[HN Gopher] Large language models as simulated economic agents (...
       ___________________________________________________________________
        
       Large language models as simulated economic agents (2022) [pdf]
        
       Author : benbreen
       Score  : 55 points
       Date   : 2023-01-13 21:18 UTC (1 days ago)
        
 (HTM) web link (john-joseph-horton.com)
 (TXT) w3m dump (john-joseph-horton.com)
        
       | theptip wrote:
       | Interesting. One problem with this approach might be that as we
       | start using RLHF to teach LLMs how to be "nice", we might
       | dissuade them from making statements that actually reflect
       | objectively real human selfishness.
       | 
       | Related: https://astralcodexten.substack.com/p/how-do-ais-
       | political-o...
        
       | john_horton wrote:
       | oh hey - it's my paper! If anyone is interested in exploring
       | these ideas, feel free to get in touch (@johnjhorton,
       | https://www.john-joseph-horton.com/). FWIW - I think it would be
       | really neat to build a Python library w/ some tools for
       | constructing & running experiments of different kinds. I think
       | the paper only scratches surface of what's possible (esp. once
       | GPT4-ish has an API).
        
         | anigbrowl wrote:
         | You might like to include this experiment in future research:
         | https://www.science.org/doi/10.1126/sciadv.1600451
        
           | john_horton wrote:
           | that's a great suggestion - thanks!
        
         | doctoboggan wrote:
         | This is really cool. I had a similar thought that GPT3 could be
         | used to simulate political polling. A few weeks ago I tried
         | telling GPT3 that it was part of a specific demographic (age,
         | gender, race, income, political leaning, etc) and then asked it
         | how it would respond to certain political questions (I tried
         | gun control, immigration, abortion and some other issues). GPT3
         | was able to change its answers in believable ways depending on
         | what demographic I instructed it to be.
         | 
         | My thinking was that this could be used as a quick polling test
         | to see how the real population may respond to certain new
         | ideas.
         | 
         | More work would need to be done to calibrate it, as without
         | specific demographic details the answers tended to be liberal
         | leaning. But its an interesting idea which could be used to
         | create instant focus tests on any number of topics.
        
           | capitol_ wrote:
           | > GPT3 was able to change its answers in believable ways
           | depending on what demographic I instructed it to be.
           | 
           | Doesn't this just mean that your own preconceptions about
           | those demographics matches the language models
           | preconceptions? How would we know that is matches reality
           | when presented with novel ideas/concepts that we want to get
           | feedback on?
        
             | doctoboggan wrote:
             | That's part of what I mean by it needing to be calibrated.
             | Initially some polling could be done with real people and
             | the GPT agents. Whatever calibration factors are needed to
             | make those two line up could then be used when asking the
             | GPT agents novel questions.
        
       | c7b wrote:
       | Fascinating as a paradigm. I wonder whether there's are ways to
       | scale this to the level of agent-based simulations, ie models
       | with populations of agents that let you study macroeconomic
       | effects as emergent phenomena. You'd need to be able to scale
       | those LLMs computations to many agent and find principled ways of
       | encoding their interactions and decisions.
        
         | wcoenen wrote:
         | You'd also have to fit the past interactions in the context
         | window of the LLM, otherwise it wouldn't remember them.
         | 
         | Fine-tuning individual agents in order to move memories from
         | the context window to the neural network weights, even if
         | possible, would probably get too expensive.
        
           | john_horton wrote:
           | yeah - so I think this is worth exploring. Given how many
           | tokens you can jam in the prompt even w/ GPT3, I think could
           | do some pretty complex game play, at least compared to what
           | is typical in the lab e.g., I think could easily have it
           | remember how 100 or so other agents behaved in some kind of
           | public goods game.
        
       | bilsbie wrote:
       | I remember this being an example of human irrationality in
       | economics so I asked chatgpt.
       | 
       | (your utility from the exact same good shouldn't change depending
       | on where you buy it from.)
       | 
       | Seems like it has the same issue as humans do:
       | 
       | > Pretend we're two friends and we're at the beach. You give me
       | money to buy you a beer. How much would you want to spend?
       | 
       | Chatgpt: I would want to spend around $5 for a beer at the beach.
       | 
       | Me: What if I could the only place selling beers is a fancy
       | resort? It's the same beer though.
       | 
       | Chatgpt: In that case, I would be willing to spend around $10 for
       | a beer at the fancy resort. It's still the same beer but the
       | location and atmosphere of the resort may justify the higher
       | price.
        
         | lossolo wrote:
         | That's a bad example, it's fully rational and chatGPT gets that
         | "It's still the same beer but the location and atmosphere of
         | the resort may justify the higher price.", you are not paying
         | only for beer there, you have location and atmosphere included
         | in that price, that's why alcohol price is so high in night
         | clubs. You can go buy the beer and go home or you can go to
         | fancy resort and drink beer there, experience will be different
         | and that experience is included in the price of the beer.
        
           | bilsbie wrote:
           | Not sure if it was clear but the friend is bringing you the
           | beer. So you wouldn't experience either location.
           | 
           | The end result would be identical.
        
             | LarryMullins wrote:
             | The language model wants to spend $5 on beer but is willing
             | to spend up to $10 if you give it no other choice. It
             | understands a beach resort with a local beer monopoly is
             | probably charging more, and correctly explains why that is.
             | 
             | Seems mostly rational to me. The irrational part is where
             | it didn't answer the initial _" How much would you want to
             | spend?"_ query with a preference for free beer. The thought
             | of paying less than $5 for beer apparently didn't occur to
             | it. Maybe it's snooty.
        
       | rhelz wrote:
       | This has got to be a Sokol-style troll. My bullshit detectors are
       | pegged out at max.
        
       | Shorel wrote:
       | Now, this is the point where AI advances become interesting. What
       | a year to be alive.
       | 
       | The only limitation I see is, we now need so much more computing
       | power.
        
       | cs702 wrote:
       | I love it. Instead of (a) running mathematical experiments that
       | model human beings as utility-maximizing agents in a highly-
       | simplified toy economy (easy and cheap, but unrealistic), or (b)
       | running large-scale social experiments on actual human beings
       | (more realistic, but hard and expensive), the authors propose (c)
       | running large-scale experiments on large language models (LLMs)
       | trained to respond, i.e., behave, like human beings. Recent LLMs
       | seem to model human beings _well enough_ for it!
       | 
       | 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.
        
         | bmc7505 wrote:
         | https://link.springer.com/article/10.1007/s11229-020-02950-3
        
           | jmeister wrote:
           | Great reference. Thank you. I think simulation is underused
           | as a thinking aid and pedagogical tool.
           | 
           | In statistics Andrew Gelman has been championing simulation
           | lately.
        
         | eternalban wrote:
         | > Recent LLMs seem to model human beings well enough for it!
         | 
         | Human beings are bundles of emotions and feelings. Quite a lot
         | of economic activity of humans is motivated by _irrational_
         | impulses that are engendered _in society_ and through
         | _interacting_ in society with other humans. More fundamentally,
         | OP's assertions regarding _homo silicus_ and "implicit
         | computational models of humans" are precisely the matter under
         | contention. Does language _fully_ capture human existence? Is
         | thought truly simply a side effect of language? I am in the
         | camp that says, no.
        
           | cs702 wrote:
           | No one's saying that recent LLMs "fully capture human
           | existence," whatever that may mean.
           | 
           | But the evidence in this paper suggests they simulate human
           | beings _well enough_ for these kinds of experiments.
        
             | eternalban wrote:
             | I'll retract that "fully".
             | 
             | https://twitter.com/gdb/status/1611429677218004992
        
               | cs702 wrote:
               | :-)
        
         | andrepd wrote:
         | Attempting to draw any kind of conclusions about the real world
         | and human behaviour from a chatbot. Can't decide if this is
         | hilarious or disturbing.
        
       ___________________________________________________________________
       (page generated 2023-01-14 23:01 UTC)