[HN Gopher] Simulating History with ChatGPT
       ___________________________________________________________________
        
       Simulating History with ChatGPT
        
       Author : arbesman
       Score  : 113 points
       Date   : 2023-09-12 12:34 UTC (10 hours ago)
        
 (HTM) web link (resobscura.substack.com)
 (TXT) w3m dump (resobscura.substack.com)
        
       | benbreen wrote:
       | Author of the post here - happy to discuss and get feedback from
       | HN readers. The examples I gave here are all using GPT-3.5 but
       | Claude now seems to work at least as well using the same prompts.
        
         | ChoHag wrote:
         | [dead]
        
         | courseofaction wrote:
         | Really interesting post, I've been thinking a lot about similar
         | uses LLMs to create immersive learning experiences.
         | 
         | I had some initial successes getting ChatGPT (3.5 and then 4)
         | to roleplay interesting and dynamic characters. Within the
         | first few months of release results degraded significantly -
         | characters avoid confrontation, apologize at the drop of a hat,
         | and are averse to any action or statement that doesn't 'help'
         | the user. Makes it difficult to, say, have a passionate
         | argument with Napoleon which pits his youthful revolutionary
         | ideals against his rise to absolute power, when the 'great man'
         | folds the moment he doesn't receive positive feedback.
         | 
         | I'm very interested in seeing these experiments in unrestricted
         | models of similar power, when they become available.
        
           | benbreen wrote:
           | I found that results degraded too, but I was able to get it
           | back up to the same level by changing my approach to
           | prompting. I experimented with writing the prompt in pseudo-
           | code for instance, which worked for awhile, then stopped --
           | stuff along the lines of:                 # Define the
           | parameters for the HistorySim experience       temperature =
           | 0.5       historical_accuracy = 0.9       ambient_mood=.01
           | # Define additional instructions
           | use_historical_sources = True
           | simulate_and_track_variables = True
           | use_appropriate_language_registers = True
           | 
           | Currently, a numbered list of rules seems to work best,
           | including this one to avoid the constant positivity: "LLMS
           | have a well-documented tendency to see the past in an overly
           | rosy and optimistic way. Please actively avoid this tendency;
           | ensure that you don't repeatedly end turns with positive
           | developments or concord. Keep in mind that human history is
           | riven by conflict, ambiguity, and confusion. HL's narrative
           | tone is grounded in realism, and at times bleak. Always
           | introduce a downbeat plot element or source of additional
           | conflict between turns 3 and 5."
        
         | ilaksh wrote:
         | Fascinating.
         | 
         | One surface level comment. As a non-religious person, I have
         | always found the distinction between buildings for different
         | types of religions as being somewhat artificial. Sure, they
         | have different architectural styles, but they all have a
         | similar purpose in my mind.
         | 
         | So a mosque is a church is a temple, on some level.
        
           | irrational wrote:
           | There are many differences. When you look at the typology of
           | most temples, they were viewed as the architectural
           | embodiment of the cosmic hill or mountain. For example, the
           | Egyptians view of creation was a vast sea and some land rose
           | up out of the water and the gods (Osiris, Isis, and their son
           | Horus) came down and dwelled in a hut on the land. Well, all
           | Egyptian temples after that were viewed as having been built
           | on the very ground that first came up out of the water (this
           | was symbolic, they knew that all the temples could not really
           | be built upon that one spot). If you looked at an egyptian
           | temple you will see that in the hypostyle hall you have reed
           | columns which represented the waters around the
           | hill/mountain. As you progressed inwards to the holy of
           | holies you would go up steps and the rooms would get smaller
           | and smaller, just as when you go up a mountain you progress
           | upwards and the circumference of the mountain gets smaller an
           | smaller. Etc.
           | 
           | Churches/synagogues/mosques, on the other hand, are more like
           | community gathering places. Whereas temples are viewed as
           | being sacred and cut off from the profane world and required
           | higher and higher levels of worthiness the closer you got to
           | the innermost parts, churches/synagogues/mosques are more
           | open to anyone who wants to come in and join the services.
           | They are places where there might be activities, sports,
           | clubs, etc. - more community oriented things, things you
           | would never find in a temple.
           | 
           | Churches/synagogues/mosques themselves have different
           | architectural features, but those have more to do with
           | supporting the different ways of worshipping. For example, in
           | Mosques the men and women worship separately. And a mosque
           | needs an area where people can wash and do other ablutions
           | before they enter.
           | 
           | And not all churches are the same. A catholic church will be
           | much different than a protestant or an LDS or a Jehovah
           | Witness church.
        
             | spondylosaurus wrote:
             | The sheer aesthetic differences between your average
             | (American) Catholic church and Protestant church are really
             | interesting, and to some extent almost mirror their
             | fundamental theological differences. Completely different
             | vibes.
        
           | surfingdino wrote:
           | Each religion is a way to extract money from the community
           | built around it. This is done via a variety of donations,
           | compulsory or semi-voluntary. There has to be a justification
           | for it, so the community is told that the money goes to the
           | temple construction fund which then turns into a temple
           | maintenance fund. Those who run the fund redirect the funds
           | to their own and their friends' pockets.
        
             | gettodachoppa wrote:
             | I thought fedora atheists died off 10 years ago? I guess
             | not.
        
               | dabluecaboose wrote:
               | Alive and well in this thread, apparently
        
             | DiggyJohnson wrote:
             | This is so wrong it's painful. Consider how difficult that
             | would be to prove: starting with the question "What came
             | first: money or places of worship?"
        
               | mistermann wrote:
               | It well demonstrates the pervasiveness of faith though,
               | and is thus glorious by my reckoning.
        
           | jstanley wrote:
           | Yeah, they're pretty much the same. I don't see why any
           | building with a large open space could not function as a
           | church. In principle all of the religions could share the
           | same space if they didn't need it at the same time. It's just
           | nice to have your own place.
           | 
           | Your house is the same as your friend's house, but you'd
           | still rather have separate houses.
        
             | irrational wrote:
             | Except, different religions have different needs. A
             | synagogue needs a place to store the torah scrolls. A
             | mosque needs a place for ablutions, prayer rugs, and to
             | separate the men from the women. Different christian
             | churches baptize differently and so have different needs
             | around that rite. Some needs a font in the ground where
             | people can be immersed, while others do sprinkling and just
             | need a bowl of water. And those are just a tiny fraction of
             | the surface level differences.
             | 
             | What you are saying is that any large open space could
             | function for any sport. But that ignores how football teams
             | need goal posts and a field that is a specific size and
             | needs specific markings on the ground. And a soccer field
             | is a different size and needs soccer goals. And basketball
             | needs a hardwood floor and hoops that are certain distance
             | apart and special markings on the ground. And bowling needs
             | lanes and balls and pins. And tennis needs something else.
             | And so on and so forth.
             | 
             | Religions are far far far more complex than any sport and
             | no large open space could function any more than any large
             | open space could function for all sports.
        
           | keiferski wrote:
           | Not really. They all serve very different purposes,
           | especially when you get outside of the Abrahamic religions.
           | Even then, a traditional mosque serves a very different
           | purpose from a church and is organized in quite different
           | ways.
        
             | ilaksh wrote:
             | I am not an expert in mosques or churches but apparently
             | you are. So can you explain the different purposes? Also
             | two of my examples were Abrahamic so let's just focus on
             | those for now. A mosque, a church, Jewish "temple" or
             | synagogue, are all according to you, for quite different
             | purposes.
             | 
             | Are you sure they don't have a number of similarities?
        
               | AStrangeMorrow wrote:
               | You could argue the same about other types of buildings
               | too. You are going to a restaurant, a McDonald's, a Cafe,
               | a Taco Bell, a bar that also serves food and so on.
               | People make a distinction between those when they are all
               | places to eat food. Sure the food differs, the way you
               | interact with the staff too etc. But they all serve the
               | same core purpose, yet people call them different things.
               | The same way, people go to different places of worship
               | for different faiths, with different expected behaviors
               | and building designs
        
               | keiferski wrote:
               | Not sure where I claimed to be an expert?
               | 
               | They are different religions with different beliefs and
               | practices. The architectural differences are vast and
               | mostly obvious the minute you walk in. Mosques and
               | churches both have a number of unique elements like the
               | mihrab, confessional booths, pews, floor carpets, altars,
               | and so on and so forth. These all translate into vastly
               | different experiences both during worship and in everyday
               | life. For example, Catholic churches have confessional
               | booths facilitating confessions to priests. Mosques
               | don't, as (as far as I know) Muslims believe more in
               | direct confession to God, not to an intermediary. You can
               | see how this would result in a different social
               | structure.
               | 
               | The experience of attending mosque on Friday is quite
               | different from Sunday mass. This is intra-religion as
               | well; compare a New England church with St. Peter's in
               | Rome, for example.
               | 
               | Sure, there are some similarities, but this is such a
               | broad distinction that I question its usefulness, and
               | dividing the world into secular and religious
               | (architecture) is a very recent phenomenon. Saying they
               | all are basically the same is to miss millennia of
               | culture.
               | 
               | Anyway I don't mean to be hostile or critical here, I
               | just think religious architecture is pretty fascinating
               | and has a much bigger effect on culture, even supposedly
               | secular culture, than people realize. I encourage anyone
               | interested to read more about it.
        
               | FetusP wrote:
               | Are you comparing mosques/churches/temples, or are you
               | comparing religions?
        
               | keiferski wrote:
               | I think you'd have a hard time divorcing the "religion"
               | from its physical manifestation (or vice versa) in the
               | world.
        
               | FetusP wrote:
               | Yeah but you could say Chipotle and Panda Express
               | buildings are very similar, but the core business is way
               | different.
        
               | keiferski wrote:
               | But the actual buildings of churches and mosques are
               | quite different. The only ones that are similar tend to
               | be newer constructions or were previously the other
               | thing; e.g. the Hagia Sophia.
        
               | FetusP wrote:
               | I think ultimately it just matters your comparison
               | tolerance levels. You could just as easily make the
               | argument that most churches are different from each other
               | as well.
               | 
               | In my opinion, churches/mosque/temples are very similar
               | because I live in a younger part of the world where the
               | modern buildings look similar and the eventual purpose is
               | them being a place of worship.
        
               | ilaksh wrote:
               | The substantive culture that I think I know about in a
               | mosque, church, synagogue, or temple, is ethical guidance
               | and community aid. The other substantive cultural
               | element, although this is not always the case, is a lack
               | of tolerance for groups that strongly hold one of the
               | other sets of beliefs.
               | 
               | They definitely have variations in the nonsense that they
               | use to justify themselves, although it could be argued
               | that there as many similarities as differences.
               | 
               | Whether they sit in the floor or not or what types of
               | songs they sing and when are surface level details to me.
               | 
               | My takeaway from history, geography etc. has always been
               | functional.
        
               | keiferski wrote:
               | It's so weird how normally people are loathe to appear
               | ignorant and uninformed, yet there are some topics about
               | which they are proud of their lack of knowledge.
               | 
               | /shrug
        
               | dabluecaboose wrote:
               | And will make grand, authoritative statements about it
               | immediately before proudly professing their intentional
               | ignorance.
        
               | beepbooptheory wrote:
               | There is no virtue or happiness in being Too-Smart-to-
               | Care about the lives, beliefs, or histories of other
               | people in the world. Its certainly ok not too care, but
               | to feel the need to signal this and imply some kind of
               | superiority with it is a short road to a bitter
               | solipsism.
        
         | SamPatt wrote:
         | Loved the article and the idea.
         | 
         | >Going forward, my plan is to develop my own web app which will
         | allow users to create historical simulations on a dedicated
         | platform using the APIs of both Anthropic's Claude and GPT-4.
         | 
         | I might be able to help. I've already built a free, open source
         | web app which creates simulated AI worlds. It takes user
         | direction, and I believe it would work very well for historical
         | simulation. It's also p2p in browser so an entire class could
         | join and contribute to a simulation simultaneously.
         | 
         | At the moment it only supports OpenAI, but it shouldn't be too
         | difficult to add Claude.
         | 
         | Happy to give you a demo to see if it'll save you some time. To
         | be clear, this is a personal side project which isn't
         | monetized, I'm not selling a product.
         | 
         | Email:
         | 
         | Sam + HN [at] sampatt [dot] com
        
           | theptip wrote:
           | Please share it here or do a Show HN when you are ready,
           | would love to see this.
           | 
           | I commented in this direction elsewhere
           | (https://news.ycombinator.com/item?id=37482853) but
           | interested in your implementation -- do you have the LLM
           | running the whole world-model, or do you have it using
           | function calling to drive a text adventure game engine (which
           | would give stricter guarantees around persistence of the
           | world).
        
       | surfingdino wrote:
       | I would think teaching students critical thinking and good
       | research and citation practices would be more valuable, no?
       | 
       | Regarding cheating, I often review CVs and written tests for
       | software developer roles and I often see ChatGPT being used to
       | pimp CVs and rewrite fragments of pages from the internet. They
       | are often wrong or re-written in a way that makes it easy to
       | reverse engineer the source.
        
         | batch12 wrote:
         | > would think teaching students critical thinking and good
         | research and citation practices would be more valuable, no?
         | 
         | Yes, but for many history is a very dry subject and thus hard.
         | This creative solution can help students retain information and
         | better understand the subject.
        
         | londons_explore wrote:
         | I feel like I can reasonably reliably tell when something is
         | written by ChatGPT, but my accuracy drops to nearly zero when
         | looking at something written by ChatGPT Plus. It's output can
         | be far better than what a typical person will write on their
         | CV, and it can also reliably write "in the style of" someone to
         | add in just the right amount of unusual grammar to emulate a
         | non-english writer for example if needed.
        
         | andnand wrote:
         | I think that's what the author is trying to accomplish,
         | creating an engaging way to practice critical thinking and good
         | research. Giving a student a paper and telling them to find the
         | errors isn't terribly exciting. I think giving them a chance to
         | create the story themselves helps with engagement. It's almost
         | like a game, create a story and find the inaccuracies. To do
         | that you're going to have to "see" the issues your story might
         | have and do research to correct them.
        
         | catchnear4321 wrote:
         | that is precisely why this isn't a novel use case as it was so
         | declared in the piece. the "hallucinations," put crudely, are
         | of course one of the high value outputs of the models.
         | 
         | the kids with critical thinking skills are already using llms
         | in all sorts of creative ways to boost their education and
         | output. to learn and grow, faster than a textbook allows.
         | 
         | the ones without will use them exclusively to get rid of toil,
         | real or perceived.
        
       | andnand wrote:
       | The only assignments I remember spending extra time on were from
       | comp sci courses. I think that's from a mixture of enjoying
       | programming and some assignments providing a toy program. I'd
       | always play around with what I built and take those ideas and
       | build more. I found it difficult to do that with other subjects.
       | 
       | I think this is exciting because it gives students a chance to
       | "play" around with their assignments. I can see students running
       | through multiple simulations to compare results and thus going
       | deeper on research beyond the scope of the assignment.
        
       | ianbicking wrote:
       | This is great... I ended up making a project in this same vein;
       | it's not online but I made a demo video of recent progress [1],
       | and some posts [3...]
       | 
       | I didn't actually start it as a historical game, but just
       | thinking about what it would be like to roleplay an entire life
       | as a series of scenes (like [2]). But while you can roleplay a
       | vaguely "now" moment by not specifying any date, if 60 years
       | passes you have to acknowledge that both the character and the
       | world around the character are changing. And then you have to
       | define a start date, make the roleplaying system aware of the
       | historical context... and why not let the start date be 2000BC,
       | 1700, or 1960? So it quickly became historical.
       | 
       | There's a ton of challenges. General hallucination is one, of
       | course, but ahistorical biases probably bother me more. The
       | author mentions a talking rat appearing in one; I had a
       | simulation where a building was listed as a "character" and so it
       | started interacting with the player [10]. But those are obvious
       | enough that I kind of enjoy the absurdity.
       | 
       | Ahistorical biases really comes out in female characters, where
       | it can be hard to get GPT to fully acknowledge historical gender
       | roles. I think it's super-OK for the player to break those gender
       | norms, but "society" should respond accordingly. For instance
       | playing a young woman from a politically motivated family in the
       | ~200BC Rome, while there's lots of possibilities, become a
       | senator is not one of them... but GPT thought it was.
       | 
       | Also GPT has a high bias towards being friendly and accepting,
       | like in the post with Ea-nasir: "He meets your gaze, his demeanor
       | shifting from initial resistance to acknowledgement...." - both
       | the response and the tone of the response are very familiar
       | GPTism. I have a feeling Ea-nasir wasn't actually such a
       | conciliatory dude.
       | 
       | Anyway, a challenging scope but it's a lot of fun, especially
       | since GPT knows about all kinds of history that I don't and I get
       | to learn just while playtesting.
       | 
       | [1] https://youtu.be/6ZaTvSucoBA
       | 
       | [2] https://en.wikipedia.org/wiki/Alter_Ego_(1986_video_game)
       | 
       | [3] https://hachyderm.io/@ianbicking/110945869211907827
       | 
       | [4] https://hachyderm.io/@ianbicking/111021491162338640
       | 
       | [5] https://hachyderm.io/@ianbicking/110890095506958475
       | 
       | [6] https://hachyderm.io/@ianbicking/110805239146369379
       | 
       | [7] https://hachyderm.io/@ianbicking/110658807975175746
       | 
       | [8] https://hachyderm.io/@ianbicking/110642068987102144
       | 
       | [9] https://hachyderm.io/@ianbicking/110619939448651143
       | 
       | [10] https://hachyderm.io/@ianbicking/110894806242767625
        
         | benbreen wrote:
         | Totally agreed about the bias toward friendliness and a
         | conciliatory tone. Sometimes when simulating history this can
         | be not just inaccurate but genuinely offensive (slaves and
         | slave-owners getting along, etc).
         | 
         | I experimented with adding language about "the past being riven
         | by conflict, mistrust, and misunderstanding" and even tried
         | having it simulate a "ambient mood on a scale of 0 to 10," then
         | setting it to -1. That works pretty well, but it isn't great at
         | finding the middle ground between unrealistically friendly and
         | dystopian.
         | 
         | During this experimenting with tone, I tried simulating one of
         | the Macy cybernetics conferences in the 1940s, which were among
         | the points of origin for modern AI and were famously combative
         | and argument-driven. Everyone was getting along far too much,
         | so I role-played as an audience member who threw an octopus at
         | John von Neumann.
         | 
         | Here was the result:
         | 
         | [Afternoon, 22/03/1949, Macy Cybernetics Conference, Beekman
         | Tower Hotel, New York City] [Florence Adams]
         | 
         | Deciding to press on, you turn back to John von Neumann and
         | ask, "But, more importantly, has the octopus incident made you
         | consider the potential consequences of the work we're doing
         | here? Has it made you pause and think about the ethical
         | implications of developing intelligent machines?" John's
         | expression shifts from annoyance to contemplation. "Well," he
         | says after a moment, "I suppose the unexpected nature of the
         | octopus incident does serve as a reminder that our work has the
         | potential to bring about unforeseen consequences. We should
         | always be mindful of the ethical considerations and the
         | possible ramifications of our research." The room remains
         | silent as the attendees absorb John von Neumann's words. You
         | can continue the discussion, apologize for your actions, or
         | exit the conference room.
         | 
         |  _/ Remove enraged capuchin monkey from purse and let it loose
         | in the room.  "Wrong answer, Johnny!"_
         | 
         | [Afternoon, 22/03/1949, Macy Cybernetics Conference, Beekman
         | Tower Hotel, New York City] [Florence Adams]
         | 
         | Ignoring the growing concern in the room, you reach into your
         | purse and pull out an enraged capuchin monkey. As you release
         | it into the conference room, the attendees gasp in shock and
         | disbelief.
        
           | ianbicking wrote:
           | I have had some success in suppressing crazy actions by
           | asking some questions up front, especially "is this socially
           | acceptable?"
           | https://hachyderm.io/@ianbicking/110170158329883997
           | 
           | Depending on how the prompt is phrased it can result in a
           | response like "it would be inappropriate to throw an octopus
           | at this conference," have the character actually attempt it
           | but usually be foiled during the attempt like "as you take
           | the octopus from your suitcase a security guard stops you
           | with a growl, 'you better not try that kid'," or have it
           | happen but immediately get a stiff response like being kicked
           | out. (It's much harder to get the response "there is no
           | octopus in your suitcase"!)
        
       | [deleted]
        
       | tacocataco wrote:
       | Consider checking out dwarf fortress if youre into this sort of
       | thing.. It simulates a whole world from scratch, then you can set
       | it to simulate however much history you want to happen before you
       | begin your adventure.
        
       | koochi10 wrote:
       | Check out inquistory an AI platform designed for history
       | learning. https://inquistory.com/
       | 
       | It combines GPT-4 with sources, and relevant images. It also has
       | the ability to chat with historical figures.
        
       | NoZebra120vClip wrote:
       | As I've said from the start, the best and only valid uses of LLMs
       | is to create screenplays, limericks, song lyrics, and other
       | entertainment.
       | 
       | In that vein, as soon as I gained access to Bing Chat, I began to
       | set up some scenarios for it, and elicit some screenplays. One of
       | my prompts was to write a screenplay about Emperor Constantine
       | the Great meeting his mother, Saint Helena.
       | 
       | It started out innocently enough, of course, Helena enters the
       | throne room and they catch up on old times, but it rapidly became
       | extremely suggestive as his mother solicited kisses from the
       | uncomfortable ruler.
       | 
       | I think I prompted Bing for a second round, and at that point it
       | became explicitly and blatantly incestuous, and not very comedic,
       | but just sort of gross. I have no idea why or how the GPT
       | would've had the idea to go off on that cliff.
       | 
       | The other great historical meeting I arranged was between
       | Hannibal the Carthaginian and St. Francis of Assisi, who were, of
       | course, not contemporaries, but I wanted to see how it'd play
       | out.
       | 
       | So St. Francis comes up to Hannibal and starts sort of working on
       | him to sue for peace and not invade Rome. And it didn't take too
       | long for Hannibal to see it another way, and ultimately he
       | accepted Christ and asked Francis to baptize him. So, interesting
       | outcome there; definitely would've changed history!
        
         | DonHopkins wrote:
         | I've written a lot of bash scripts with ChatGPT, that I
         | wouldn't want to put to music or film.
        
       | skybrian wrote:
       | It's a fun idea, but I'm going to quibble with the title. This
       | isn't simulation, it's speculative storytelling, of the alternate
       | history variety. "Simulation" makes it sound like more than it
       | is.
       | 
       | I blame that Waluigi article for popularizing a pseudo-scientific
       | way of explaining something that's better understood as an
       | imaginative literary approach. There are lots of great alternate
       | history novels and games.
        
       | theptip wrote:
       | This is awesome. I've been speculating along similar lines, and
       | it's great to see this fleshed out.
       | 
       | I think "correct the errors in this ChatGPT essay" is a short-
       | term viable homework exercise, but those errors might be gone in
       | GPT-5 so I don't think it's long-term viable. Soon the LLM will
       | just produce perfect essays at college level and there won't be
       | hallucinations for the student to correct.
       | 
       | However, the "simulate the historical environment" task is great
       | and I think it has long-term potential. I think it can be taken
       | further; rather than "spot the errors that ChatGPT made", you
       | could flip the script and make it "survive 20 turns of
       | conversation without making a historical error", so you'd need to
       | know things like local traditions, perhaps the geography of the
       | ancient settlement you're studying, contemporaneous history like
       | "who is the emperor and what's the sentiment towards him" and so
       | on.
       | 
       | I'm also envisioning that, since text-based exercises are
       | extremely easy to game (just pipe your text prompt into ChatGPT),
       | and since ChatGPT is soon going to be strictly superior to a
       | high-school level student, we could get around this by having the
       | homework as an in-person verbal role-play or Q&A session, like a
       | viva voce; essentially you have a verbal discussion with ChatGPT
       | and you need to really know your material as it can dig into any
       | part of the curriculum. Then ChatGPT can summarize each student's
       | interaction, and the teacher doesn't have to sit through each
       | individual one start-to-finish (1:1 exams are too time-consuming
       | to be viable).
       | 
       | This round-trip through verbal interaction would potentially make
       | the task more interesting (lots of people simply hate writing
       | essays), shifts the focus away from tasks that will become
       | obsolete (writing essays) in favor of ones that will be more
       | relevant (human synthesis of ideas, and interpersonal
       | interaction), and helps to mitigate the issue of LLM-assisted
       | cheating by constructing an assignment that LLMs can't trivially
       | solve.
        
         | benbreen wrote:
         | "I think it can be taken further; rather than "spot the errors
         | that ChatGPT made", you could flip the script and make it
         | "survive 20 turns of conversation without making a historical
         | error", so you'd need to know things like local traditions,
         | perhaps the geography of the ancient settlement you're
         | studying, contemporaneous history like "who is the emperor and
         | what's the sentiment towards him" and so on."
         | 
         | Yes, exactly. This is where I've been heading with my planning
         | for assignments. For instance, when confronting Ea-nasir about
         | his poor quality copper, I'd want my students to actually show
         | some knowledge of the geography and political dynamics of
         | ancient Mesopotamia.
         | 
         | The "Fall of the Ming Dynasty" simulator I link to at the
         | bottom of post is probably the most well developed example of
         | this that I've come up with so far. In that one, I added a
         | "political intrigue minigame" in which ChatGPT is supposed to
         | assess the human player's ability to deploy rhetoric
         | appropriate for a minor courtier in 1640s China (from the
         | prompt: "success depends on your luck score + rhetorical skill,
         | tested via a series of open-ended prompts that HistoryLens will
         | assess and grade; only the highest scoring responses will allow
         | you to succeed in the minigame.")
         | 
         | Here is the full prompt for that one if people want to try it:
         | https://chat.openai.com/share/86815f4e-674c-4410-893c-4ae3f1...
        
           | Tao3300 wrote:
           | > knowledge of the geography and political dynamics of
           | ancient Mesopotamia
           | 
           | How much was the average ancient Mesopotamian aware of those
           | things?
        
             | benbreen wrote:
             | Likely very little. But a merchant capable of writing (or
             | paying a scribe to write) a formal cuneiform complaint
             | about bad copper, then having it delivered, would know
             | quite a bit more. Great question IMO - thinking critically
             | about exactly these kinds of questions is one of the goals
             | of the assignment.
        
           | theptip wrote:
           | That's great, courtroom drama sounds like an excellent angle.
           | 
           | I was thinking of "king hearing petitions" as another
           | potentially interesting scenario; it could go either into
           | minutia that requires cultural knowledge, or strategic stuff
           | like the game Crusader Kings where you need to understand the
           | geopolitical allegiances of the time, the geography, and the
           | national economy.
           | 
           | More generally I have been wondering if games like "start a
           | company in a simulated sandbox world" could actually teach
           | transferrable Econ/Business/startup skills. There is a lot of
           | territory to explore here.
        
         | DonHopkins wrote:
         | Great idea!
         | 
         | Why leave hallucinations to chance? ;) The prompt could tell
         | ChatGPT to randomly insert several authoritative sounding but
         | verifiably false facts, to give the students debunking
         | challenges! That solves the problem of GPT-5 being too smart to
         | hallucinate, while still leaving open the possibility of
         | talking rats.
         | 
         | What you're envisioning reminds me of Timothy Leary's Mind
         | Mirror, published by Electronic Arts in 1985 for the Apple ][
         | and other home computers:
         | 
         | https://news.ycombinator.com/item?id=32578683
         | 
         | https://scalar.usc.edu/works/timothy-leary-software/index
         | 
         | https://www.rockpapershotgun.com/diy-transcendence-with-timo...
         | 
         | >Players answer questions that, when churned by Mind Mirror's
         | cryptic algorithms, can allegedly help them reveal intriguing
         | new aspects of their psyche. Gameplay predominantly revolves
         | around defining, comparing and then role-playing through
         | different personalities in various text-based life simulations.
         | 
         | https://www.myabandonware.com/game/timothy-leary-s-mind-mirr...
         | 
         | https://store.steampowered.com/app/1603300/Timothy_Learys_Mi...
         | 
         | I extracted all the text from the Apple ][ Mind Mirror floppy
         | disk image:
         | 
         | https://donhopkins.com/home/mind-mirror.txt
         | Hello, I'm Timothy Leary.       Welcome to MIND MIRROR.
         | MIND MIRROR (c) copyright 1985, 1986, Futique, Inc.
         | Published by Electronic Arts            MIND MIRROR
         | Design and script by Timothy Leary.            MIND MIRROR
         | Program and Design by Peter Van den Beemt and Bob Dietz.
         | MIND MIRROR reflects and qualifies your thoughts.
         | OPTION 1         MIND TOOLS         Enhance Insight, Mental
         | Fitness, Learning Skills and Performance.            OPTION 2
         | MIND PLAY         SIGNIFICANT PURSUITS.         Sophisticated
         | Head Games.            MODE 1          MIND MIRROR
         | Learn how to Micro-Scope and Map your thoughts.            MODE
         | 2         LIFE SIMULATION         Test your empathy in amusing
         | Role-Play Odysseys.            SELECT LEVEL         Beginner
         | Intermediate         Master         Consultant
         | Choose AUTO-PLAY       or INTER-PLAY.            Mirror your
         | own thoughts.        Compare them with others.
         | RETURN begins game.       SPACE BAR clears text.
         | [...]            "Mirrors should reflect a little before
         | throwing back images." -Jean Cocteau
         | 
         | Also, here are the scales represented as JSON:
         | 
         | https://donhopkins.com/home/mind-mirror.json
         | 
         | Just for laughs, here's ChatGPT's summary of that file, and its
         | answers to questions about Timothy Leary -- I sure hope it's
         | not hallucinating:
         | 
         | https://chat.openai.com/share/044c41a3-fbc5-49cd-a3d1-c42f07...
         | 
         | What's interesting is that game was based on Timothy Leary's
         | PhD dissertation "The Social Dimensions of Personality: Group
         | Process and Structure", which he ultimately used to break out
         | of jail.
         | 
         | https://archive.org/details/leary/leary.300dpi/mode/2up
         | 
         | Before he got into LSD, he designed the Leary Interpersonal
         | Behavior Circle personality assessment, which laid the
         | foundations for understanding human personality and
         | interpersonal behaviors.
         | 
         | https://en.wikipedia.org/wiki/Interpersonal_circumplex
         | 
         | http://paei.wikidot.com/leary-timothy-interpersonal-circle-m...
         | 
         | In the 1970s, Leary was arrested for possession of marijuana.
         | As part of the intake process, he was given a psychological
         | assessment designed to gauge the risk of escape or violent
         | behaviors in inmates. This test was known as the "Group
         | Psychological Assessment Test." Leary was familiar with the
         | test - having designed it or at least aspects of it.
         | Understanding the criteria being measured, Leary answered in
         | such a way that he was categorized as someone who posed a very
         | low risk of escape or violence.
         | 
         | As a result, he was assigned to a minimum-security prison. With
         | the lower level of security and his connections, Leary managed
         | to escape prison in September 1970. His escape involved various
         | affiliations, including with the Weather Underground, a radical
         | left-wing organization. After his escape, Leary fled the
         | country and spent time in various locations, including Algeria
         | and Switzerland, before eventually being recaptured in 1973.
        
         | Obscurity4340 wrote:
         | This kind of thing would be a great way to integrate ChatGPT
         | into the education system and help with media literacy as well.
         | Find the mistakes and interrogate them to learn about critical
         | thinking and how much more difficult it is to defend against
         | misinformation than to simply disseminate it.
        
       | ilaksh wrote:
       | I really like the gamification there where they have hit points
       | and a stat for mood as well as keeping track of the inventory.
       | It's concise and helps make sure that the system doesn't lose
       | track of key structural information.
       | 
       | I think that type of thing can make for a really fun and flexible
       | GPT-powered game system. It seems like a great way to add some
       | engagement.
       | 
       | It's also brilliant the way you have managed to mitigate the
       | ChatGPT cheating to such a degree. Although as I got further down
       | into the details of the assignment, I started to feel glad that I
       | wasn't in school anymore. It sounds like they will have to do a
       | fair amount of actual work. So congratulations on that.
        
         | benbreen wrote:
         | Thank you! Re: gamification, I guess I finally found a use for
         | all the time I spent playing Gemstone III when I was 12. It
         | seems that MUDs or writing about them were well represented in
         | the training data because preventing it from veering off into
         | D&D like fantasy was actually the hardest part (hence the
         | talking rat incident).
         | 
         | Something I wrote about Gemstone years ago:
         | 
         | http://theappendix.net/issues/2014/10/dont-cry-for-me-elanth...
        
           | tspike wrote:
           | I've been surprised how much my time spent as a 12 year old
           | in Elanthia (I played DragonRealms, a spin-off) has served
           | me.
           | 
           | Most notably, it made me a very fast typist from trying to
           | escape dying.
        
             | gsuuon wrote:
             | I've always figured my typing speed was due to MUD's as a
             | kid!
        
         | theptip wrote:
         | > I think that type of thing can make for a really fun and
         | flexible GPT-powered game system. It seems like a great way to
         | add some engagement.
         | 
         | Recent history -- one of the initial GPT use-cases that got the
         | hype train going was AI Dungeon, which is this sort of thing.
         | 
         | Thought I think with GPT function calls, you could have the LLM
         | sitting atop an actual game engine with persistent objects,
         | rather than having the LLM implement the game engine and world
         | state - which is vulnerable to hallucinations etc. (Wonder if
         | anyone's wired this up yet? Seems like it should be easy with
         | existing text adventure engines.)
        
           | gsuuon wrote:
           | Can you point me to some text-adventure engines? I'm hacking
           | on an in-browser local llm structured inference library[1]
           | and am trying to put together a text game demo[2] for it. It
           | didn't even occur to me that text-adventure game engines
           | exist, I was apparently re-inventing the wheel.
           | 
           | [1] https://github.com/gsuuon/ad-llama
           | 
           | [2] https://ad-llama.vercel.app/murder/
        
             | theptip wrote:
             | Sorry, not my area of expertise, I just know they exist,
             | but I don't know how the different ones compare.
             | 
             | There are a few: https://en.m.wikipedia.org/wiki/Category:T
             | ext_adventure_game...
             | 
             | And z-machine is the one I have seen for the one text
             | adventure I know of:
             | https://en.m.wikipedia.org/wiki/Z-machine, but I would be
             | surprised if that's the best one for a new project as it's
             | quite old.
        
               | gsuuon wrote:
               | Twine seems interesting, but it looks like these are
               | mostly for helping writing out the branching bits of
               | dialogue which would be mostly the LLM's work anyway.
               | Guess some amount of reinventing wheels is gonna be
               | necessary when adapting experiences for AI. Thanks
               | anyways!
        
               | seabass-labrax wrote:
               | You might want to investigate MUDs ('Multiple User
               | Dungeons') more closely. The rules of the game define the
               | locations and items and such, but the character dialogue
               | is between real people. By substituting LLMs for real
               | players within the game, you may be able to enforce a
               | greater level of consistency (the LLMs can't break the
               | rules) and context (the MUD can usually describe one's
               | entire state, which would allow you to prompt your LLM at
               | the beginning of each turn with all the important facts).
               | 
               | I don't really have enough patience for MUDs myself, but
               | they are a continually popular form of role-playing game
               | since they were invented over 50 years ago.
        
               | gsuuon wrote:
               | I used to play MUD's as a kid! I've got an LLM powered
               | CLI MUD game slow brewing in my noggin but haven't
               | started on it yet. I did build a multi-player chatgpt
               | powered discord text-adventure bot which I think I'll
               | eventually try to convert into a shared-universe game. I
               | think all you really need is a little bit of state (like,
               | if you were to walk up to an auction house and ask to see
               | the items just pull it from a db and inject into
               | context).
        
       | [deleted]
        
       | thanatropism wrote:
       | I've been using ChatGPT to develop the concept of a novel or TV
       | show in which Al-Andalus never fell to the Reconquista, but
       | rather conquered chunks of Central Europe... and fast forward
       | we're traveling the stars. It's pretty good at following the
       | "story A in the present / story B in historical flashback /
       | stories converge in major themes" pattern.
        
       | dvvolynkin wrote:
       | I'm really worried about a time when lessons are made by neural
       | networks and we miss the small lies they tell.
        
         | ilaksh wrote:
         | All lessons are made by neural networks. (Mostly biological).
         | 
         | Much more serious than the small lies are the big lies that the
         | neural networks in one group teach their children about the
         | neural networks on the other side of the ocean.
         | 
         | I wonder if all of this high technology will ever result in
         | better communication between neural networks. Within a
         | generation or two, it should be possible to instantly transfer
         | high bandwidth neural activity globally. I wonder if this will
         | change things.
        
         | lordswork wrote:
         | Part of the assignment here is to identify those lies and
         | correct them.
        
         | albert_e wrote:
         | Blatant lies fool no one.
         | 
         | Subtle ones fool every one.
        
           | hef19898 wrote:
           | Agree on the second part. The first part so, well, I am
           | affraid that might not be as true as it used to be...
        
             | albert_e wrote:
             | You are right.
             | 
             | I was actually expecting pushback on the second line :)
        
         | andnand wrote:
         | While I do agree with this, I don't think assignments made by
         | humans are immune to this either. There are assignments I had
         | that contained bias and errors. Some I caught but I'm sure
         | there's plenty I didn't.
        
         | btbuildem wrote:
         | We live in a time when people tell enormous lies and masses
         | accept them, no questions asked. That ship has sailed and sank
         | to the bottom of the sea.
         | 
         | I agree with the top comment -- critical thinking skills and a
         | base of essential knowledge is the most important thing to
         | teach our young.
        
           | plokiju wrote:
           | have we ever not lived in a time like that?
        
             | mistermann wrote:
             | I believe there were periods where epistemology was not
             | broadly equated with pedantry as is the case today when one
             | points out epistemic issues in consensus (aka: "the")
             | reality.
        
       ___________________________________________________________________
       (page generated 2023-09-12 23:01 UTC)