Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

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-nāṣir: "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-nāṣir 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



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.


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"!)




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: