{"id":"https://openalex.org/W4378945697","doi":"https://doi.org/10.48550/arxiv.2305.19223","title":"Intent-aligned AI systems deplete human agency: the need for agency foundations research in AI safety","display_name":"Intent-aligned AI systems deplete human agency: the need for agency foundations research in AI safety","publication_year":2023,"publication_date":"2023-05-30","ids":{"openalex":"https://openalex.org/W4378945697","doi":"https://doi.org/10.48550/arxiv.2305.19223"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.19223","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.19223","pdf_url":"https://arxiv.org/pdf/2305.19223","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.19223","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072148140","display_name":"Catalin Mitelut","orcid":"https://orcid.org/0000-0003-0471-9816","observed_orcids":["https://orcid.org/0000-0003-0471-9816"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitelut, Catalin","raw_affiliation_strings":["New York University , Zurich AI Alignment Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University , Zurich AI Alignment Group","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105194558","display_name":"Ben Smith","orcid":"https://orcid.org/0009-0003-7187-0070","observed_orcids":["https://orcid.org/0009-0003-7187-0070"]},"institutions":[{"id":"https://openalex.org/I181233156","display_name":"University of Oregon","ror":"https://ror.org/0293rh119","country_code":"US","type":"education","lineage":["https://openalex.org/I181233156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Smith, Ben","raw_affiliation_strings":["University of Oregon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oregon","institution_ids":["https://openalex.org/I181233156"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080095540","display_name":"Peter W. Vamplew","orcid":"https://orcid.org/0000-0002-8687-4424","observed_orcids":["https://orcid.org/0000-0002-8687-4424"]},"institutions":[{"id":"https://openalex.org/I149672521","display_name":"Federation University","ror":"https://ror.org/05qbzwv83","country_code":"AU","type":"education","lineage":["https://openalex.org/I149672521"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Vamplew, Peter","raw_affiliation_strings":["Federation University of Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federation University of Australia","institution_ids":["https://openalex.org/I149672521"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/human-agency","display_name":"human agency","score":0.7720000147819519},{"id":"https://openalex.org/keywords/ai-alignment","display_name":"AI alignment","score":0.597000002861023},{"id":"https://openalex.org/keywords/ai-safety","display_name":"AI safety","score":0.7670000195503235},{"id":"https://openalex.org/keywords/misuse-of-ai","display_name":"AI misuse","score":0.9139999747276306},{"id":"https://openalex.org/keywords/artificial-general-intelligence","display_name":"artificial general intelligence","score":0.6729999780654907},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.8550000190734863},{"id":"https://openalex.org/keywords/embedded-agents","display_name":"embedded agents","score":0.921999990940094},{"id":"https://openalex.org/keywords/mechanistic-interpretability","display_name":"mechanistic interpretability","score":0.9100000262260437},{"id":"https://openalex.org/keywords/loss-of-agency","display_name":"loss of agency","score":0.5619999766349792}],"concepts":[{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.7712633609771729},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6650426983833313},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.6293737888336182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5281037092208862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5179104208946228},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.33898046612739563},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3201546370983124},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23884928226470947},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.2263670265674591},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2078692615032196},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.18166294693946838},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.19223","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.19223","pdf_url":"https://arxiv.org/pdf/2305.19223","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.19223","doi":"https://doi.org/10.48550/arxiv.2305.19223","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.19223","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.19223","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.19223","pdf_url":"https://arxiv.org/pdf/2305.19223","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378945697.pdf","grobid_xml":"https://content.openalex.org/works/W4378945697.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7033206588","https://openalex.org/W7204266743","https://openalex.org/W7165015952","https://openalex.org/W7161421965","https://openalex.org/W7137267772","https://openalex.org/W7117823136","https://openalex.org/W7116075166","https://openalex.org/W7202365383","https://openalex.org/W7138855862","https://openalex.org/W7213786192"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,39,98,101,135,145,153,207,222,232,237],"artificial":[4,10],"intelligence":[5,12],"(AI)":[6],"systems":[7,14,55,64,94,126,167],"suggests":[8],"that":[9,22,52,65,70,84,96,111,124,140,165,193],"general":[11],"(AGI)":[13],"may":[15,103],"soon":[16],"arrive.":[17],"Many":[18],"researchers":[19],"are":[20,56],"concerned":[21],"AIs":[23],"and":[24,50,79,95,109,117,131,137,163,212,242],"AGIs":[25],"will":[26],"harm":[27],"humans":[28,60,71,102,142,170],"via":[29],"intentional":[30],"misuse":[31],"(AI-misuse)":[32],"or":[33,68],"through":[34],"accidents":[35],"(AI-accidents).":[36],"In":[37],"respect":[38],"AI-accidents,":[40],"there":[41],"is":[42,89],"an":[43],"increasing":[44],"effort":[45],"focused":[46],"on":[47,159],"developing":[48],"algorithms":[49],"paradigms":[51],"ensure":[53],"AI":[54,63,93,125,166],"aligned":[57],"to":[58,86,113,197,218],"what":[59],"intend,":[61],"e.g.":[62],"yield":[66],"actions":[67],"recommendations":[69],"might":[72],"judge":[73],"as":[74],"consistent":[75],"with":[76,176],"their":[77],"intentions":[78],"goals.":[80],"Here":[81],"we":[82,202],"argue":[83,123,164],"alignment":[85],"human":[87,129,233],"intent":[88],"insufficient":[90],"for":[91],"safe":[92],"preservation":[97],"long-term":[99],"agency":[100,161,183,223,238],"be":[104,114,173],"a":[105,118,204],"more":[106],"robust":[107],"standard,":[108],"one":[110],"needs":[112],"separated":[115],"explicitly":[116],"priori":[119],"during":[120],"optimization.":[121],"We":[122,147,180],"can":[127,185],"reshape":[128],"intention":[130],"discuss":[132],"the":[133,149],"lack":[134],"biological":[136],"psychological":[138],"mechanisms":[139],"protect":[141],"from":[143,245],"loss":[144,184],"agency.":[146],"provide":[148],"first":[150],"formal":[151],"definition":[152],"agency-preserving":[154],"AI-human":[155,225],"interactions":[156],"which":[157],"focuses":[158],"forward-looking":[160],"evaluations":[162],"-":[168,171],"not":[169],"must":[172],"increasingly":[174],"tasked":[175],"making":[177],"these":[178],"evaluations.":[179],"show":[181],"how":[182],"occur":[186],"in":[187,224,240],"simple":[188],"environments":[189],"containing":[190],"embedded":[191],"agents":[192],"use":[194],"temporal-difference":[195],"learning":[196,244],"make":[198],"action":[199],"recommendations.":[200],"Finally,":[201],"propose":[203],"new":[205],"area":[206],"research":[208],"called":[209],"\"agency":[210],"foundations\"":[211],"pose":[213],"four":[214],"initial":[215],"topics":[216],"designed":[217],"improve":[219],"our":[220],"understanding":[221],"interactions:":[226],"benevolent":[227],"game":[228],"theory,":[229],"algorithmic":[230],"foundations":[231],"rights,":[234],"mechanistic":[235],"interpretability":[236],"representation":[239],"neural-networks":[241],"reinforcement":[243],"internal":[246],"states.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-06-01T00:00:00"}