Dimitri Coelho Mollo
Photo: SCIoI
Dimitri Coelho Mollo’s main areas of research are Philosophy of Mind and Cognitive Science (including Philosophy of Neuroscience and Philosophy of Artificial Intelligence), and Philosophy of Computing. He is also interested in Philosophy of Biology, General Philosophy of Science, and the ethics of current and future use of AI systems. Since April 2022, Dimitri is Assistant Professor at Umeå University. Dimitri’s aim is to help shed light on the nature of intelligence and intelligent behavior by bringing together relevant empirical and theoretical insights from different fields, including philosophy, cognitive science, artificial intelligence, comparative psychology, and ethology. His project aims at revealing some of the underlying theoretical principles and core notions required to make sense of intelligence in biological and artificial systems. To do so, Dimitri examines candidate foundational notions relevant for understanding intelligence, such as representation, computation, and embodiment, as well as the internal and external factors that may be required for intelligent behavior to be possible.
Projects
Dimitri Coelho Mollo is member of:
Publications +
6984777
Coelho Mollo
1
apa
50
date
desc
year
19828
https://www.scienceofintelligence.de/wp-content/plugins/zotpress/
%7B%22status%22%3A%22success%22%2C%22updateneeded%22%3Afalse%2C%22instance%22%3Afalse%2C%22meta%22%3A%7B%22request_last%22%3A0%2C%22request_next%22%3A0%2C%22used_cache%22%3Atrue%7D%2C%22data%22%3A%5B%7B%22key%22%3A%226IBR7EB3%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Dahlgren%20Lindstr%5Cu00f6m%20et%20al.%22%2C%22parsedDate%22%3A%222025-06-04%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BDahlgren%20Lindstr%26%23xF6%3Bm%2C%20A.%2C%20Methnani%2C%20L.%2C%20Krause%2C%20L.%2C%20Ericson%2C%20P.%2C%20de%20Rituerto%20de%20Troya%2C%20%26%23xCD%3B.%20M.%2C%20Coelho%20Mollo%2C%20D.%2C%20%26amp%3B%20Dobbe%2C%20R.%20%282025%29.%20Helpful%2C%20harmless%2C%20honest%3F%20Sociotechnical%20limits%20of%20AI%20alignment%20and%20safety%20through%20Reinforcement%20Learning%20from%20Human%20Feedback.%20%26lt%3Bi%26gt%3BEthics%20and%20Information%20Technology%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B27%26lt%3B%5C%2Fi%26gt%3B%282%29%2C%2028.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2Fs10676-025-09837-2%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2Fs10676-025-09837-2%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Helpful%2C%20harmless%2C%20honest%3F%20Sociotechnical%20limits%20of%20AI%20alignment%20and%20safety%20through%20Reinforcement%20Learning%20from%20Human%20Feedback%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adam%22%2C%22lastName%22%3A%22Dahlgren%20Lindstr%5Cu00f6m%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Leila%22%2C%22lastName%22%3A%22Methnani%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lea%22%2C%22lastName%22%3A%22Krause%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Petter%22%2C%22lastName%22%3A%22Ericson%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22%5Cu00cd%5Cu00f1igo%20Mart%5Cu00ednez%22%2C%22lastName%22%3A%22de%20Rituerto%20de%20Troya%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dimitri%22%2C%22lastName%22%3A%22Coelho%20Mollo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Roel%22%2C%22lastName%22%3A%22Dobbe%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20critically%20evaluates%20the%20attempts%20to%20align%20Artificial%20Intelligence%20%28AI%29%20systems%2C%20especially%20Large%20Language%20Models%20%28LLMs%29%2C%20with%20human%20values%20and%20intentions%20through%20Reinforcement%20Learning%20from%20Feedback%20methods%2C%20involving%20either%20human%20feedback%20%28RLHF%29%20or%20AI%20feedback%20%28RLAIF%29.%20Specifically%2C%20we%20show%20the%20shortcomings%20of%20the%20broadly%20pursued%20alignment%20goals%20of%20honesty%2C%20harmlessness%2C%20and%20helpfulness.%20Through%20a%20multidisciplinary%20sociotechnical%20critique%2C%20we%20examine%20both%20the%20theoretical%20underpinnings%20and%20practical%20implementations%20of%20RLHF%20techniques%2C%20revealing%20significant%20limitations%20in%20their%20approach%20to%20capturing%20the%20complexities%20of%20human%20ethics%2C%20and%20contributing%20to%20AI%20safety.%20We%20highlight%20tensions%20inherent%20in%20the%20goals%20of%20RLHF%2C%20as%20captured%20in%20the%20HHH%20principle%20%28helpful%2C%20harmless%20and%20honest%29.%20In%20addition%2C%20we%20discuss%20ethically-relevant%20issues%20that%20tend%20to%20be%20neglected%20in%20discussions%20about%20alignment%20and%20RLHF%2C%20among%20which%20the%20trade-offs%20between%20user-friendliness%20and%20deception%2C%20flexibility%20and%20interpretability%2C%20and%20system%20safety.%20We%20offer%20an%20alternative%20vision%20for%20AI%20safety%20and%20ethics%20which%20positions%20RLHF%20approaches%20within%20a%20broader%20context%20of%20comprehensive%20design%20across%20institutions%2C%20processes%20and%20technological%20systems%2C%20and%20suggest%20the%20establishment%20of%20AI%20safety%20as%20a%20sociotechnical%20discipline%20that%20is%20open%20to%20the%20normative%20and%20political%20dimensions%20of%20artificial%20intelligence.%22%2C%22date%22%3A%222025-06-04%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1007%5C%2Fs10676-025-09837-2%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2Fs10676-025-09837-2%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%221572-8439%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A16Z%22%7D%7D%2C%7B%22key%22%3A%22RZP2KCHZ%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Coelho%20Mollo%20and%20Vernazzani%22%2C%22parsedDate%22%3A%222024%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BCoelho%20Mollo%2C%20D.%2C%20%26amp%3B%20Vernazzani%2C%20A.%20%282024%29.%20The%20Formats%20of%20Cognitive%20Representation%3A%20A%20Computational%20Account.%20%26lt%3Bi%26gt%3BPhilosophy%20of%20Science%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B91%26lt%3B%5C%2Fi%26gt%3B%283%29%2C%20682%26%23x2013%3B701.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1017%5C%2Fpsa.2023.123%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1017%5C%2Fpsa.2023.123%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22The%20Formats%20of%20Cognitive%20Representation%3A%20A%20Computational%20Account%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dimitri%22%2C%22lastName%22%3A%22Coelho%20Mollo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alfredo%22%2C%22lastName%22%3A%22Vernazzani%22%7D%5D%2C%22abstractNote%22%3A%22Abstract%5Cn%20%20%20%20%20%20%20%20%20%20%20%20Cognitive%20representations%20are%20typically%20analyzed%20in%20terms%20of%20content%2C%20vehicle%2C%20and%20format.%20Although%20current%20work%20on%20formats%20appeals%20to%20intuitions%20about%20external%20representations%2C%20such%20as%20words%20and%20maps%2C%20in%20this%20article%2C%20we%20develop%20a%20computational%20view%20of%20formats%20that%20does%20not%20rely%20on%20intuitions.%20In%20our%20view%2C%20formats%20are%20individuated%20by%20the%20computational%20profiles%20of%20vehicles%2C%20that%20is%2C%20the%20set%20of%20constraints%20that%20fix%20the%20computational%20transformations%20vehicles%20can%20undergo.%20The%20resulting%20picture%20is%20strongly%20pluralistic%2C%20makes%20space%20for%20a%20variety%20of%20different%20formats%2C%20and%20is%20intimately%20tied%20to%20the%20computational%20approach%20to%20cognition%20in%20cognitive%20science%20and%20artificial%20intelligence.%22%2C%22date%22%3A%2207%5C%2F2024%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1017%5C%2Fpsa.2023.123%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.cambridge.org%5C%2Fcore%5C%2Fproduct%5C%2Fidentifier%5C%2FS003182482300123X%5C%2Ftype%5C%2Fjournal_article%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%220031-8248%2C%201539-767X%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A58%3A18Z%22%7D%7D%2C%7B%22key%22%3A%22KHWA9MPY%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Coelho%20Mollo%22%2C%22parsedDate%22%3A%222024%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BCoelho%20Mollo%2C%20D.%20%282024%29.%20Intelligent%20Behaviour.%20%26lt%3Bi%26gt%3BErkenntnis%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B89%26lt%3B%5C%2Fi%26gt%3B%282%29%2C%20705%26%23x2013%3B721.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2Fs10670-022-00552-8%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2Fs10670-022-00552-8%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Intelligent%20Behaviour%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dimitri%22%2C%22lastName%22%3A%22Coelho%20Mollo%22%7D%5D%2C%22abstractNote%22%3A%22Abstract%5Cn%20%20%20%20%20%20%20%20%20%20%20%20The%20notion%20of%20intelligence%20is%20relevant%20to%20several%20fields%20of%20research%2C%20including%20cognitive%20and%20comparative%20psychology%2C%20neuroscience%2C%20artificial%20intelligence%2C%20and%20philosophy%2C%20among%20others.%20However%2C%20there%20is%20little%20agreement%20within%20and%20across%20these%20fields%20on%20how%20to%20characterise%20and%20explain%20intelligence.%20I%20put%20forward%20a%20behavioural%2C%20operational%20characterisation%20of%20intelligence%20that%20can%20play%20an%20integrative%20role%20in%20the%20sciences%20of%20intelligence%2C%20as%20well%20as%20preserve%20the%20distinctive%20explanatory%20value%20of%20the%20notion%2C%20setting%20it%20apart%20from%20the%20related%20concepts%20of%20cognition%20and%20rationality.%20Finally%2C%20I%20examine%20a%20popular%20hypothesis%20about%20the%20underpinnings%20of%20intelligence%3A%20the%20capacity%20to%20manipulate%20internal%20representations%20of%20the%20environment.%20I%20argue%20that%20the%20hypothesis%20needs%20refinement%2C%20and%20that%20so%20refined%2C%20it%20applies%20only%20to%20some%20forms%20of%20intelligence.%22%2C%22date%22%3A%2202%5C%2F2024%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1007%5C%2Fs10670-022-00552-8%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Flink.springer.com%5C%2F10.1007%5C%2Fs10670-022-00552-8%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%220165-0106%2C%201572-8420%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A39Z%22%7D%7D%2C%7B%22key%22%3A%22JJMKHI33%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Aler%20Tubella%20et%20al.%22%2C%22parsedDate%22%3A%222023-06-12%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BAler%20Tubella%2C%20A.%2C%20Coelho%20Mollo%2C%20D.%2C%20Dahlgren%20Lindstr%26%23xF6%3Bm%2C%20A.%2C%20Devinney%2C%20H.%2C%20Dignum%2C%20V.%2C%20Ericson%2C%20P.%2C%20Jonsson%2C%20A.%2C%20Kampik%2C%20T.%2C%20Lenaerts%2C%20T.%2C%20Mendez%2C%20J.%20A.%2C%20%26amp%3B%20Nieves%2C%20J.%20C.%20%282023%29.%20ACROCPoLis%3A%20A%20Descriptive%20Framework%20for%20Making%20Sense%20of%20Fairness.%20%26lt%3Bi%26gt%3B2023%20ACM%20Conference%20on%20Fairness%20Accountability%20and%20Transparency%26lt%3B%5C%2Fi%26gt%3B%2C%201014%26%23x2013%3B1025.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F3593013.3594059%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F3593013.3594059%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22ACROCPoLis%3A%20A%20Descriptive%20Framework%20for%20Making%20Sense%20of%20Fairness%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrea%22%2C%22lastName%22%3A%22Aler%20Tubella%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dimitri%22%2C%22lastName%22%3A%22Coelho%20Mollo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adam%22%2C%22lastName%22%3A%22Dahlgren%20Lindstr%5Cu00f6m%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hannah%22%2C%22lastName%22%3A%22Devinney%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Virginia%22%2C%22lastName%22%3A%22Dignum%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Petter%22%2C%22lastName%22%3A%22Ericson%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anna%22%2C%22lastName%22%3A%22Jonsson%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Timotheus%22%2C%22lastName%22%3A%22Kampik%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tom%22%2C%22lastName%22%3A%22Lenaerts%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Julian%20Alfredo%22%2C%22lastName%22%3A%22Mendez%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Juan%20Carlos%22%2C%22lastName%22%3A%22Nieves%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22proceedingsTitle%22%3A%222023%20ACM%20Conference%20on%20Fairness%20Accountability%20and%20Transparency%22%2C%22conferenceName%22%3A%22FAccT%20%2723%3A%20the%202023%20ACM%20Conference%20on%20Fairness%2C%20Accountability%2C%20and%20Transparency%22%2C%22date%22%3A%222023-06-12%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1145%5C%2F3593013.3594059%22%2C%22ISBN%22%3A%22979-8-4007-0192-4%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fdoi%5C%2F10.1145%5C%2F3593013.3594059%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A58%3A15Z%22%7D%7D%2C%7B%22key%22%3A%22DTL7UU6F%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Coelho%20Mollo%22%2C%22parsedDate%22%3A%222022%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BCoelho%20Mollo%2C%20D.%20%282022%29.%20Deflationary%20realism%3A%20Representation%20and%20idealisation%20in%20cognitive%20science.%20%26lt%3Bi%26gt%3BMind%20%26amp%3B%20Language%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B37%26lt%3B%5C%2Fi%26gt%3B%285%29%2C%201048%26%23x2013%3B1066.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1111%5C%2Fmila.12364%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1111%5C%2Fmila.12364%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Deflationary%20realism%3A%20Representation%20and%20idealisation%20in%20cognitive%20science%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dimitri%22%2C%22lastName%22%3A%22Coelho%20Mollo%22%7D%5D%2C%22abstractNote%22%3A%22Debate%20on%20the%20nature%20of%20representation%20in%20cognitive%20systems%20tends%20to%20oscillate%20between%20robustly%20realist%20views%20and%20various%20anti%5Cu2010realist%20options.%20I%20defend%20an%20alternative%20view%2C%20deflationary%20realism%2C%20which%20sees%20cognitive%20representation%20as%20an%20offshoot%20of%20the%20extended%20application%20to%20cognitive%20systems%20of%20an%20explanatory%20model%20whose%20primary%20domain%20is%20public%20representation%20use.%20This%20extended%20application%2C%20justified%20by%20a%20common%20explanatory%20target%2C%20embodies%20idealisations%2C%20partial%20mismatches%20between%20model%20and%20reality.%20By%20seeing%20representation%20as%20part%20of%20an%20idealised%20model%2C%20deflationary%20realism%20avoids%20the%20problems%20with%20robust%20realist%20views%2C%20while%20keeping%20allegiance%20to%20realism.%22%2C%22date%22%3A%2211%5C%2F2022%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1111%5C%2Fmila.12364%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fonlinelibrary.wiley.com%5C%2Fdoi%5C%2F10.1111%5C%2Fmila.12364%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%220268-1064%2C%201468-0017%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A29Z%22%7D%7D%2C%7B%22key%22%3A%229J6Z8TAD%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Coelho%20Mollo%22%2C%22parsedDate%22%3A%222021-12-01%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BCoelho%20Mollo%2C%20D.%20%282021%29.%20Against%20Computational%20Perspectivalism.%20%26lt%3Bi%26gt%3BThe%20British%20Journal%20for%20the%20Philosophy%20of%20Science%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B72%26lt%3B%5C%2Fi%26gt%3B%284%29%2C%201129%26%23x2013%3B1153.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1093%5C%2Fbjps%5C%2Faxz036%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1093%5C%2Fbjps%5C%2Faxz036%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Against%20Computational%20Perspectivalism%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dimitri%22%2C%22lastName%22%3A%22Coelho%20Mollo%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222021-12-01%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1093%5C%2Fbjps%5C%2Faxz036%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.journals.uchicago.edu%5C%2Fdoi%5C%2F10.1093%5C%2Fbjps%5C%2Faxz036%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%220007-0882%2C%201464-3537%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A40Z%22%7D%7D%2C%7B%22key%22%3A%22URJDWPV6%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Coelho%20Mollo%22%2C%22parsedDate%22%3A%222021%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BCoelho%20Mollo%2C%20D.%20%282021%29.%20Why%20go%20for%20a%20computation-based%20approach%20to%20cognitive%20representation.%20%26lt%3Bi%26gt%3BSynthese%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B199%26lt%3B%5C%2Fi%26gt%3B%283%26%23x2013%3B4%29%2C%206875%26%23x2013%3B6895.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2Fs11229-021-03097-5%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2Fs11229-021-03097-5%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Why%20go%20for%20a%20computation-based%20approach%20to%20cognitive%20representation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dimitri%22%2C%22lastName%22%3A%22Coelho%20Mollo%22%7D%5D%2C%22abstractNote%22%3A%22Abstract%5Cn%20%20%20%20%20%20%20%20%20%20%20%20An%20influential%20view%20in%20%28philosophy%20of%29%20cognitive%20science%20is%20that%20computation%20in%20cognitive%20systems%20is%20semantic%2C%20conceptually%20depending%20on%20representation%3A%20to%20compute%20is%20to%20manipulate%20representations.%20I%20argue%20that%20accepting%20the%20non-semantic%20teleomechanistic%20view%20of%20computation%20lays%20the%20ground%20for%20a%20promising%20alternative%20strategy%2C%20in%20which%20computation%20helps%20to%20explain%20and%20naturalise%20representation%2C%20rather%20than%20the%20other%20way%20around.%20I%20show%20that%20this%20computation-based%20approach%20to%20representation%20presents%20six%20decisive%20advantages%20over%20the%20semantic%20view.%20I%20claim%20that%20it%20can%20improve%20the%20two%20most%20influential%20current%20theories%20of%20representation%2C%20teleosemantics%20and%20structural%20representation%2C%20by%20providing%20them%20with%20precious%20tools%20to%20tackle%20some%20of%20their%20main%20shortcomings.%20In%20addition%2C%20the%20computation-based%20approach%20opens%20up%20interesting%20new%20theoretical%20paths%20for%20the%20project%20of%20naturalising%20representation%2C%20in%20which%20teleology%20plays%20a%20role%20in%20individuating%20computations%2C%20but%20not%20representations.%22%2C%22date%22%3A%2212%5C%2F2021%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1007%5C%2Fs11229-021-03097-5%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Flink.springer.com%5C%2F10.1007%5C%2Fs11229-021-03097-5%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%220039-7857%2C%201573-0964%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A28Z%22%7D%7D%2C%7B%22key%22%3A%22UMNDA3AR%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Coelho%20Mollo%20et%20al.%22%2C%22parsedDate%22%3A%222021%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BCoelho%20Mollo%2C%20D.%2C%20Milli%26%23xE8%3Bre%2C%20R.%2C%20Rathkopf%2C%20C.%2C%20%26amp%3B%20Stinson%2C%20C.%20%282021%29.%20%26lt%3Bi%26gt%3BConceptual%20Combinations%20%26%23x2013%3B%20Benchmark%20task%20for%20Beyond%20the%20Imitation%20Game%20Benchmark%26lt%3B%5C%2Fi%26gt%3B%20%5BOther%5D.%20Github.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fgithub.com%5C%2Fgoogle%5C%2FBIG-bench%5C%2Ftree%5C%2Fmain%5C%2Fbigbench%5C%2Fbenchmark_tasks%5C%2Fconceptual_combinations%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fgithub.com%5C%2Fgoogle%5C%2FBIG-bench%5C%2Ftree%5C%2Fmain%5C%2Fbigbench%5C%2Fbenchmark_tasks%5C%2Fconceptual_combinations%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22document%22%2C%22title%22%3A%22Conceptual%20Combinations%20%5Cu2013%20Benchmark%20task%20for%20Beyond%20the%20Imitation%20Game%20Benchmark%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Dimitri%22%2C%22lastName%22%3A%22Coelho%20Mollo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rapha%5Cu00ebl%22%2C%22lastName%22%3A%22Milli%5Cu00e8re%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Charles%22%2C%22lastName%22%3A%22Rathkopf%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Catherine%22%2C%22lastName%22%3A%22Stinson%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22type%22%3A%22other%22%2C%22date%22%3A%222021%22%2C%22DOI%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fgithub.com%5C%2Fgoogle%5C%2FBIG-bench%5C%2Ftree%5C%2Fmain%5C%2Fbigbench%5C%2Fbenchmark_tasks%5C%2Fconceptual_combinations%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-05-26T13%3A22%3A22Z%22%7D%7D%5D%7D
Dahlgren Lindström, A., Methnani, L., Krause, L., Ericson, P., de Rituerto de Troya, Í. M., Coelho Mollo, D., & Dobbe, R. (2025). Helpful, harmless, honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human Feedback. Ethics and Information Technology, 27(2), 28. https://doi.org/10.1007/s10676-025-09837-2
Coelho Mollo, D., & Vernazzani, A. (2024). The Formats of Cognitive Representation: A Computational Account. Philosophy of Science, 91(3), 682–701. https://doi.org/10.1017/psa.2023.123
Coelho Mollo, D. (2024). Intelligent Behaviour. Erkenntnis, 89(2), 705–721. https://doi.org/10.1007/s10670-022-00552-8
Aler Tubella, A., Coelho Mollo, D., Dahlgren Lindström, A., Devinney, H., Dignum, V., Ericson, P., Jonsson, A., Kampik, T., Lenaerts, T., Mendez, J. A., & Nieves, J. C. (2023). ACROCPoLis: A Descriptive Framework for Making Sense of Fairness. 2023 ACM Conference on Fairness Accountability and Transparency, 1014–1025. https://doi.org/10.1145/3593013.3594059
Coelho Mollo, D. (2022). Deflationary realism: Representation and idealisation in cognitive science. Mind & Language, 37(5), 1048–1066. https://doi.org/10.1111/mila.12364
Coelho Mollo, D. (2021). Against Computational Perspectivalism. The British Journal for the Philosophy of Science, 72(4), 1129–1153. https://doi.org/10.1093/bjps/axz036
Coelho Mollo, D. (2021). Why go for a computation-based approach to cognitive representation. Synthese, 199(3–4), 6875–6895. https://doi.org/10.1007/s11229-021-03097-5
Coelho Mollo, D., Millière, R., Rathkopf, C., & Stinson, C. (2021). Conceptual Combinations – Benchmark task for Beyond the Imitation Game Benchmark [Other]. Github. https://github.com/google/BIG-bench/tree/main/bigbench/benchmark_tasks/conceptual_combinations
Perraudin, L., Brock, O., Coelho Mollo, D., Mareis, C., Müller, M., Nestler, A., Puhlmann, S., Schäffner, W., Steinhardt, S. 2021. »Wenn Materie lebendig wird«. Experimentallabor für Wissenschaftskommunikation »CollActive Materials«. Berlin University Alliance, project funding for 2022-2024.
https://www.collactive-materials.de/
Thursday Morning Talk -
Dimitri Coelho Mollo (Umeå University), “Functional Ontologies for AI systems: Tasks, Mechanisms, and Capacities”
Thursday Morning Talk -
Dimitri Coelho Mollo (Science of Intelligence), “The Concept of Intelligence – A progress report”
Thursday Morning Talk -
Dimitri Coelho Mollo (SCIoI), “Modelling Intelligence: The Good, the Bad, and the Plural”
