IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2301.07543.html
   My bibliography  Save this paper

Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?

Author

Listed:
  • John J. Horton

Abstract

Newly-developed large language models (LLM) -- because of how they are trained and designed -- are implicit computational models of humans -- a homo silicus. These models can be used the same way economists use homo economicus: they can be given endowments, information, preferences, and so on and then their behavior can be explored in scenarios via simulation. I demonstrate this approach using OpenAI's GPT3 with experiments derived from Charness and Rabin (2002), Kahneman, Knetsch and Thaler (1986) and Samuelson and Zeckhauser (1988). The findings are qualitatively similar to the original results, but it is also trivially easy to try variations that offer fresh insights. Departing from the traditional laboratory paradigm, I also create a hiring scenario where an employer faces applicants that differ in experience and wage ask and then analyze how a minimum wage affects realized wages and the extent of labor-labor substitution.

Suggested Citation

  • John J. Horton, 2023. "Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?," Papers 2301.07543, arXiv.org.
  • Handle: RePEc:arx:papers:2301.07543
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2301.07543
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Donald Mackenzie & Fabian Muniesa & Lucia Siu, 2007. "Do Economists Make Markets? On the Performativity of Economics," Post-Print halshs-00149145, HAL.
    2. John Horton & David Rand & Richard Zeckhauser, 2011. "The online laboratory: conducting experiments in a real labor market," Experimental Economics, Springer;Economic Science Association, vol. 14(3), pages 399-425, September.
    3. Judd B. Kessler & Corinne Low & Colin D. Sullivan, 2019. "Incentivized Resume Rating: Eliciting Employer Preferences without Deception," American Economic Review, American Economic Association, vol. 109(11), pages 3713-3744, November.
    4. Lucas, Robert E, Jr, 1980. "Methods and Problems in Business Cycle Theory," Journal of Money, Credit and Banking, Blackwell Publishing, vol. 12(4), pages 696-715, November.
    5. Herbert A. Simon, 1996. "The Sciences of the Artificial, 3rd Edition," MIT Press Books, The MIT Press, edition 1, volume 1, number 0262691914, December.
    6. Kahneman, Daniel & Knetsch, Jack L & Thaler, Richard, 1986. "Fairness as a Constraint on Profit Seeking: Entitlements in the Market," American Economic Review, American Economic Association, vol. 76(4), pages 728-741, September.
    7. John A. List, 2011. "Does Market Experience Eliminate Market Anomalies? The Case of Exogenous Market Experience," American Economic Review, American Economic Association, vol. 101(3), pages 313-317, May.
    8. Gary Charness & Matthew Rabin, 2002. "Understanding Social Preferences with Simple Tests," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 117(3), pages 817-869.
    9. Donald MacKenzie & Fabian Muniesa & Lucia Siu, 2007. "Introduction to Do Economists Make Markets? On the Performativity of Economics," Introductory Chapters, in: Donald MacKenzie & Fabian Muniesa & Lucia Siu (ed.),Do Economists Make Markets? On the Performativity of Economics, Princeton University Press.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Chen, Daniel L. & Horton, John J., 2016. "Are Online Labor Markets Spot Markets for Tasks?: A Field Experiment on the Behavioral Response to Wage Cuts," IAST Working Papers 16-37, Institute for Advanced Study in Toulouse (IAST).
    2. Daniel L. Chen & John J. Horton, 2016. "Research Note—Are Online Labor Markets Spot Markets for Tasks? A Field Experiment on the Behavioral Response to Wage Cuts," Information Systems Research, INFORMS, vol. 27(2), pages 403-423, June.
    3. Mourelatos, Evangelos, 2021. "Personality and Ethics on Online Labor Markets: How mood influences ethical perceptions," EconStor Preprints 244735, ZBW - Leibniz Information Centre for Economics.
    4. Lilian Muchimba & Alexis Stenfors, 2021. "Beyond LIBOR: Money Markets and the Illusion of Representativeness," Journal of Economic Issues, Taylor & Francis Journals, vol. 55(2), pages 565-573, April.
    5. Christoph Engel & Michael Kurschilgen, 2011. "Fairness Ex Ante and Ex Post: Experimentally Testing Ex Post Judicial Intervention into Blockbuster Deals," Journal of Empirical Legal Studies, John Wiley & Sons, vol. 8(4), pages 682-708, December.
    6. Antonides, Gerrit & Kroft, Maaike, 2005. "Fairness judgments in household decision making," Journal of Economic Psychology, Elsevier, vol. 26(6), pages 902-913, December.
    7. Leon Wansleben, 2013. "Dreaming with BRICs," Journal of Cultural Economy, Taylor & Francis Journals, vol. 6(4), pages 453-471, November.
    8. Loconto, Allison & Rajão, Raoni, 2020. "Governing by models: Exploring the technopolitics of the (in)visilibities of land," Land Use Policy, Elsevier, vol. 96(C).
    9. Aleksandra Kuzior & Aleksy Kwilinski & Ihor Hroznyi, 2021. "The Factorial-Reflexive Approach to Diagnosing the Executors’ and Contractors’ Attitude to Achieving the Objectives by Energy Supplying Companies," Energies, MDPI, vol. 14(9), pages 1-16, April.
    10. Dawn Thilmany & Lilian Brislen & Hailey Edmondson & Mackenzie Gill & Becca B. R. Jablonski & Jairus Rossi & Tim Woods & Samantha Schaffstall, 2021. "Novel methods for an interesting time: Exploring U.S. local food systems’ impacts and initiatives to respond to COVID," Australian Journal of Agricultural and Resource Economics, Australian Agricultural and Resource Economics Society, vol. 65(4), pages 848-877, October.
    11. Andreas Leibbrandt, 2016. "Behavioral Constraints on Pricing: Experimental Evidence on Price Discrimination and Customer Antagonism," CESifo Working Paper Series 6214, CESifo.
    12. François-Xavier de Vaujany & Sabine Carton & Carine Dominguez-Perry & Emmanuelle Vaast, 2012. "Performativity and Information Technologies: An inter-organizational perspective," Post-Print halshs-00851315, HAL.
    13. Rezaei, Sarah & Rosenkranz, Stephanie & Weitzel, Utz & Westbrock, Bastian, 2024. "Social preferences on networks," Journal of Public Economics, Elsevier, vol. 234(C).
    14. Franck Cochoy & Martin Giraudeau & Liz McFall, 2010. "Performativity, Economics And Politics," Journal of Cultural Economy, Taylor & Francis Journals, vol. 3(2), pages 139-146, July.
    15. Heidi Østbø Haugen, 2018. "The unmaking of a commodity: Intermediation and the entanglement of power cables in Nigeria," Environment and Planning A, , vol. 50(6), pages 1295-1313, September.
    16. Christian Koch, 2021. "Can reference points explain wage rigidity? Experimental evidence," Journal for Labour Market Research, Springer;Institute for Employment Research/ Institut für Arbeitsmarkt- und Berufsforschung (IAB), vol. 55(1), pages 1-17, December.
    17. Shuchen Ni & Chun Feng & Handan Gou, 2023. "Nash-Bargaining Fairness Concerns under Push and Pull Supply Chains," Mathematics, MDPI, vol. 11(23), pages 1-20, November.
    18. Hernán Bejarano & Brice Corgnet & Joaquín Gómez-Miñambres, 2019. "Labor Contracts, Gift-Exchange and Reference Wages: Your Gift Need Not Be Mine!," Working Papers 19-26, Chapman University, Economic Science Institute.
    19. Bogliacino, Francesco & Grimalda, Gianluca & Pipke, David, 2021. "Kind or contented? An investigation of the gift exchange hypothesis in a natural field experiment in Colombia," OSF Preprints xmjaq, Center for Open Science.
    20. Benjamin Braun, 2016. "From performativity to political economy: index investing, ETFs and asset manager capitalism," New Political Economy, Taylor & Francis Journals, vol. 21(3), pages 257-273, May.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2301.07543. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.