arxiv: 2604.09586 · v1 · submitted 2026-02-27 · 💻 cs.HC

Recognition: 2 theorem links

· Lean Theorem

Co-Disclosing the Computer: LLM-Mediated Computing through Reflective Conversation

Mattias Rost

Authors on Pith no claims yet

Pith reviewed 2026-05-15 18:54 UTC · model grok-4.3

classification 💻 cs.HC

keywords LLM-mediated computingreflective conversationco-disclosurepostphenomenologyhuman-computer interactiondynamic softwareintent-based interaction

0 comments

The pith

LLM-mediated computing lets interaction emerge in real time through human intent and model interpretation instead of fixed applications.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This conceptual paper introduces LLM-mediated computing as a paradigm shift where computer functionality is no longer locked into static applications but arises dynamically as humans converse with large language models. The authors frame this through the metaphor of reflective conversation to guide how such systems should be designed and experienced. They draw on postphenomenology to analyze the resulting human-LLM-computer relations and propose co-disclosure as the mechanism by which the computer's capabilities become available only in the moment of use. A sympathetic reader would care because this view dissolves the traditional boundary between user goals and software tools, suggesting that computing itself is reconstituted on the fly rather than selected from a menu of prebuilt programs.

Core claim

LLM-mediated computing constitutes a new mode of interaction in which the computer is co-disclosed through reflective conversation: human intent and LLM interpretation together generate functionality in real time without dependence on fixed application structures, analyzed via a postphenomenological lens.

What carries the argument

The reflective conversation metaphor, which treats ongoing dialogue as the process that discloses and assembles computing capabilities dynamically.

If this is right

Traditional application boundaries dissolve as tasks are assembled on demand from conversational turns.
Design work shifts from crafting fixed interfaces to shaping patterns of intent expression and interpretation.
Postphenomenological analysis becomes a practical tool for examining how human relations to technology change when the computer is no longer a stable object.
Co-disclosure replaces the idea of a fully pre-specified computer, making functionality available only through use.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Users may need to cultivate new habits of precise yet flexible intent phrasing to make the system reliable.
Software development could move from building complete apps to curating or steering LLM interpretation layers.
Hybrid approaches that retain minimal fixed scaffolds might emerge to handle cases where pure conversational emergence proves unstable.

Load-bearing premise

LLMs can consistently and reliably interpret open-ended human intent to dynamically constitute computing functionality without fixed structures.

What would settle it

Repeated trials in which users state open-ended intents and the resulting LLM-mediated system produces non-functional or inconsistent computing behavior more often than not.

read the original abstract

Large language models (LLMs) are changing how we interact with computers. As they become capable of generating software dynamically, they invite a fundamental rethinking of the computer's role in human activity. In this conceptual paper, we introduce LLM-mediated computing: a paradigm in which interaction is no longer structured around fixed applications, but emerges in real-time through human intent and LLM interpretation. We make three contributions: (1) we articulate a new interaction metaphor of reflective conversation to guide future design, (2) we use the lens of postphenomenology to understand the human-LLM-computer relation, and (3) we propose a new mode of computing based on co-disclosure, in which the computer is constituted in use. Together, they define a new mode of computing, provide a lens to analyze it, and offer a metaphor to design with.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper introduces a conceptual framing for LLM-mediated computing through reflective conversation and co-disclosure but stays high-level without mechanisms or evidence for handling intent ambiguity or state consistency.

read the letter

The main thing here is a proposal for LLM-mediated computing, where interactions emerge in real time from human intent interpreted by an LLM instead of fixed applications. It uses reflective conversation as a design metaphor, applies a postphenomenological lens to the human-LLM-computer relation, and suggests co-disclosure as the way the computer gets constituted in use. These three pieces are presented as defining a new mode of computing. The combination of the metaphor, the philosophical lens, and the co-disclosure mode is new as a unified package, and the paper does a clean job of laying them out together so they reinforce each other. That synthesis could give HCI theorists a fresh way to talk about what changes when LLMs generate behavior on the fly. The postphenomenological angle is applied directly and without forcing, which keeps the argument readable. The soft spots are straightforward. The whole piece is conceptual with no examples, scenarios, prototypes, or analysis of how an LLM would actually maintain coherent state across turns, recover from unclear intent, or avoid drift. The central assumption that open-ended intent can reliably produce consistent functionality is stated but not tested or even walked through in any detail, so the claims rest on an unexamined premise about current model behavior. This is not a fatal gap for a purely theoretical paper, but it does limit how far the argument can be pushed. The work is aimed at readers who follow philosophical HCI and postphenomenology applied to new interfaces. Someone looking for implementable designs, empirical checks, or concrete predictions will not find them. The citations stay within relevant prior literature without obvious padding. I would bring this to a reading group for the framing discussion, but I would not cite it as a result in my own work. It deserves a serious referee in a venue that publishes conceptual pieces, because the synthesis is original enough to get useful feedback even if the authors will need to add more on the practical limits.

Referee Report

2 major / 2 minor

Summary. This conceptual paper introduces LLM-mediated computing as a paradigm in which interaction emerges in real-time through human intent and LLM interpretation rather than fixed applications. It contributes (1) a reflective conversation metaphor for design, (2) a postphenomenological analysis of the human-LLM-computer relation, and (3) a co-disclosure mode in which the computer is constituted in use.

Significance. If the interpretive framework holds, the work could usefully extend postphenomenology into generative-AI contexts and supply a design metaphor for intent-driven systems. Its purely conceptual character, however, means significance hinges on whether future empirical or technical work can operationalize the unexamined assumptions about LLM reliability in open-ended interaction.

major comments (2)

[Abstract] Abstract: the central claim that interaction 'emerges in real-time through human intent and LLM interpretation' without fixed applications is load-bearing for the entire paradigm, yet the manuscript provides no account of state maintenance, ambiguity resolution, or error recovery across turns; this leaves the proposal dependent on an unexamined reliability assumption.
[Contributions] Section on contributions (reflective conversation and co-disclosure): the three listed contributions are presented as jointly defining a new mode of computing, but the postphenomenological lens and co-disclosure remain interpretive extensions of prior literature without concrete mechanisms, examples, or falsifiable implications that would allow the paradigm to be distinguished from existing conversational interfaces.

minor comments (2)

[Abstract] The abstract and introduction could more explicitly differentiate LLM-mediated computing from current LLM-augmented tools (e.g., code generators or chat-based IDEs) to sharpen the novelty claim.
Notation for key terms such as 'reflective conversation' and 'co-disclosure' is introduced without a dedicated glossary or consistent cross-referencing, which may hinder readers unfamiliar with the cited postphenomenology literature.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive comments. Our responses address each major point directly, with revisions planned where the feedback identifies gaps in the current conceptual framing.

read point-by-point responses

Referee: [Abstract] the central claim that interaction 'emerges in real-time through human intent and LLM interpretation' without fixed applications is load-bearing for the entire paradigm, yet the manuscript provides no account of state maintenance, ambiguity resolution, or error recovery across turns; this leaves the proposal dependent on an unexamined reliability assumption.

Authors: We agree that the manuscript, being conceptual, does not supply technical mechanisms for state maintenance, ambiguity resolution, or error recovery. These elements are intentionally left as open questions for subsequent implementation work. In revision we will add an explicit subsection under 'Limitations and Open Challenges' that states the reliability assumptions about current LLMs and enumerates the missing operational details as necessary future research. revision: yes
Referee: [Contributions] the three listed contributions are presented as jointly defining a new mode of computing, but the postphenomenological lens and co-disclosure remain interpretive extensions of prior literature without concrete mechanisms, examples, or falsifiable implications that would allow the paradigm to be distinguished from existing conversational interfaces.

Authors: The contributions are framed as interpretive and metaphorical precisely because the paper's purpose is to supply a new lens rather than an implemented system. To address the request for distinction, we will expand the 'Reflective Conversation' section with two brief, real-world LLM interaction vignettes that highlight how co-disclosure differs from turn-based chat. We will also add a short paragraph outlining potential falsifiable implications (e.g., measurable changes in user sense of agency) for future empirical studies. No new empirical data will be added, as that lies outside the paper's conceptual scope. revision: partial

Circularity Check

0 steps flagged

No significant circularity; conceptual definition of LLM-mediated computing extends external postphenomenology literature

full rationale

The paper introduces LLM-mediated computing as a new paradigm defined by real-time emergence through human intent and LLM interpretation, using the lens of postphenomenology and proposing co-disclosure. This is a definitional and metaphorical contribution rather than a derivation chain. No equations, fitted parameters, or predictions are present. The central framing draws on cited external literature without reducing to self-citation load-bearing steps or self-definitional loops. The derivation remains self-contained as a conceptual reframing, consistent with the reader's low circularity assessment.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 2 invented entities

The paper rests on philosophical assumptions from postphenomenology and introduces new conceptual entities without independent empirical or formal support.

axioms (1)

domain assumption Postphenomenology provides an appropriate lens for analyzing human-LLM-computer relations
Invoked to understand the mediation relation in the proposed paradigm.

invented entities (2)

LLM-mediated computing no independent evidence
purpose: New paradigm replacing fixed-application interaction
Introduced as the core contribution; no independent evidence or falsifiable prediction supplied.
reflective conversation no independent evidence
purpose: Interaction metaphor to guide design
New metaphor proposed; no external validation or prior use cited.

pith-pipeline@v0.9.0 · 5432 in / 1128 out tokens · 20020 ms · 2026-05-15T18:54:33.843896+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Foundation/RealityFromDistinction.lean reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

we introduce LLM-mediated computing: a paradigm in which interaction is no longer structured around fixed applications, but emerges in real-time through human intent and LLM interpretation... new mode of computing based on co-disclosure, in which the computer is constituted in use
IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

reflective conversation... cycles of seeing–moving–seeing... backtalk... reframing

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

75 extracted references · 75 canonical work pages · 3 internal anchors

[1]

Philip E. Agre. 1994. Surveillance and Capture: Two Models of Privacy.The In- formation Society10, 2 (April 1994), 101–127. doi:10.1080/01972243.1994.9960162

work page doi:10.1080/01972243.1994.9960162 1994
[2]

Bennett, Kori Inkpen, Jaime Teevan, Ruth Kikin-Gil, and Eric Horvitz

Saleema Amershi, Dan Weld, Mihaela Vorvoreanu, Adam Fourney, Besmira Nushi, Penny Collisson, Jina Suh, Shamsi Iqbal, Paul N. Bennett, Kori Inkpen, Jaime Teevan, Ruth Kikin-Gil, and Eric Horvitz. 2019. Guidelines for Human- AI Interaction. InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI ’19). Association for Computing Ma...

work page doi:10.1145/3290605.3300233 2019
[3]

Vera Liao, and Justin D

Zahra Ashktorab, Mohit Jain, Q. Vera Liao, and Justin D. Weisz. 2019. Resilient Chatbots: Repair Strategy Preferences for Conversational Breakdowns. InPro- ceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI ’19). Association for Computing Machinery, New York, NY, USA, 1–12. doi:10.1145/3290605.3300484

work page doi:10.1145/3290605.3300484 2019
[4]

2015.Humanistic HCI

Jeffrey Bardzell and Shaowen Bardzell. 2015.Humanistic HCI. Springer Interna- tional Publishing, Cham. doi:10.1007/978-3-031-02214-2

work page doi:10.1007/978-3-031-02214-2 2015
[5]

Michel Beaudouin-Lafon. 2000. Instrumental Interaction: An Interaction Model for Designing Post-WIMP User Interfaces. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’00). Association for Computing Machinery, New York, NY, USA, 446–453. doi:10.1145/332040.332473

work page doi:10.1145/332040.332473 2000
[6]

On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? In Proc

Emily M. Bender, Timnit Gebru, Angelina McMillan-Major, and Margaret Mitchell. 2021. On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?. InProceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (FAccT ’21). Association for Computing Machinery, New York, NY, USA, 610–623. doi:10.1145/3442188.3445922

work page doi:10.1145/3442188.3445922 2021
[7]

2019.Race After Technology: Abolitionist Tools for the New Jim Code

Ruha Benjamin. 2019.Race After Technology: Abolitionist Tools for the New Jim Code. John Wiley & Sons

work page 2019
[8]

Abeba Birhane. 2021. Algorithmic Injustice: A Relational Ethics Approach. Patterns2, 2 (Feb. 2021), 100205. doi:10.1016/j.patter.2021.100205

work page doi:10.1016/j.patter.2021.100205 2021
[9]

Susanne Bødker. 2006. When Second Wave HCI Meets Third Wave Challenges. In Proceedings of the 4th Nordic Conference on Human-computer Interaction: Changing Roles (NordiCHI ’06). Association for Computing Machinery, New York, NY, USA, 1–8. doi:10.1145/1182475.1182476

work page doi:10.1145/1182475.1182476 2006
[10]

Bowker and Susan Leigh Star

Geoffrey C. Bowker and Susan Leigh Star. 2000.Sorting Things Out: Classification and Its Consequences. MIT Press, Cambridge, MA, USA

work page 2000
[11]

Jennie Carroll. 2004. Completing Design in Use: Closing the Appropriation Cycle. ECIS 2004 Proceedings(Jan. 2004)

work page 2004
[12]

Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, Nick Ryder, Mikhail Pavlov, Alethea Power, Lukasz Kaiser, Mohammad Bavarian...

work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2107.03374 2021
[13]

Ravi Chugh, Brian Hempel, Mitchell Spradlin, and Jacob Albers. 2016. Pro- grammatic and Direct Manipulation, Together at Last. InProceedings of the 37th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI ’16). Association for Computing Machinery, New York, NY, USA, 341–354. doi:10.1145/2908080.2908103

work page doi:10.1145/2908080.2908103 2016
[14]

Clark and Susan E

Herbert H. Clark and Susan E. Brennan. 1991. Grounding in Communication. In Perspectives on Socially Shared Cognition., Lauren B. Resnick, John M. Levine, and Stephanie D. Teasley (Eds.). American Psychological Association, Washington, 127–149. doi:10.1037/10096-006

work page doi:10.1037/10096-006 1991
[15]

2020.AI Ethics

Mark Coeckelbergh. 2020.AI Ethics. MIT Press

work page 2020
[16]

2021.The Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence

Kate Crawford. 2021.The Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence. Yale University Press

work page 2021
[17]

Halbert, David Kurlander, Henry Lieberman, David Maulsby, Brad A

Allen Cypher, Daniel C. Halbert, David Kurlander, Henry Lieberman, David Maulsby, Brad A. Myers, and Alan Turransky (Eds.). 1993.Watch What I Do: Programming by Demonstration. MIT Press, Cambridge, MA, USA

work page 1993
[18]

Bas de Boer. 2021. Explaining Multistability: Postphenomenology and Affor- dances of Technologies.AI Soc.38, 6 (Sept. 2021), 2267–2277. doi:10.1007/s00146- 021-01272-3

work page doi:10.1007/s00146- 2021
[19]

2001.Where the Action Is: The Foundations of Embodied Interaction

Paul Dourish. 2001.Where the Action Is: The Foundations of Embodied Interaction. The MIT Press. doi:10.7551/mitpress/7221.001.0001

work page doi:10.7551/mitpress/7221.001.0001 2001
[20]

2013.Speculative Everything: Design, Fiction, and Social Dreaming

Anthony Dunne and Fiona Raby. 2013.Speculative Everything: Design, Fiction, and Social Dreaming. MIT Press

work page 2013
[21]

Thomas Erickson. 1990. Working with Interface Metaphors. InThe Art of Human Computer Interface Design, B Laurel (Ed.). Addison-Wesley, 65–73

work page 1990
[22]

Gerhard Fischer and Elisa Giaccardi. 2006. Meta-Design: A Framework for the Future of End-User Development. InEnd User Development, Henry Lieberman, Fabio Paternò, and Volker Wulf (Eds.). Springer Netherlands, Dordrecht, 427–457. doi:10.1007/1-4020-5386-X_19

work page doi:10.1007/1-4020-5386-x_19 2006
[23]

Fischer, Stuart Reeves, Martin Porcheron, and Rein Ove Sikveland

Joel E. Fischer, Stuart Reeves, Martin Porcheron, and Rein Ove Sikveland. 2019. Progressivity for Voice Interface Design. InProceedings of the 1st International Conference on Conversational User Interfaces (CUI ’19). Association for Computing Machinery, New York, NY, USA, 1–8. doi:10.1145/3342775.3342788

work page doi:10.1145/3342775.3342788 2019
[24]

Christopher Frauenberger. 2019. Entanglement HCI The Next Wave?ACM Trans. Comput.-Hum. Interact.27, 1 (Nov. 2019), 2:1–2:27. doi:10.1145/3364998

work page doi:10.1145/3364998 2019
[25]

2013.Truth and Method

Hans-Georg Gadamer. 2013.Truth and Method. A&C Black

work page 2013
[26]

Gaver, Jacob Beaver, and Steve Benford

William W. Gaver, Jacob Beaver, and Steve Benford. 2003. Ambiguity as a Resource for Design. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’03). Association for Computing Machinery, New York, NY, USA, 233–240. doi:10.1145/642611.642653

work page doi:10.1145/642611.642653 2003
[27]

Katrin Glinka and Claudia Müller-Birn. 2023. Critical-Reflective Human-AI Collaboration: Exploring Computational Tools for Art Historical Image Retrieval. Proc. ACM Hum.-Comput. Interact.7, CSCW2 (Oct. 2023), 263:1–263:33. doi:10. 1145/3610054

work page 2023
[28]

2007.The Three Paradigms of HCI

Steve Harrison, Deborah Tatar, and Phoebe Sengers. 2007.The Three Paradigms of HCI. Alt. Chi. Session at the SIGCHI Conference on Human Factors in Computing Systems San Jose, California, USA

work page 2007
[29]

James Hollan, Edwin Hutchins, and David Kirsh. 2000. Distributed Cognition: Toward a New Foundation for Human-Computer Interaction Research.ACM Trans. Comput.-Hum. Interact.7, 2 (June 2000), 174–196. doi:10.1145/353485. Mattias Rost 353487

work page doi:10.1145/353485 2000
[30]

Eric Horvitz. 1999. Principles of Mixed-Initiative User Interfaces. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’99). Association for Computing Machinery, New York, NY, USA, 159–166. doi:10. 1145/302979.303030

work page arXiv 1999
[31]

1990.Technology and the Lifeworld: From Garden to Earth

Don Ihde. 1990.Technology and the Lifeworld: From Garden to Earth. Indiana University Press

work page 1990
[32]

Jacob, Audrey Girouard, Leanne M

Robert J.K. Jacob, Audrey Girouard, Leanne M. Hirshfield, Michael S. Horn, Orit Shaer, Erin Treacy Solovey, and Jamie Zigelbaum. 2008. Reality-Based Interaction: A Framework for Post-WIMP Interfaces. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’08). Association for Computing Machinery, New York, NY, USA, 201–210. doi:...

work page doi:10.1145/1357054.1357089 2008
[33]

Johnson, T.L

J. Johnson, T.L. Roberts, W. Verplank, D.C. Smith, C.H. Irby, M. Beard, and K. Mackey. 1989. The Xerox Star: A Retrospective.Computer22, 9 (Sept. 1989), 11–26. doi:10.1109/2.35211

work page doi:10.1109/2.35211 1989
[34]

Martin Jonsson, Jakob Tholander, Mattias Rost, Advait Sarkar, Ylva Fernaeus, Ahmed Kharrufa, and Thomas Ludwig. 2025. The End of Programming as We Know It: Envisioning Radical Re-Conceptualizations of Co-Coding with AI. In Adjunct Proceedings of the Sixth Decennial Aarhus Conference: Computing X Crisis (AAR Adjunct ’25). Association for Computing Machiner...

work page doi:10.1145/3737609.3747093 2025
[35]

Alan C. Kay. 1993. The Early History of Smalltalk.SIGPLAN Not.28, 3 (March 1993), 69–95. doi:10.1145/155360.155364

work page doi:10.1145/155360.155364 1993
[36]

Amy J. Ko, Robin Abraham, Laura Beckwith, Alan Blackwell, Margaret Burnett, Martin Erwig, Chris Scaffidi, Joseph Lawrance, Henry Lieberman, Brad Myers, Mary Beth Rosson, Gregg Rothermel, Mary Shaw, and Susan Wiedenbeck. 2011. The State of the Art in End-User Software Engineering.ACM Comput. Surv.43, 3 (April 2011), 21:1–21:44. doi:10.1145/1922649.1922658

work page doi:10.1145/1922649.1922658 2011
[37]

Alina Krischkowsky, Bernhard Maurer, and Manfred Tscheligi. 2016. Captology and Technology Appropriation: Unintended Use as a Source for Designing Per- suasive Technologies. InPersuasive Technology, Alexander Meschtscherjakov, Boris De Ruyter, Verena Fuchsberger, Martin Murer, and Manfred Tscheligi (Eds.). Springer International Publishing, Cham, 78–83. d...

work page doi:10.1007/978-3-319-31510- 2016
[38]

Olya Kudina and Peter-Paul Verbeek. 2019. Ethics from Within: Google Glass, the Collingridge Dilemma, and the Mediated Value of Privacy.Science, Technology, & Human Values44, 2 (March 2019), 291–314. doi:10.1177/0162243918793711

work page doi:10.1177/0162243918793711 2019
[39]

Kari Kuutti and Liam J. Bannon. 2014. The Turn to Practice in HCI: Towards a Research Agenda. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’14). Association for Computing Machinery, New York, NY, USA, 3543–3552. doi:10.1145/2556288.2557111

work page doi:10.1145/2556288.2557111 2014
[40]

2003.Metaphors We Live By

George Lakoff and Mark Johnson. 2003.Metaphors We Live By. University of Chicago Press, Chicago, IL

work page 2003
[41]

Liang, Melissa Lin, Nikitha Rao, and Brad A

Jenny T. Liang, Melissa Lin, Nikitha Rao, and Brad A. Myers. 2025. Prompts Are Programs Too! Understanding How Developers Build Software Containing Prompts.Proc. ACM Softw. Eng.2, FSE (June 2025), FSE072:1591–FSE072:1614. doi:10.1145/3729342

work page doi:10.1145/3729342 2025
[42]

Vera Liao, Daniel Gruen, and Sarah Miller

Q. Vera Liao, Daniel Gruen, and Sarah Miller. 2020. Questioning the AI: Informing Design Practices for Explainable AI User Experiences. InProceedings of the 2020 CHI Conference on Human Factors in Computing Systems (CHI ’20). Association for Computing Machinery, New York, NY, USA, 1–15. doi:10.1145/3313831.3376590

work page doi:10.1145/3313831.3376590 2020
[44]

2006.End User Development

Henry Lieberman, Fabio Paternò, and Volker Wulf. 2006.End User Development. Springer Science & Business Media

work page 2006
[45]

Sean McDirmid. 2007. Living It up with a Live Programming Language.SIGPLAN Not.42, 10 (Oct. 2007), 623–638. doi:10.1145/1297105.1297073

work page doi:10.1145/1297105.1297073 2007
[46]

Annemarie Mol. 1999. Ontological Politics. A Word and Some Questions.The Sociological Review47, 1_suppl (May 1999), 74–89. doi:10.1111/j.1467-954X.1999. tb03483.x

work page doi:10.1111/j.1467-954x.1999 1999
[47]

Bonnie A. Nardi. 1993.A Small Matter of Programming: Perspectives on End User Computing. MIT Press

work page 1993
[48]

Jakob Nielsen. [n. d.]. AI: First New UI Paradigm in 60 Years. https://www.nngroup.com/articles/ai-paradigm/

work page
[49]

2018.Algorithms of Oppression: How Search Engines Reinforce Racism

Safiya Umoja Noble. 2018.Algorithms of Oppression: How Search Engines Reinforce Racism. NYU Press. jstor:j.ctt1pwt9w5 doi:10.2307/j.ctt1pwt9w5

work page doi:10.2307/j.ctt1pwt9w5 2018
[51]

Seymour A. Papert. 2020.Mindstorms: Children, Computers, And Powerful Ideas. Hachette UK

work page 2020
[52]

Dominik Pins, Timo Jakobi, Alexander Boden, Fatemeh Alizadeh, and Volker Wulf. 2021. Alexa, We Need to Talk: A Data Literacy Approach on Voice Assis- tants. InProceedings of the 2021 ACM Designing Interactive Systems Conference (DIS ’21). Association for Computing Machinery, New York, NY, USA, 495–507. doi:10.1145/3461778.3462001

work page doi:10.1145/3461778.3462001 2021
[53]

Fischer, Stuart Reeves, and Sarah Sharples

Martin Porcheron, Joel E. Fischer, Stuart Reeves, and Sarah Sharples. 2018. Voice Interfaces in Everyday Life. InProceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI ’18). Association for Computing Machinery, New York, NY, USA, 1–12. doi:10.1145/3173574.3174214

work page doi:10.1145/3173574.3174214 2018
[54]

Forough Poursabzi-Sangdeh, Daniel G Goldstein, Jake M Hofman, Jennifer Wort- man Vaughan, and Hanna Wallach. 2021. Manipulating and Measuring Model Interpretability. InProceedings of the 2021 CHI Conference on Human Factors in Computing Systems (CHI ’21). Association for Computing Machinery, New York, NY, USA, 1–52. doi:10.1145/3411764.3445315

work page doi:10.1145/3411764.3445315 2021
[55]

Stuart Reeves, Martin Porcheron, and Joel Fischer. 2018. ’This Is Not What We Wanted’: Designing for Conversation with Voice Interfaces.interactions26, 1 (Dec. 2018), 46–51. doi:10.1145/3296699

work page doi:10.1145/3296699 2018
[56]

Mattias Rost. 2025. Reclaiming the Computer through LLM-Mediated Computing. ACM Interactions32, 5 (Aug. 2025), 26–31. doi:10.1145/3747585

work page doi:10.1145/3747585 2025
[57]

Harvey Sacks, Emanuel Schegloff, and Gail Jefferson. 1974. A Simple Systematic for the Organisation of Turn Taking in Conversation.Language50 (Dec. 1974), 696–735. doi:10.2307/412243

work page doi:10.2307/412243 1974
[58]

Antti Salovaara, Sacha Helfenstein, and Antti Oulasvirta. 2011. Everyday Ap- propriations of Information Technology: A Study of Creative Uses of Digital Cameras.Journal of the American Society for Information Science and Technology 62, 12 (2011), 2347–2363. doi:10.1002/asi.21643

work page doi:10.1002/asi.21643 2011
[59]

Antti Salovaara and Sakari Tamminen. 2009. Acceptance or Appropriation? A Design-Oriented Critique of Technology Acceptance Models. InFuture Interaction Design II, Hannakaisa Isomäki and Pertti Saariluoma (Eds.). Springer, London, 157–173. doi:10.1007/978-1-84800-385-9_8

work page doi:10.1007/978-1-84800-385-9_8 2009
[60]

Emanuel Schegloff, Gail Jefferson, and Harvey Sacks. 1977. The Preference for Self-Correction in the Organization of Repair in Conversation.Language53 (June 1977), 361–382. doi:10.2307/413107

work page doi:10.2307/413107 1977
[61]

Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language Models Can Teach Themselves to Use Tools. arXiv:2302.04761 [cs] doi:10.48550/arXiv.2302.04761

work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2302.04761 2023
[62]

Donald A. Schon. 1992. Designing as Reflective Conversation with the Materials of a Design Situation.Research in Engineering Design3, 3 (Sept. 1992), 131–147. doi:10.1007/BF01580516

work page doi:10.1007/bf01580516 1992
[63]

Donald A. Schön. 2017.The Reflective Practitioner: How Professionals Think in Action. Routledge, London. doi:10.4324/9781315237473

work page doi:10.4324/9781315237473 2017
[64]

Phoebe Sengers, Kirsten Boehner, Shay David, and Joseph ’Jofish’ Kaye. 2005. Reflective Design. InProceedings of the 4th Decennial Conference on Critical Computing: Between Sense and Sensibility (CC ’05). Association for Computing Machinery, New York, NY, USA, 49–58. doi:10.1145/1094562.1094569

work page doi:10.1145/1094562.1094569 2005
[65]

Ben Shneiderman. 1983. Direct Manipulation: A Step Beyond Programming Languages.Computer16, 8 (Aug. 1983), 57–69. doi:10.1109/MC.1983.1654471

work page doi:10.1109/mc.1983.1654471 1983
[66]

2022.Human-Centered AI

Ben Shneiderman. 2022.Human-Centered AI. Oxford University Press, Oxford, New York

work page 2022
[67]

1998.Harvey Sacks: Social Science and Conversation Analysis

David Silverman. 1998.Harvey Sacks: Social Science and Conversation Analysis. Oxford University

work page 1998
[68]

1975.Pygmalion: A Creative Programming Environment

David Canfield Smith. 1975.Pygmalion: A Creative Programming Environment. Stanford University

work page 1975
[69]

2007.Human-Machine Reconfigurations: Plans and Situ- ated Actions(2 ed.)

Lucy Suchman. 2007.Human-Machine Reconfigurations: Plans and Situ- ated Actions(2 ed.). Cambridge University Press, Cambridge. doi:10.1017/ CBO9780511808418

work page 2007
[70]

2005.What Things Do: Philosophical Reflections on Technology, Agency, and Design

Peter-Paul Verbeek. 2005.What Things Do: Philosophical Reflections on Technology, Agency, and Design. Penn State University Press

work page 2005
[71]

Bret Victor. 2006. Magic Ink: Information Software and the Graphical Interface. http://worrydream.com/MagicInk/. Accessed 2025-09-06

work page 2006
[72]

Bret Victor. 2012. Learnable Programming. http://worrydream.com/ LearnableProgramming/. Accessed 2025-09-06

work page 2012
[73]

John von Neumann. 1982. First Draft of a Report on the EDVAC. InThe Ori- gins of Digital Computers: Selected Papers, Brian Randell (Ed.). Springer, Berlin, Heidelberg, 383–392. doi:10.1007/978-3-642-61812-3_30

work page doi:10.1007/978-3-642-61812-3_30 1982
[74]

Weisz, Jessica He, Michael Muller, Gabriela Hoefer, Rachel Miles, and Werner Geyer

Justin D. Weisz, Jessica He, Michael Muller, Gabriela Hoefer, Rachel Miles, and Werner Geyer. 2024. Design Principles for Generative AI Applications. InPro- ceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI ’24). Association for Computing Machinery, New York, NY, USA, 1–22. doi:10.1145/3613904.3642466

work page doi:10.1145/3613904.3642466 2024
[75]

Matt Welsh. 2023. The End of Programming.Commun. ACM66, 1 (Jan. 2023), 34–35. doi:10.1145/3570220

work page doi:10.1145/3570220 2023
[76]

Yi Wen and Meng Xia. 2025. Promoting Real-Time Reflection in Synchronous Communication with Generative AI. arXiv:2504.15647 [cs] doi:10.48550/arXiv. 2504.15647

work page internal anchor Pith review doi:10.48550/arxiv 2025
[77]

1986.Understanding Computers and Cog- nition: A New Foundation for Design

Terry Winograd and Fernando Flores. 1986.Understanding Computers and Cog- nition: A New Foundation for Design. Ablex Publishing Corporation

work page 1986