7547-3951","authenticated-orcid":false,"given":"Alan","family":"Chan","sequence":"first","affiliation":[{"name":"Centre for the Governance of AI, United Kingdom and Mila (Quebec AI Institute), Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7488-9258","authenticated-orcid":false,"given":"Carson","family":"Ezell","sequence":"additional","affiliation":[{"name":"Harvard University, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8708-2472","authenticated-orcid":false,"given":"Max","family":"Kaufmann","sequence":"additional","affiliation":[{"name":"Independent, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8522-4333","authenticated-orcid":false,"given":"Kevin","family":"Wei","sequence":"additional","affiliation":[{"name":"Harvard Law School, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1695-0871","authenticated-orcid":false,"given":"Lewis","family":"Hammond","sequence":"additional","affiliation":[{"name":"University of Oxford, United Kingdom and Cooperative AI Foundation, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5390-1257","authenticated-orcid":false,"given":"Herbie","family":"Bradley","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5970-9100","authenticated-orcid":false,"given":"Emma","family":"Bluemke","sequence":"additional","affiliation":[{"name":"Centre for the Governance of AI, 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\/0000-0001-7256-0937","authenticated-orcid":false,"given":"David","family":"Krueger","sequence":"additional","affiliation":[{"name":"University of Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2538-6295","authenticated-orcid":false,"given":"Noam","family":"Kolt","sequence":"additional","affiliation":[{"name":"University of Toronto, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2593-266X","authenticated-orcid":false,"given":"Lennart","family":"Heim","sequence":"additional","affiliation":[{"name":"Centre for the Governance of AI, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8766-9582","authenticated-orcid":false,"given":"Markus","family":"Anderljung","sequence":"additional","affiliation":[{"name":"Centre for the Governance of AI, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2024,6,5]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. 42 U.S. Code \u00a7 17941 - Recognition of security practices. https:\/\/www.law.cornell.edu\/uscode\/text\/42\/17941"},{"key":"e_1_3_2_1_2_1","volume-title":"Proposal for a Regulation of the European Parliament and of the Council Laying Down Harmonised Rules on Artificial Intelligence","year":"2021","unstructured":"2021. Proposal for a Regulation of the European Parliament and of the Council Laying Down Harmonised Rules on Artificial Intelligence (Artificial Intelligence Act) and Amending Certain Union Legislative Acts. https:\/\/eur-lex.europa.eu\/legal-content\/EN\/TXT\/?uri=celex%3A52021PC0206"},{"key":"e_1_3_2_1_3_1","unstructured":"2022. 12 CFR \u00a7 1026.25 - Record retention.Federal Register (Jan. 2022)."},{"key":"e_1_3_2_1_4_1","unstructured":"2023. 14 CFR \u00a7 91.609 - Flight data recorders and cockpit voice recorders.Federal Register (Jan. 2023)."},{"key":"e_1_3_2_1_5_1","unstructured":"2023. character.ai. https:\/\/beta.character.ai\/"},{"key":"e_1_3_2_1_6_1","volume-title":"The Economics of Artificial Intelligence: An Agenda","author":"Acemoglu Daron","unstructured":"Daron Acemoglu and Pascual Restrepo. 2018. Artificial Intelligence, Automation, and Work. In The Economics of Artificial Intelligence: An Agenda. University of Chicago Press, 197\u2013236. https:\/\/www.nber.org\/books-and-chapters\/economics-artificial-intelligence-agenda\/artificial-intelligence-automation-and-work"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1257\/jep.33.2.3"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1177\/1461444816676645"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Markus Anderljung Joslyn Barnhart Anton Korinek Jade Leung Cullen O\u2019Keefe Jess Whittlestone Shahar Avin Miles Brundage Justin Bullock Duncan Cass-Beggs Ben Chang Tantum Collins Tim Fist Gillian Hadfield Alan Hayes Lewis Ho Sara Hooker Eric Horvitz Noam Kolt Jonas Schuett Yonadav Shavit Divya Siddarth Robert Trager and Kevin Wolf. 2023. Frontier AI Regulation: Managing Emerging Risks to Public Safety. https:\/\/doi.org\/10.48550\/arXiv.2307.03718 arXiv:2307.03718 [cs].","DOI":"10.48550\/arXiv.2307.03718"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.31219\/osf.io"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2212.08073"},{"key":"e_1_3_2_1_12_1","volume-title":"Image Hijacks: Adversarial Images can Control Generative Models at Runtime. https:\/\/arxiv.org\/abs\/2309.00236v2","author":"Bailey Luke","year":"2023","unstructured":"Luke Bailey, Euan Ong, Stuart Russell, and Scott Emmons. 2023. Image Hijacks: Adversarial Images can Control Generative Models at Runtime. https:\/\/arxiv.org\/abs\/2309.00236v2"},{"key":"e_1_3_2_1_13_1","unstructured":"Tessa Baker. 2023. The EU AI Act: A Primer. https:\/\/cset.georgetown.edu\/article\/the-eu-ai-act-a-primer\/"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1080\/00236561003654776"},{"key":"e_1_3_2_1_15_1","unstructured":"Matthew Barnett and Tamay Besiroglu. 2023. The Direct Approach. https:\/\/epochai.org\/blog\/the-direct-approach"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Manish Bhatt Sahana Chennabasappa Cyrus Nikolaidis Shengye Wan Ivan Evtimov Dominik Gabi Daniel Song Faizan Ahmad Cornelius Aschermann Lorenzo Fontana Sasha Frolov Ravi\u00a0Prakash Giri Dhaval Kapil Yiannis Kozyrakis David LeBlanc James Milazzo Aleksandar Straumann Gabriel Synnaeve Varun Vontimitta Spencer Whitman and Joshua Saxe. 2023. Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models. https:\/\/doi.org\/10.48550\/arXiv.2312.04724 arXiv:2312.04724 [cs].","DOI":"10.48550\/arXiv.2312.04724"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3538637.3539616"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1473-3099(20)30458-8"},{"key":"e_1_3_2_1_19_1","volume-title":"Freedom of Information and Openness: Fundamental Human Rights?Administrative Law Review 58, 1","author":"Birkinshaw Patrick","year":"2006","unstructured":"Patrick Birkinshaw. 2006. Freedom of Information and Openness: Fundamental Human Rights?Administrative Law Review 58, 1 (2006), 177\u2013218. https:\/\/www.jstor.org\/stable\/40712007 Publisher: American Bar Association."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","unstructured":"Emma Bluemke Tantum Collins Ben Garfinkel and Andrew Trask. 2023. Exploring the Relevance of Data Privacy-Enhancing Technologies for AI Governance Use Cases. https:\/\/doi.org\/10.48550\/arXiv.2303.08956 arXiv:2303.08956 [cs].","DOI":"10.48550\/arXiv.2303.08956"},{"key":"e_1_3_2_1_21_1","unstructured":"Board of Governors of the Federal Reserve System. 2021. Proactive Monitoring of Markets and Institutions. https:\/\/www.federalreserve.gov\/financial-stability\/proactive-monitoring-of-markets-and-institutions.htm"},{"key":"e_1_3_2_1_22_1","unstructured":"Daniil\u00a0A. Boiko Robert MacKnight and Gabe Gomes. 2023. Emergent autonomous scientific research capabilities of large language models. http:\/\/arxiv.org\/abs\/2304.05332arXiv:2304.05332 [physics]."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"Rishi Bommasani Kathleen\u00a0A. Creel Ananya Kumar Dan Jurafsky and Percy Liang. 2022. Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?https:\/\/doi.org\/10.48550\/arXiv.2211.13972 arXiv:2211.13972 [cs].","DOI":"10.48550\/arXiv.2211.13972"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.15772"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature11421"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.05376"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-soc-090820-020800"},{"key":"e_1_3_2_1_29_1","unstructured":"Vitalik Buterin. 2023. My Techno-Optimism. https:\/\/vitalik.eth.limo\/general\/2023\/11\/27\/techno_optimism.html"},{"key":"e_1_3_2_1_30_1","first-page":"2640","volume-title":"Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence. PMLR, 271\u2013281","author":"Carey Ryan","year":"2023","unstructured":"Ryan Carey and Tom Everitt. 2023. Human Control: Definitions and Algorithms. In Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence. PMLR, 271\u2013281. https:\/\/proceedings.mlr.press\/v216\/carey23a.html ISSN: 2640-3498."},{"key":"e_1_3_2_1_31_1","unstructured":"John Cassidy. 2009. How markets fail: The logic of economic calamities. Farrar Straus and Giroux."},{"key":"e_1_3_2_1_32_1","unstructured":"CFTC. 2023. CFTC Market Surveillance Program. https:\/\/www.cftc.gov\/IndustryOversight\/MarketSurveillance\/CFTCMarketSurveillanceProgram\/index.htm"},{"key":"e_1_3_2_1_33_1","unstructured":"CFTC. 2023. Large Trader Reporting Program. https:\/\/www.cftc.gov\/IndustryOversight\/MarketSurveillance\/LargeTraderReportingProgram\/index.htm"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604658"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594033"},{"key":"e_1_3_2_1_36_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_37_1","volume-title":"mrbullwinkle, eric urban, and aahill","author":"PatrickFarley HMSFT","year":"2023","unstructured":"ChrisHMSFT, PatrickFarley, mrbullwinkle, eric urban, and aahill. 2023. Data, privacy, and security for Azure OpenAI Service - Azure AI services. https:\/\/learn.microsoft.com\/en-us\/legal\/cognitive-services\/openai\/data-privacy"},{"key":"e_1_3_2_1_38_1","unstructured":"Google Cloud. 2023. Generative AI Privacy and Google Cloud. Technical Report. https:\/\/services.google.com\/fh\/files\/misc\/genai_privacy_google_cloud_202308.pdf"},{"key":"e_1_3_2_1_39_1","volume-title":"Seeking Truth for Power: Informational Strategy and Regulatory Policy Making. Minnesota Law Review (Jan","author":"Coglianese Cary","year":"2004","unstructured":"Cary Coglianese, Richard Zeckhauser, and Edward Parson. 2004. Seeking Truth for Power: Informational Strategy and Regulatory Policy Making. Minnesota Law Review (Jan. 2004). https:\/\/scholarship.law.upenn.edu\/faculty_scholarship\/107"},{"key":"e_1_3_2_1_40_1","volume-title":"Complex networks: structure, robustness and function","author":"Cohen Reuven","unstructured":"Reuven Cohen and Shlomo Havlin. 2010. Complex networks: structure, robustness and function. Cambridge university press."},{"key":"e_1_3_2_1_41_1","volume-title":"brokers and dealers.Federal Register (April","author":"Securities and\u00a0Exchange Commission","year":"2022","unstructured":"Securities and\u00a0Exchange Commission. 2022. 17 CFR \u00a7 240.17a-3 - Records to be made by certain exchange members, brokers and dealers.Federal Register (April 2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"brokers and dealers.Federal Register (April","author":"Securities and\u00a0Exchange Commission","year":"2022","unstructured":"Securities and\u00a0Exchange Commission. 2022. 17 CFR \u00a7 240.17a-4 - Records to be preserved by certain exchange members, brokers and dealers.Federal Register (April 2022)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533150"},{"key":"e_1_3_2_1_44_1","unstructured":"PCI Security\u00a0Standars Council. 2022. Payment Card Industry Data Security Standard."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","unstructured":"Andrew Critch and Stuart Russell. 2023. TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI. https:\/\/doi.org\/10.48550\/arXiv.2306.06924 arXiv:2306.06924 [cs].","DOI":"10.48550\/arXiv.2306.06924"},{"key":"e_1_3_2_1_46_1","volume-title":"Preliminary findings regarding the market events of may 6","author":"CTFC","year":"2010","unstructured":"CTFC and SEC. 2010. Preliminary findings regarding the market events of may 6, 2010. Technical Report. U.S. Commodity Futures Trading Commission and U.S. Securities & Exchange Commission. https:\/\/www.sec.gov\/sec-cftc-prelimreport.pdf tex.creationdate: 2023-10-29T16:47:57."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.2514\/6.2004-6313"},{"key":"e_1_3_2_1_48_1","volume-title":"Regulatory capture: A review. Oxford review of economic policy 22, 2","author":"Dal\u00a0B\u00f3 Ernesto","year":"2006","unstructured":"Ernesto Dal\u00a0B\u00f3. 2006. Regulatory capture: A review. Oxford review of economic policy 22, 2 (2006), 203\u2013225. Publisher: Oxford University Press."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","unstructured":"Tom Davidson Jean-Stanislas Denain Pablo Villalobos and Guillem Bas. 2023. AI capabilities can be significantly improved without expensive retraining. https:\/\/doi.org\/10.48550\/arXiv.2312.07413 arXiv:2312.07413 [cs].","DOI":"10.48550\/arXiv.2312.07413"},{"key":"e_1_3_2_1_50_1","volume-title":"Automated Systems Are Trapping Citizens in Bureaucratic Nightmares With Their Lives on the Line. TIME (May","author":"De\u00a0La\u00a0Garza Alejandro","year":"2020","unstructured":"Alejandro De\u00a0La\u00a0Garza. 2020. States\u2019 Automated Systems Are Trapping Citizens in Bureaucratic Nightmares With Their Lives on the Line. TIME (May 2020). https:\/\/time.com\/5840609\/algorithm-unemployment\/"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04301-9"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1093\/idpl"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Sylvie Delacroix Joelle Pineau and Jessica Montgomery. 2020. Democratising the Digital Revolution: The Role of Data Governance. https:\/\/papers.ssrn.com\/abstract=3720208","DOI":"10.1007\/978-3-030-69128-8_3"},{"key":"e_1_3_2_1_54_1","volume-title":"A New Law Makes Bots Identify Themselves\u2014That\u2019s the Problem. Wired (July","author":"DiResta Renee","year":"2019","unstructured":"Renee DiResta. 2019. A New Law Makes Bots Identify Themselves\u2014That\u2019s the Problem. Wired (July 2019). https:\/\/www.wired.com\/story\/law-makes-bots-identify-themselves\/ Section: tags."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","unstructured":"Florian\u00a0E. Dorner. 2021. Algorithmic collusion: A critical review. https:\/\/doi.org\/10.48550\/arXiv.2110.04740 arXiv:2110.04740 [cs].","DOI":"10.48550\/arXiv.2110.04740"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","unstructured":"Janet Egan and Lennart Heim. 2023. Oversight for Frontier AI through a Know-Your-Customer Scheme for Compute Providers. https:\/\/doi.org\/10.48550\/arXiv.2310.13625 arXiv:2310.13625 [cs].","DOI":"10.48550\/arXiv.2310.13625"},{"key":"e_1_3_2_1_57_1","volume-title":"Ely and Balazs Szentes","author":"C.","year":"2023","unstructured":"Jeffrey\u00a0C. Ely and Balazs Szentes. 2023. Natural selection of artificial intelligence. (2023)."},{"key":"e_1_3_2_1_58_1","unstructured":"Let\u2019s Encrypt. 2024. Let\u2019s Encrypt Stats - Let\u2019s Encrypt. https:\/\/letsencrypt.org\/stats\/"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1080\/001401399185595"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1518\/001872095779064555"},{"key":"e_1_3_2_1_61_1","unstructured":"Epoch. 2023. Key trends and figures in Machine Learning. https:\/\/epochai.org\/trends"},{"key":"e_1_3_2_1_62_1","unstructured":"Ege Erdil and Tamay Besiroglu. 2023. Algorithmic progress in computer vision. _eprint: 2212.05153."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1086\/467038"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1093\/idpl"},{"key":"e_1_3_2_1_65_1","unstructured":"Kevin Frazier. 2023. The Right to Reality. https:\/\/www.lawfaremedia.org\/article\/the-right-to-reality"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","unstructured":"Chengguang Gan Qinghao Zhang and Tatsunori Mori. 2024. Application of LLM Agents in Recruitment: A Novel Framework for Resume Screening. https:\/\/doi.org\/10.48550\/arXiv.2401.08315 arXiv:2401.08315 [cs].","DOI":"10.48550\/arXiv.2401.08315"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533229"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458723"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604698"},{"key":"e_1_3_2_1_70_1","volume-title":"Cooperation or resistance?: The role of tech companies in government surveillance. 131","author":"Goodwin Chloe","year":"2018","unstructured":"Chloe Goodwin. 2018. Cooperation or resistance?: The role of tech companies in government surveillance. 131 (2018), 1722\u20131722."},{"key":"e_1_3_2_1_71_1","unstructured":"Google. 2023. Bard Privacy Help Hub - Bard Help. https:\/\/support.google.com\/bard\/answer\/13594961?sjid=16420951458997305974-EU&visit_id=638406643042311657-3533103185&p=bard_pntos_retention&rd=1#retention&zippy=%2Cwhy-does-google-retain-my-conversations-after-i-turn-off-bard-activity-and-what-does-google-do-with-this-data"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clsr.2022.105681"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11403-023-00385-w"},{"key":"e_1_3_2_1_74_1","unstructured":"Ryan Greenblatt Buck Shlegeris Kshitij Sachan and Fabien Roger. 2024. AI Control: Improving Safety Despite Intentional Subversion. http:\/\/arxiv.org\/abs\/2312.06942arXiv:2312.06942 [cs]."},{"key":"e_1_3_2_1_75_1","volume-title":"NSA Prism program taps in to user data of Apple, Google and others. The Guardian (June","author":"Greenwald Glenn","year":"2013","unstructured":"Glenn Greenwald and Ewen MacAskill. 2013. NSA Prism program taps in to user data of Apple, Google and others. The Guardian (June 2013). https:\/\/www.theguardian.com\/world\/2013\/jun\/06\/us-tech-giants-nsa-data"},{"key":"e_1_3_2_1_76_1","volume-title":"Surveillance on Healthcare Workers During the First Wave of SARS-CoV-2 Pandemic in Italy: The Experience of a Tertiary Care Pediatric Hospital. Frontiers in Public Health 9","author":"Guarnieri Valentina","year":"2021","unstructured":"Valentina Guarnieri, Maria Moriondo, Mattia Giovannini, Lorenzo Lodi, Silvia Ricci, Laura Pisano, Paola Barbacci, Costanza Bini, Giuseppe Indolfi, Alberto Zanobini, and Chiara Azzari. 2021. Surveillance on Healthcare Workers During the First Wave of SARS-CoV-2 Pandemic in Italy: The Experience of a Tertiary Care Pediatric Hospital. Frontiers in Public Health 9 (2021). https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2021.644702"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","unstructured":"Julian Hazell. 2023. Large Language Models Can Be Used To Effectively Scale Spear Phishing Campaigns. https:\/\/doi.org\/10.48550\/arXiv.2305.06972 arXiv:2305.06972 [cs].","DOI":"10.48550\/arXiv.2305.06972"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","unstructured":"Dan Hendrycks. 2023. Natural Selection Favors AIs over Humans. https:\/\/doi.org\/10.48550\/arXiv.2303.16200 arXiv:2303.16200 [cs].","DOI":"10.48550\/arXiv.2303.16200"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594028"},{"key":"e_1_3_2_1_81_1","unstructured":"Marius Hobbhahn and Tamay Besiroglu. 2022. Trends in GPU Price-Performance. https:\/\/epochai.org\/blog\/trends-in-gpu-price-performance"},{"key":"e_1_3_2_1_82_1","unstructured":"Marius Hobbhahn Lennart Heim and G\u00f6k\u00e7e Aydos. 2023. Trends in machine learning hardware. https:\/\/epochai.org\/blog\/trends-in-machine-learning-hardware"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","unstructured":"Jordan Hoffmann Sebastian Borgeaud Arthur Mensch Elena Buchatskaya Trevor Cai Eliza Rutherford Diego de\u00a0Las Casas Lisa\u00a0Anne Hendricks Johannes Welbl Aidan Clark Tom Hennigan Eric Noland Katie Millican George van\u00a0den Driessche Bogdan Damoc Aurelia Guy Simon Osindero Karen Simonyan Erich Elsen Jack\u00a0W. Rae Oriol Vinyals and Laurent Sifre. 2022. Training Compute-Optimal Large Language Models. https:\/\/doi.org\/10.48550\/arXiv.2203.15556 arXiv:2203.15556 [cs].","DOI":"10.48550\/arXiv.2203.15556"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1093\/jleo\/7.special_issue.24"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.2307\/3003320"},{"key":"e_1_3_2_1_88_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_89_1","unstructured":"ISO. 2022. ISO\/IEC 27001. https:\/\/www.iso.org\/standard\/27001"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581196"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375873"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462566"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1016\/0304-405X(76)90026-X"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom\u00a0B. 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_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445899"},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579592"},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103963"},{"key":"e_1_3_2_1_98_1","volume-title":"Haoxing Du, Brian Goodrich, Max Hasin","author":"Kinniment Megan","year":"2023","unstructured":"Megan Kinniment, Lucas Jun\u00a0Koba Sato, Haoxing Du, Brian Goodrich, Max Hasin, Lawrence Chan, Luke\u00a0Harold Miles, Tao\u00a0R. Lin, Hjalmar Wijk, Joel Burget, Aaron Ho, Elizabeth Barnes, and Paul Christiano. 2023. Evaluating Language-Model Agents on Realistic Autonomous Tasks. https:\/\/evals.alignment.org\/Evaluating_LMAs_Realistic_Tasks.pdf"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.japwor.2023.101191"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","unstructured":"Leonie Koessler and Jonas Schuett. 2023. Risk assessment at AGI companies: A review of popular risk assessment techniques from other safety-critical industries. https:\/\/doi.org\/10.48550\/arXiv.2307.08823 arXiv:2307.08823 [cs].","DOI":"10.48550\/arXiv.2307.08823"},{"key":"e_1_3_2_1_101_1","doi-asserted-by":"publisher","unstructured":"Anton Korinek and Megan Juelfs. 2022. Preparing for the (Non-Existent?) Future of Work. https:\/\/doi.org\/10.3386\/w30172","DOI":"10.3386\/w30172"},{"key":"e_1_3_2_1_102_1","first-page":"57","article-title":"Intelligent Autonomous Agents are Key to Cyber Defense of the Future Army Networks","volume":"3","author":"Kott Alexander","year":"2018","unstructured":"Alexander Kott. 2018. Intelligent Autonomous Agents are Key to Cyber Defense of the Future Army Networks. The Cyber Defense Review 3, 3 (2018), 57\u201370. https:\/\/www.jstor.org\/stable\/26554997 Publisher: Army Cyber Institute.","journal-title":"The Cyber Defense Review"},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv7h0rwr"},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.1145\/258549.258592"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","unstructured":"Aiwei Liu Leyi Pan Yijian Lu Jingjing Li Xuming Hu Lijie Wen Irwin King and Philip\u00a0S. Yu. 2024. A Survey of Text Watermarking in the Era of Large Language Models. https:\/\/doi.org\/10.48550\/arXiv.2312.07913 arXiv:2312.07913 [cs].","DOI":"10.48550\/arXiv.2312.07913"},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","unstructured":"Xiao Liu Hao Yu Hanchen Zhang Yifan Xu Xuanyu Lei Hanyu Lai Yu Gu Hangliang Ding Kaiwen Men Kejuan Yang Shudan Zhang Xiang Deng Aohan Zeng Zhengxiao Du Chenhui Zhang Sheng Shen Tianjun Zhang Yu Su Huan Sun Minlie Huang Yuxiao Dong and Jie Tang. 2023. AgentBench: Evaluating LLMs as Agents. https:\/\/doi.org\/10.48550\/arXiv.2308.03688 arXiv:2308.03688 [cs].","DOI":"10.48550\/arXiv.2308.03688"},{"key":"e_1_3_2_1_107_1","volume-title":"Judges in England and Wales Given Cautious Approval to Use AI. TIME (Jan","author":"Melley Brian","year":"2024","unstructured":"Brian Melley. 2024. Judges in England and Wales Given Cautious Approval to Use AI. TIME (Jan. 2024). https:\/\/time.com\/6553030\/ai-legal-opinions-england-wales\/"},{"key":"e_1_3_2_1_108_1","unstructured":"Gr\u00e9goire Mialon Cl\u00e9mentine Fourrier Craig Swift Thomas Wolf Yann LeCun and Thomas Scialom. 2023. GAIA: a benchmark for General AI Assistants. https:\/\/arxiv.org\/abs\/2311.12983v1"},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"publisher","unstructured":"Smitha Milli Micah Carroll Yike Wang Sashrika Pandey Sebastian Zhao and Anca\u00a0D. Dragan. 2023. Engagement User Satisfaction and the Amplification of Divisive Content on Social Media. https:\/\/doi.org\/10.48550\/arXiv.2305.16941 arXiv:2305.16941 [cs].","DOI":"10.48550\/arXiv.2305.16941"},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.1007\/s44206-022-00022-2"},{"key":"e_1_3_2_1_112_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287596"},{"key":"e_1_3_2_1_113_1","doi-asserted-by":"publisher","unstructured":"Meredith\u00a0Ringel Morris Jascha Sohl-dickstein Noah Fiedel Tris Warkentin Allan Dafoe Aleksandra Faust Clement Farabet and Shane Legg. 2023. Levels of AGI: Operationalizing Progress on the Path to AGI. https:\/\/doi.org\/10.48550\/arXiv.2311.02462 arXiv:2311.02462 [cs].","DOI":"10.48550\/arXiv.2311.02462"},{"key":"e_1_3_2_1_114_1","unstructured":"mrbullwinkle and eric urban. 2023. Azure OpenAI Service abuse monitoring - Azure OpenAI. https:\/\/learn.microsoft.com\/en-us\/azure\/ai-services\/openai\/concepts\/abuse-monitoring"},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","unstructured":"Jakob M\u00f6kander Jonas Schuett Hannah\u00a0Rose Kirk and Luciano Floridi. 2023. Auditing Large Language Models: A Three-Layered Approach. https:\/\/doi.org\/10.2139\/ssrn.4361607","DOI":"10.2139\/ssrn.4361607"},{"key":"e_1_3_2_1_116_1","doi-asserted-by":"publisher","unstructured":"Silen Naihin David Atkinson Marc Green Merwane Hamadi Craig Swift Douglas Schonholtz Adam\u00a0Tauman Kalai and David Bau. 2023. Testing Language Model Agents Safely in the Wild. https:\/\/doi.org\/10.48550\/arXiv.2311.10538 arXiv:2311.10538 [cs].","DOI":"10.48550\/arXiv.2311.10538"},{"key":"e_1_3_2_1_117_1","unstructured":"Richard Ngo Lawrence Chan and S\u00f6ren Mindermann. 2022. The alignment problem from a deep learning perspective. https:\/\/arxiv.org\/abs\/2209.00626v5"},{"key":"e_1_3_2_1_118_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02639315"},{"key":"e_1_3_2_1_119_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.00328"},{"key":"e_1_3_2_1_120_1","unstructured":"U.S.\u00a0Department of Human and Health\u00a0Services. 2022. Guidance Regarding Methods for De-identification of Protected Health Information in Accordance with the Health Insurance Portability and Accountability Act (HIPAA) Privacy Rule. https:\/\/www.hhs.gov\/hipaa\/for-professionals\/privacy\/special-topics\/de-identification\/index.html Last Modified: 2023-02-22T10:17:21-0500."},{"key":"e_1_3_2_1_122_1","unstructured":"OpenAI. 2023. ChatGPT plugins. https:\/\/openai.com\/blog\/chatgpt-plugins"},{"key":"e_1_3_2_1_124_1","unstructured":"OpenAI. 2023. Introducing GPTs. https:\/\/openai.com\/blog\/introducing-gpts"},{"key":"e_1_3_2_1_125_1","unstructured":"OpenAI. 2024. Introducing the GPT Store. https:\/\/openai.com\/blog\/introducing-the-gpt-store"},{"key":"e_1_3_2_1_126_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.00672"},{"key":"e_1_3_2_1_127_1","doi-asserted-by":"publisher","unstructured":"Alexander Pan Chan\u00a0Jun Shern Andy Zou Nathaniel Li Steven Basart and others. 2023. Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark. https:\/\/doi.org\/10.48550\/arXiv.2304.03279 arXiv:2304.03279[cs] Issue: arXiv:2304.03279.","DOI":"10.48550\/arXiv.2304.03279"},{"key":"e_1_3_2_1_128_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_3_2_1_129_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372828"},{"key":"e_1_3_2_1_130_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533158"},{"key":"e_1_3_2_1_131_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534181"},{"key":"e_1_3_2_1_132_1","volume-title":"Transactions on Machine Learning Research","author":"Reed Scott","year":"2022","unstructured":"Scott Reed, Konrad Zolna, Emilio Parisotto, Sergio\u00a0G\u00f3mez Colmenarejo, Alexander Novikov, Gabriel Barth-maron, Mai Gim\u00e9nez, Yury Sulsky, Jackie Kay, Jost\u00a0Tobias Springenberg, Tom Eccles, Jake Bruce, Ali Razavi, Ashley Edwards, Nicolas Heess, Yutian Chen, Raia Hadsell, Oriol Vinyals, Mahyar Bordbar, and Nando\u00a0de Freitas. 2022. A Generalist Agent. Transactions on Machine Learning Research (2022). https:\/\/openreview.net\/forum?id=1ikK0kHjvj"},{"key":"e_1_3_2_1_133_1","unstructured":"Toran\u00a0Bruce Richards. 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_134_1","volume-title":"Infographic: Amazon Maintains Lead in the Cloud Market. https:\/\/www.statista.com\/chart\/18819\/worldwide-market-share-of-leading-cloud-infrastructure-service-providers","author":"Richter Felix","year":"2023","unstructured":"Felix Richter. 2023. Infographic: Amazon Maintains Lead in the Cloud Market. https:\/\/www.statista.com\/chart\/18819\/worldwide-market-share-of-leading-cloud-infrastructure-service-providers"},{"key":"e_1_3_2_1_135_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581407"},{"key":"e_1_3_2_1_136_1","doi-asserted-by":"publisher","unstructured":"Fabien Roger and Ryan Greenblatt. 2023. Preventing Language Models From Hiding Their Reasoning. https:\/\/doi.org\/10.48550\/arXiv.2310.18512 arXiv:2310.18512 [cs].","DOI":"10.48550\/arXiv.2310.18512"},{"key":"e_1_3_2_1_137_1","doi-asserted-by":"publisher","unstructured":"Yangjun Ruan Honghua Dong Andrew Wang Silviu Pitis Yongchao Zhou Jimmy Ba Yann Dubois Chris\u00a0J. Maddison and Tatsunori Hashimoto. 2023. Identifying the Risks of LM Agents with an LM-Emulated Sandbox. https:\/\/doi.org\/10.48550\/arXiv.2309.15817 arXiv:2309.15817 [cs].","DOI":"10.48550\/arXiv.2309.15817"},{"key":"e_1_3_2_1_138_1","volume-title":"Russell and Peter Norvig","author":"J.","year":"2021","unstructured":"Stuart\u00a0J. Russell and Peter Norvig. 2021. Artificial Intelligence: A Modern Approach (4 ed.)."},{"key":"e_1_3_2_1_139_1","doi-asserted-by":"publisher","unstructured":"Jonas Sandbrink Hamish Hobbs Jacob Swett Allan Dafoe and Anders Sandberg. 2022. Differential technology development: An innovation governance consideration for navigating technology risks. https:\/\/doi.org\/10.2139\/ssrn.4213670","DOI":"10.2139\/ssrn.4213670"},{"key":"e_1_3_2_1_140_1","unstructured":"Jonas\u00a0B. Sandbrink. 2023. Artificial intelligence and biological misuse: Differentiating risks of language models and biological design tools. http:\/\/arxiv.org\/abs\/2306.13952arXiv:2306.13952 [cs]."},{"key":"e_1_3_2_1_141_1","doi-asserted-by":"publisher","unstructured":"William Saunders Catherine Yeh Jeff Wu Steven Bills Long Ouyang Jonathan Ward and Jan Leike. 2022. Self-critiquing models for assisting human evaluators. https:\/\/doi.org\/10.48550\/arXiv.2206.05802 arXiv:2206.05802 [cs].","DOI":"10.48550\/arXiv.2206.05802"},{"key":"e_1_3_2_1_142_1","volume-title":"Debunking the AI Arms Race Theory (Summer","author":"Scharre Paul","year":"2021","unstructured":"Paul Scharre. 2021. Debunking the AI Arms Race Theory (Summer 2021). (2021). https:\/\/hdl.handle.net\/2152\/87035 Publisher: Texas National Security Review."},{"key":"e_1_3_2_1_143_1","unstructured":"Thomas\u00a0C. Schelling. 1978. Micromotives and Macrobehavior. W. W. Norton & Company."},{"key":"e_1_3_2_1_144_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.04761"},{"key":"e_1_3_2_1_145_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604693"},{"key":"e_1_3_2_1_146_1","volume-title":"Dan Braun, J\u00e9r\u00e9my Scheurer, Mikita Balesni, Lucius Bushnaq, Charlotte Stix, and Marius Hobbhahn.","author":"Sharkey Lee","year":"2023","unstructured":"Lee Sharkey, Cl\u00edodhna N\u00ed Ghuidhir, Dan Braun, J\u00e9r\u00e9my Scheurer, Mikita Balesni, Lucius Bushnaq, Charlotte Stix, and Marius Hobbhahn. 2023. A Causal Framework for AI Regulation and Auditing. https:\/\/static1.squarespace.com\/static\/6461e2a5c6399341bcfc84a5\/t\/654bc268049d687cecac24d8\/1699463818729\/auditing_framework_web.pdf"},{"key":"e_1_3_2_1_147_1","unstructured":"Yonadav Shavit Sandhini Agarwal Miles Brundage Steven Adler Cullen O\u2019Keefe Rosie Campbell Teddy Lee Pamela Mishkin Tyna Eloundou Alan Hickey Katarina Slama Lama Ahmad Paul McMillan Alex Beutel Alexandre Passos and David\u00a0G. Robinson. 2023. Practices for Governing Agentic AI Systems."},{"key":"e_1_3_2_1_148_1","volume-title":"Technical Report. United States Congress Joint Economic Committee. https:\/\/www.jec.senate.gov\/public\/index.cfm\/republicans\/2021\/12\/is-instagram-causing-poorer-mental-health-among-teen-girls","author":"Sheffield Rachel","year":"2021","unstructured":"Rachel Sheffield and Catherine Francois. 2021. Is Instagram Causing Poorer Mental Health Among Teen Girls? - Is Instagram Causing Poorer Mental Health Among Teen Girls? - United States Joint Economic Committee. Technical Report. United States Congress Joint Economic Committee. https:\/\/www.jec.senate.gov\/public\/index.cfm\/republicans\/2021\/12\/is-instagram-causing-poorer-mental-health-among-teen-girls"},{"key":"e_1_3_2_1_149_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604673"},{"key":"e_1_3_2_1_150_1","doi-asserted-by":"publisher","unstructured":"Yongliang Shen Kaitao Song Xu Tan Dongsheng Li Weiming Lu and Yueting Zhuang. 2023. HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face. https:\/\/doi.org\/10.48550\/arXiv.2303.17580 arXiv:2303.17580 [cs].","DOI":"10.48550\/arXiv.2303.17580"},{"key":"e_1_3_2_1_151_1","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v10i1.21997"},{"key":"e_1_3_2_1_152_1","unstructured":"Toby Shevlane Sebastian Farquhar Ben Garfinkel Mary Phuong Jess Whittlestone Jade Leung Daniel Kokotajlo Nahema Marchal Markus Anderljung Noam Kolt Lewis Ho Divya Siddarth Shahar Avin Will Hawkins Been Kim Iason Gabriel Vijay Bolina Jack Clark Yoshua Bengio Paul Christiano and Allan Dafoe. 2023. Model evaluation for extreme risks. https:\/\/arxiv.org\/abs\/2305.15324v2"},{"key":"e_1_3_2_1_153_1","volume-title":"An introduction to complex systems science and its applications. Complexity 2020","author":"Siegenfeld F","year":"2020","unstructured":"Alexander\u00a0F Siegenfeld and Yaneer Bar-Yam. 2020. An introduction to complex systems science and its applications. Complexity 2020 (2020), 1\u201316. Publisher: Hindawi Limited."},{"key":"e_1_3_2_1_154_1","volume-title":"Corrigibility. In Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence.","author":"Soares Nate","year":"2015","unstructured":"Nate Soares, Benja Fallenstein, Stuart Armstrong, and Eliezer Yudkowsky. 2015. Corrigibility. In Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_155_1","doi-asserted-by":"publisher","unstructured":"Emily\u00a0H. Soice Rafael Rocha Kimberlee Cordova Michael Specter and Kevin\u00a0M. Esvelt. 2023. Can large language models democratize access to dual-use biotechnology?https:\/\/doi.org\/10.48550\/arXiv.2306.03809 arXiv:2306.03809 [cs].","DOI":"10.48550\/arXiv.2306.03809"},{"key":"e_1_3_2_1_156_1","doi-asserted-by":"publisher","unstructured":"Irene Solaiman. 2023. The Gradient of Generative AI Release: Methods and Considerations. https:\/\/doi.org\/10.48550\/arXiv.2302.04844 arXiv:2302.04844 [cs].","DOI":"10.48550\/arXiv.2302.04844"},{"key":"e_1_3_2_1_157_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534185"},{"key":"e_1_3_2_1_158_1","doi-asserted-by":"publisher","unstructured":"Theodore\u00a0R. Sumers Shunyu Yao Karthik Narasimhan and Thomas\u00a0L. Griffiths. 2023. Cognitive Architectures for Language Agents. https:\/\/doi.org\/10.48550\/arXiv.2309.02427 arXiv:2309.02427 [cs].","DOI":"10.48550\/arXiv.2309.02427"},{"key":"e_1_3_2_1_159_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton S.","year":"2018","unstructured":"Richard\u00a0S. Sutton and Andrew\u00a0G. Barto. 2018. Reinforcement learning: An introduction (second edition ed.). The MIT Press, Cambridge, Massachusetts. tex.lccn: Q325.6.R45 2018."},{"key":"e_1_3_2_1_160_1","doi-asserted-by":"publisher","unstructured":"Adaptive\u00a0Agent 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_161_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.11805"},{"key":"e_1_3_2_1_162_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00465-9"},{"key":"e_1_3_2_1_163_1","doi-asserted-by":"publisher","unstructured":"Karthik Valmeekam Matthew Marquez and Subbarao Kambhampati. 2023. Can Large Language Models Really Improve by Self-critiquing Their Own Plans?https:\/\/doi.org\/10.48550\/arXiv.2310.08118 arXiv:2310.08118 [cs].","DOI":"10.48550\/arXiv.2310.08118"},{"key":"e_1_3_2_1_164_1","doi-asserted-by":"publisher","unstructured":"Karthik Valmeekam Alberto Olmo Sarath Sreedharan and Subbarao Kambhampati. 2023. 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_165_1","first-page":"2","article-title":"Regulatory Monitors: Policing Firms in the Compliance Era","volume":"119","author":"Van\u00a0Loo Rory","year":"2019","unstructured":"Rory Van\u00a0Loo. 2019. Regulatory Monitors: Policing Firms in the Compliance Era. Columbia Law Review 119, 2 (Jan. 2019), 369. https:\/\/scholarship.law.bu.edu\/faculty_scholarship\/265","journal-title":"Columbia Law Review"},{"key":"e_1_3_2_1_166_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372876"},{"key":"e_1_3_2_1_167_1","volume-title":"The rise of AI fake news is creating a \u2018misinformation superspreader\u2019. Washington Post (Dec","author":"Verma Pranshu","year":"2023","unstructured":"Pranshu Verma. 2023. The rise of AI fake news is creating a \u2018misinformation superspreader\u2019. Washington Post (Dec. 2023). https:\/\/www.washingtonpost.com\/technology\/2023\/12\/17\/ai-fake-news-misinformation\/"},{"key":"e_1_3_2_1_168_1","volume-title":"They thought loved ones were calling for help. It was an AI scam.Washington Post (March","author":"Verma Pranshu","year":"2023","unstructured":"Pranshu Verma. 2023. They thought loved ones were calling for help. It was an AI scam.Washington Post (March 2023). https:\/\/www.washingtonpost.com\/technology\/2023\/03\/05\/ai-voice-scam\/"},{"key":"e_1_3_2_1_169_1","doi-asserted-by":"publisher","unstructured":"Lei Wang Chen Ma Xueyang Feng Zeyu Zhang Hao Yang Jingsen Zhang Zhiyuan Chen Jiakai Tang Xu Chen Yankai Lin Wayne\u00a0Xin Zhao Zhewei Wei and Ji-Rong Wen. 2023. A Survey on Large Language Model based Autonomous Agents. https:\/\/doi.org\/10.48550\/arXiv.2308.11432 arXiv:2308.11432[cs] Issue: arXiv:2308.11432.","DOI":"10.48550\/arXiv.2308.11432"},{"key":"e_1_3_2_1_170_1","unstructured":"Zihan Wang Olivia Byrnes Hu Wang Ruoxi Sun Congbo Ma Huaming Chen Qi Wu and Minhui Xue. 2021. Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography. https:\/\/arxiv.org\/abs\/2107.09287v3"},{"key":"e_1_3_2_1_171_1","volume-title":"Microsoft\u2019s new Copilot Pro brings AI-powered Office features to the rest of us. The Verge (Jan","author":"Warren Tom","year":"2024","unstructured":"Tom Warren. 2024. Microsoft\u2019s new Copilot Pro brings AI-powered Office features to the rest of us. The Verge (Jan. 2024). https:\/\/www.theverge.com\/2024\/1\/15\/24038711\/microsoft-copilot-pro-office-ai-apps"},{"key":"e_1_3_2_1_172_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.11903"},{"key":"e_1_3_2_1_173_1","doi-asserted-by":"publisher","unstructured":"Laura Weidinger Maribeth Rauh Nahema Marchal Arianna Manzini Lisa\u00a0Anne Hendricks Juan Mateos-Garcia Stevie Bergman Jackie Kay Conor Griffin Ben Bariach Iason Gabriel Verena Rieser and William Isaac. 2023. Sociotechnical Safety Evaluation of Generative AI Systems. https:\/\/doi.org\/10.48550\/arXiv.2310.11986 arXiv:2310.11986 [cs].","DOI":"10.48550\/arXiv.2310.11986"},{"key":"e_1_3_2_1_174_1","doi-asserted-by":"crossref","unstructured":"David\u00a0Gray Widder Meredith Whittaker and Sarah Myers\u00a0West. 2023. Open (for Business): Big Tech Concentrated Power and the Political Economy of Open AI. https:\/\/ssrn.com\/abstract=4543807","DOI":"10.2139\/ssrn.4543807"},{"key":"e_1_3_2_1_175_1","unstructured":"Simon Willison. 2023. Prompt injection: What\u2019s the worst that can happen?https:\/\/simonwillison.net\/2023\/Apr\/14\/worst-that-can-happen\/"},{"key":"e_1_3_2_1_176_1","unstructured":"Qingyun Wu Gagan Bansal Jieyu Zhang Yiran Wu Beibin Li Erkang Zhu Li Jiang Xiaoyun Zhang Shaokun Zhang Jiale Liu Ahmed\u00a0Hassan Awadallah Ryen\u00a0W. White Doug Burger and Chi Wang. 2023. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework. _eprint: 2308.08155."},{"key":"e_1_3_2_1_177_1","unstructured":"Zelai Xu Chao Yu Fei Fang Yu Wang and Yi Wu. 2023. Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game. https:\/\/arxiv.org\/abs\/2310.18940v2"},{"key":"e_1_3_2_1_178_1","doi-asserted-by":"publisher","unstructured":"Hanlin Zhang Benjamin\u00a0L. Edelman Danilo Francati Daniele Venturi Giuseppe Ateniese and Boaz Barak. 2023. Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models. https:\/\/doi.org\/10.48550\/arXiv.2311.04378 arXiv:2311.04378 [cs].","DOI":"10.48550\/arXiv.2311.04378"},{"key":"e_1_3_2_1_179_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534200"},{"key":"e_1_3_2_1_180_1","unstructured":"Andy Zou Zifan Wang Nicholas Carlini Milad Nasr J.\u00a0Zico Kolter and Matt Fredrikson. 2023. Universal and Transferable Adversarial Attacks on Aligned Language Models. https:\/\/arxiv.org\/abs\/2307.15043v2"},{"key":"e_1_3_2_1_181_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 '24: The 2024 ACM Conference on Fairness, Accountability, and Transparency","location":"Rio de Janeiro Brazil","acronym":"FAccT '24"},"container-title":["The 2024 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630106.3658948","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3630106.3658948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:57Z","timestamp":1750287057000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630106.3658948"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,3]]},"references-count":176,"alternative-id":["10.1145\/3630106.3658948","10.1145\/3630106"],"URL":"https:\/\/doi.org\/10.1145\/3630106.3658948","relation":{},"subject":[],"published":{"date-parts":[[2024,6,3]]},"assertion":[{"value":"2024-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}