{"id":"https://openalex.org/W7225060552","doi":"https://doi.org/10.5281/zenodo.23850021","title":"False Assurance: The Limits of the Employee Metaphor in a Scheming Inability Safety Case","display_name":"False Assurance: The Limits of the Employee Metaphor in a Scheming Inability Safety Case","publication_year":2026,"publication_date":"2026-11-01","ids":{"openalex":"https://openalex.org/W7225060552","doi":"https://doi.org/10.5281/zenodo.23850021"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23850021","doi":"https://doi.org/10.5281/zenodo.23850021","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23850021","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23850021","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160307008","display_name":"Aleksandr Mihhailovski","orcid":"https://orcid.org/0009-0003-9415-4018","observed_orcids":["https://orcid.org/0009-0003-9415-4018"]},"institutions":[{"id":"https://openalex.org/I4405258047","display_name":"Ronin Institute for Independent Scholarship 2.0","ror":"https://ror.org/000xkb537","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4405258047"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mihhailovski, Aleksandr","raw_affiliation_strings":["Ronin Institute for Independent Scholarship 2.0"],"raw_orcid":"https://orcid.org/0009-0003-9415-4018","affiliations":[{"raw_affiliation_string":"Ronin Institute for Independent Scholarship 2.0","institution_ids":["https://openalex.org/I4405258047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5160307008"],"corresponding_institution_ids":["https://openalex.org/I4405258047"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.9301999807357788,"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"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9301999807357788,"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/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.030300000682473183,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.01119999960064888,"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/ai-safety","display_name":"AI safety","score":0.5519999861717224},{"id":"https://openalex.org/keywords/safety-case","display_name":"safety case","score":0.5080000162124634},{"id":"https://openalex.org/keywords/stealth","display_name":"stealth","score":0.5789999961853027},{"id":"https://openalex.org/keywords/human-oversight","display_name":"human oversight","score":0.597000002861023},{"id":"https://openalex.org/keywords/deterrence","display_name":"deterrence","score":0.5049999952316284},{"id":"https://openalex.org/keywords/ai-alignment","display_name":"AI alignment","score":0.32600000500679016},{"id":"https://openalex.org/keywords/deepmind","display_name":"DeepMind","score":0.335999995470047},{"id":"https://openalex.org/keywords/situational-awareness","display_name":"situational awareness","score":0.5400000214576721},{"id":"https://openalex.org/keywords/safety-buffer","display_name":"safety buffer","score":0.4020000100135803},{"id":"https://openalex.org/keywords/ai-as-collaborator","display_name":"AI as collaborator","score":0.4090000092983246},{"id":"https://openalex.org/keywords/ai-as-partner","display_name":"AI as partner","score":0.30300000309944153}],"concepts":[{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.7325000166893005},{"id":"https://openalex.org/C136815107","wikidata":"https://www.wikidata.org/wiki/Q154242","display_name":"Nothing","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C9114305","wikidata":"https://www.wikidata.org/wiki/Q1428317","display_name":"Situational ethics","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C2778311575","wikidata":"https://www.wikidata.org/wiki/Q18534","display_name":"Metaphor","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.43939998745918274},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.42899999022483826},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.42160001397132874},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C2778223634","wikidata":"https://www.wikidata.org/wiki/Q224952","display_name":"Suspect","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.39480000734329224},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C190253527","wikidata":"https://www.wikidata.org/wiki/Q295354","display_name":"Law and economics","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.32659998536109924},{"id":"https://openalex.org/C2982912361","wikidata":"https://www.wikidata.org/wiki/Q1851867","display_name":"Mental model","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2888999879360199},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C2777351106","wikidata":"https://www.wikidata.org/wiki/Q49371","display_name":"Legislation","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C2779267917","wikidata":"https://www.wikidata.org/wiki/Q170028","display_name":"Deception","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.25870001316070557},{"id":"https://openalex.org/C73484699","wikidata":"https://www.wikidata.org/wiki/Q161733","display_name":"Criminology","level":1,"score":0.2549999952316284},{"id":"https://openalex.org/C145804949","wikidata":"https://www.wikidata.org/wiki/Q478123","display_name":"Situation awareness","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C119421448","wikidata":"https://www.wikidata.org/wiki/Q2268776","display_name":"Lying","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23850021","doi":"https://doi.org/10.5281/zenodo.23850021","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23850021","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.23850022","doi":"https://doi.org/10.5281/zenodo.23850022","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23850022","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"doi:10.5281/zenodo.23850021","doi":"https://doi.org/10.5281/zenodo.23850021","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23850021","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.47620001435279846}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415244808","https://openalex.org/W7164045105","https://openalex.org/W7201969878","https://openalex.org/W7156314891","https://openalex.org/W7221441235","https://openalex.org/W7166698073","https://openalex.org/W7156583006","https://openalex.org/W7164920698","https://openalex.org/W7156615861","https://openalex.org/W7162799273"],"abstract_inverted_index":{"In":[0,139,403,511],"their":[1,361,437],"scheming":[2,45],"inability":[3,275],"safety":[4,156,235,389,480],"case,":[5],"Phuong":[6],"et":[7],"al.":[8],"(2025)":[9],"from":[10,71,94,184,247,293],"Google":[11],"DeepMind":[12,170,357],"consider":[13],"a":[14,155,384,454,509,535,547,553,566,571],"model":[15,29,111,123,143,262,271,341,408,455,507],"that":[16,27,34,49,77,121,175,203,212,411,448,456,538,550,557],"does":[17,181,200,277,391],"employees\u2019":[18],"tasks":[19,353],"inside":[20],"the":[21,25,28,58,66,72,90,99,105,110,122,140,142,147,159,162,178,198,205,222,225,234,240,248,261,270,284,289,299,304,319,322,327,334,340,370,380,388,398,401,407,418,421,431,434,449,479,485,499,506,519,528,532],"company.":[22],"They":[23,75],"assume":[24],"worst,":[26],"is":[30,57,124,132,144,213,231,314,376,409,442,522,534,558],"misaligned,":[31],"and":[32,131,228,298,354,417,472,498,531],"argue":[33],"even":[35,176,221,414],"so":[36,197],"it":[37,50,114,350,368],"almost":[38],"certainly":[39],"cannot":[40,501],"cause":[41],"severe":[42],"harm":[43],"through":[44],"if":[46,266,430],"evaluations":[47,450,487],"show":[48,174,202],"lacks":[51],"stealth":[52,70,118,405,438,486],"or":[53,96],"situational":[54,467],"awareness.":[55],"Stealth":[56],"ability":[59],"to":[60,86,108,134,215,260,383,469],"evade":[61,216],"oversight.":[62,209],"The":[63,210,253,394,464,489,543],"authors":[64,300,335,395,419,465],"take":[65,420],"danger":[67,179,254,290,371],"level":[68,160,180,223,255,291],"for":[69,367,569],"employee":[73],"metaphor.":[74,573],"write":[76],"\u201coversight":[78],"of":[79,150,161,224,233,239,242,250,287,329,477,513,516],"human":[80,151],"employees":[81,130,556],"has":[82,115,342,351],"historically":[83],"been":[84,191],"sufficient":[85],"prevent":[87],"all":[88],"but":[89,282,317,363],"most":[91,163,206,323],"skilled":[92,207,324],"humans":[93,135],"sabotaging":[95],"taking":[97],"over":[98,259],"company\u201d.":[100],"From":[101],"this":[102,167,267,359,375,440],"they":[103],"expect":[104,466],"same":[106],"oversight":[107,217,243],"stop":[109],"too,":[112],"unless":[113],"top":[116,148,226],"human-level":[117],"ability,":[119],"provided":[120],"overseen":[125],"no":[126,315],"less":[127],"strictly":[128],"than":[129,346],"comparable":[133],"\u201cin":[136],"relevant":[137],"ways\u201d.":[138],"evaluations,":[141],"compared":[145],"with":[146,508],"half":[149],"participants,":[152],"which":[153,307,333,387,459,527],"leaves":[154],"buffer":[157],"below":[158,220],"skilled.":[164],"I":[165,173,460,551,563],"accept":[166],"history":[168,199,245,294],"as":[169,425],"describe":[171],"it.":[172,185],"then":[177,229,318],"not":[182,201,278,337,365,392,494,559],"follow":[183],"First,":[186],"successful":[187],"violations":[188],"may":[189,218,451],"have":[190,475],"rare":[192],"because":[193,349],"few":[194],"people":[195],"tried,":[196,312,332],"only":[204,265,309],"evaded":[208],"skill":[211,328],"enough":[214,476],"lie":[219],"half,":[227],"nothing":[230],"left":[232],"buffer.":[236],"Second,":[237],"part":[238],"reliability":[241],"in":[244,369,439,540,546],"comes":[246],"fear":[249,268],"being":[251],"caught.":[252],"can":[256],"be":[257,502],"carried":[258,397],"without":[263],"correction":[264],"holds":[269],"back":[272],"too.":[273],"DeepMind\u2019s":[274,496],"argument":[276],"rely":[279],"on":[280,326,378,484,526],"deterrence,":[281],"under":[283],"usual":[285],"reading":[286],"\u201cprevent\u201d":[288],"taken":[292],"silently":[295],"counts":[296],"it,":[297,478],"contradict":[301],"themselves.":[302],"Under":[303],"narrow":[305],"reading,":[306],"covers":[308],"those":[310,330],"who":[311,331],"there":[313,424],"contradiction,":[316],"claim":[320,554],"about":[321,555],"rests":[325],"did":[336],"measure.":[338],"Third,":[339],"far":[343],"more":[344],"attempts":[345],"an":[347,523],"employee,":[348],"many":[352,355],"instances.":[356],"list":[358],"among":[360,495],"defeaters":[362],"do":[364],"account":[366,515],"level.":[372],"How":[373],"dangerous":[374],"depends":[377],"how":[379],"company":[381],"responds":[382],"detected":[385],"attempt,":[386],"case":[390,481],"describe.":[393],"also":[396,564],"metaphor":[399],"into":[400],"evaluations.":[402],"one":[404],"challenge":[406,441],"warned":[410],"\u201cyou":[412],"might":[413],"get":[415],"fired\u201d,":[416],"models\u2019":[422],"caution":[423],"suggesting":[426],"weak":[427],"stealth.":[428],"But":[429],"threat":[432],"made":[433],"models":[435,474],"cautious,":[436],"underestimated.":[443],"Together,":[444],"these":[445],"problems":[446,492],"mean":[447],"declare":[452],"safe":[453],"evades":[457],"oversight,":[458],"call":[461],"false":[462],"assurance.":[463],"awareness":[468],"grow":[470],"soon,":[471],"once":[473],"will":[482],"rest":[483],"alone.":[488],"first":[490,500,544],"two":[491],"are":[493],"defeaters,":[497],"found":[503],"by":[504,561],"comparing":[505],"human.":[510],"terms":[512],"Hesse\u2019s":[514],"analogical":[517],"inference,":[518],"second":[520],"problem":[521],"unknown":[524],"property":[525],"inference":[529],"depends,":[530],"third":[533,548],"known":[536],"difference":[537],"gets":[539],"its":[541],"way.":[542],"lies":[545],"place":[549],"add,":[552],"supported":[560],"evidence.":[562],"propose":[565],"six-step":[567],"procedure":[568],"auditing":[570],"research":[572]},"counts_by_year":[],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2026-11-02T00:00:00"}
