What Happens When You Put 25 ChatGPT-Backed Agents Into an RPG Town? (arstechnica.com) 52
"A group of researchers at Stanford University and Google have created a miniature RPG-style virtual world similar to The Sims," writes Ars Technica, "where 25 characters, controlled by ChatGPT and custom code, live out their lives independently with a high degree of realistic behavior."
"Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day," write the researchers in their paper... To pull this off, the researchers relied heavily on a large language model for social interaction, specifically the ChatGPT API. In addition, they created an architecture that simulates minds with memories and experiences, then let the agents loose in the world to interact.... To study the group of AI agents, the researchers set up a virtual town called "Smallville," which includes houses, a cafe, a park, and a grocery store.... Interestingly, when the characters in the sandbox world encounter each other, they often speak to each other using natural language provided by ChatGPT. In this way, they exchange information and form memories about their daily lives.
When the researchers combined these basic ingredients together and ran the simulation, interesting things began to happen. In the paper, the researchers list three emergent behaviors resulting from the simulation. None of these were pre-programmed but rather resulted from the interactions between the agents. These included "information diffusion" (agents telling each other information and having it spread socially among the town), "relationship memory" (memory of past interactions between agents and mentioning those earlier events later), and "coordination" (planning and attending a Valentine's Day party together with other agents).... "Starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party," the researchers write, "the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time...."
To get a look at Smallville, the researchers have posted an interactive demo online through a special website, but it's a "pre-computed replay of a simulation" described in the paper and not a real-time simulation. Still, it gives a good illustration of the richness of social interactions that can emerge from an apparently simple virtual world running in a computer sandbox.
Interstingly, the researchers hired human evaluators to gauge how well the AI agents produced believable responses — and discovered they were more believable than when supplied their own responses.
Thanks to long-time Slashdot reader Baron_Yam for sharing the article.
When the researchers combined these basic ingredients together and ran the simulation, interesting things began to happen. In the paper, the researchers list three emergent behaviors resulting from the simulation. None of these were pre-programmed but rather resulted from the interactions between the agents. These included "information diffusion" (agents telling each other information and having it spread socially among the town), "relationship memory" (memory of past interactions between agents and mentioning those earlier events later), and "coordination" (planning and attending a Valentine's Day party together with other agents).... "Starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party," the researchers write, "the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time...."
To get a look at Smallville, the researchers have posted an interactive demo online through a special website, but it's a "pre-computed replay of a simulation" described in the paper and not a real-time simulation. Still, it gives a good illustration of the richness of social interactions that can emerge from an apparently simple virtual world running in a computer sandbox.
Interstingly, the researchers hired human evaluators to gauge how well the AI agents produced believable responses — and discovered they were more believable than when supplied their own responses.
Thanks to long-time Slashdot reader Baron_Yam for sharing the article.
Re:What happens is... (Score:5, Insightful)
Or you could use it to generate a massive pre-computed possibility tree and then extract a much less CPU-intensive decision tree from it, and use that to give your RPG a much more lively town than the standard 'everyone stands around offering you 1GP to kill the rats in their basement'.
Re: (Score:2)
Re: (Score:2)
curious.
could each a i be housed in smart phone
Re: (Score:2)
Re: (Score:3, Funny)
Look at it this way: that's 25 fewer Microsoft-controlled bots available to take away someone's job soon.
Re: (Score:2)
well, at least this is fun and interesting. governments spend much more money than that buying weapons to kill people.
however, the findings are not really that surprising, i don't see much more "spontaneous interaction and dissemination of information" than i would expect a few of simple scripted bots would produce by randomly bumping into each other. which is what they basically did, they scripted a bunch of gpts together. all of them have their own list of "events" which is the only stuff they have to tal
Re: (Score:2)
You burn a lot of energy, through cpu cycles, offering no value. Stop it, its just contributing to global warming.
I actually find this to be a fairly interesting experiment. A few years ago chatbot's interacting produced gibberish [slashdot.org].
Now, they're accomplishing some higher level coordination.
If nothing else an interesting experiment is worth the cycles.
But I fear this might be more practical than people realize.
I'm certain Russia is already planning a fleet of LLM bots to rile up extremists in foreign countries. What this experiment shows is just how far those bots may go. The next Jan 6th might very well be started and se
Re: (Score:3)
You burn a lot of energy, through cpu cycles, offering no value. Stop it, its just contributing to global warming.
I actually find this to be a fairly interesting experiment. A few years ago chatbot's interacting produced gibberish [slashdot.org].
Now, they're accomplishing some higher level coordination.
I can hardly wait until they give the bots crypto wallets and some bits to get started. You ain't seen CPU money burning until you've seen the AIs get into cryptocurrency!
3d printed web3 blockchain metaverse AIs are coming for you sooner than you think.
Re: (Score:3)
Whilst I shouldn't be trusting any internet post these days for exactly this reason, I do expect something like this to come from Putin. But I also expect the other countries to join in and also the corporate astroturfing will go up a notch.
We're going to need AI to filter out other AI generated posts and it likely won't be able too, now that is going to burn a lot of CPU cycles.
We mostly all hate the idea of needing strong ID to post on s
Re: (Score:1)
Who needs chat bots when you have the media repeating your lies for you?
Re: (Score:1)
Yes. You're right, of course. Fox News/OAN/Breitbart ARE utter trash. Well called.
Re: (Score:1)
You're on a PC posting this. Or a phone. Electronic devices that were manufactured using rare metals and chemicals for the battery
Every site you connect to is probably running on a server - y'know, like a big computer?
We've been doing this for decades and computers are getting less wasteful - why are we pretending language models are somehow an exception to that?
Should we stop
Re: (Score:1)
Re: What happens is... (Score:2)
In other words (Score:2, Funny)
You Get A Shitty RPG (Score:2)
Is this a trick question?
Re: (Score:2)
This being a trick question would indicate the one asking it is smart. That is obviously not the case. I think it is just a stupid question bys somebody with no insight into the actual state of Artificial Ignorance.
Supermans (Score:2)
I wonder what happens... (Score:2)
when you give them all guns.
Re: (Score:1)
IIUC, that's not quite what they did (Score:3)
Again, IIUC. I think that the "RPG town" is just a display. I mean they have characters walking into closed stores, and their proposed solution is "We'll post an amendment to the store specification that it's closed then. Not "The character will look at the store and notice that it's closed.". For bathrooms intended for one being occupied by more than one it was "We'll change the name of the place from dorm bathroom to single bathroom".
So it looks to me like the "RPG town" is just a display of the current system state. I think they've got a lot of the causal links backwards. True, there have got to be feedback loops, but the initial state should be a response to sensing the environment, and that's not what they've got.
OTOH, they've got basic navigation in "space", and they've got multi-agent coordination. These are things that a pure ChatGPT doesn't have. (However, I'm not sure about that "navigation in space" as the paper didn't give any details. But the diffusion of information was interesting.)
Simplify! (Score:2)
Re: (Score:2)
Re: (Score:2)
Because gpt was trained on mostly English text. It isn't capable of spawning its own new language onits own.
Even the valentine's party was spawned by outside input from a human. The gpt didn't recognize that valentine's was coming up soon and decide on its own to have a party.
Build a table-top town (Score:2)
With almost real characters and test advertisement strategies on them.
Feckle-Freezer!
What happens (Score:2)
Re: (Score:2)
Yep, pretty much. In this case, the whole is much, much less than the sum of its parts.
I wonder... (Score:2)
Nothing meaningful (Score:1)
Seriously, stop attributing powers to this automaton that it does very much not have. Seek your new "God" elsewhere. Or better, not at all. But that would be sophisticated and insightful, cannot have that, now can we.
Re: (Score:2)
Re: (Score:2)
You get 4chan (Score:2)
Disappointing. (Score:2)
They didn't give any of the NPCs the ability to be stressed. Stress is critical component to the behavior of anything living. I'm just saying, if you don't have any NPCs threatening to quit their job or verbally abusing each other then is it even a simulation?
Re: (Score:2)
Easy to answer (Score:2)
Ever played at the table of a "world building" GM? Someone who creates a painstakingly detailed world where every villager in the town has his or her own meaningful life with his or her own meaningful daily chores who went about their merry business, with the player characters just being yet another bunch of characters in the world?
Where the player characters decide to go ask the miller's wife about something she saw that they need to know to solve the quest they're on, only to be told that she's currently
Re: (Score:1)
Sounds kind of annoying after the initial experience wears off. Ymmv, but I want to level my characters, get the next weapon up, learn the new spell, blast the shit out of the dragon, loot its lair, and see the final victory cut scene for killing the Mighty Wizard Foozle at the end, mission accomplished, job well done, will buy the sequel in 2-3 years and do the same thing all over again with a nicer game engine.
Re: (Score:2)
It would require balance. NPCs programmed with more realistic behavior would help with immersing yourself in the story - but it would still need to be severely constrained by the needs of the plot.
I'm sure someone will figure it out, and you'll appreciate it when they do. It'll win awards.
Re: (Score:2)
NPCs should give the world the appearance to be organic and vibrant, but they should equally bend to the player's needs. If I want to be ignored by some bozo because he got better things to do than to hear me out and help me, I don't have to sit down at the gaming table, I can call my ISP.
Re: (Score:2)
It's even annoying during the initial experience annoying.
Let's assume that we're playing a story-heavy game. With an organic world where the players actually want to experience something and not just get the next +(+1) sword, half the princess and the kingdom... or something like that. Even in such a setting, the players want to be the stars of the show. They don't give a fuck about the miller's son's daily routine (unless it is a plot device that takes them down a dungeon so they can save the day).
If the
Why not embed them in silicone humanoid forms? (Score:1)
Sim City with the need for a human (Score:2)
Seriously, this sounds like an advanced Sim City on auto-pilot; no need for a human.
Oddly enough, this sounds kind of cool. It might make for an interesting 'live' art display, zooming in on characters displaying new behavior to see what they doing. The old "miniature world in a snow globe". Just let them go and see what they do, like a study in social evolution.
Re: (Score:3)
We ourselves are living in someone else's simulation anyway, thisisfine.jpg
Secret of NIMH (Score:1)
Needs a Fast Forward button (Score:2)
The simulation needs a FF button or at least a 2x speed. By 7am I need a 10x speed button.
What if they were scientists and not painters? (Score:2)
Not pre-programmed? (Score:2)
Does anyone else see a contradiction in these statements?
To pull this off, the researchers... created an architecture that simulates minds with memories and experiences...
the researchers list three emergent behaviors resulting from the simulation. None of these were pre-programmed...
These included "relationship memory" (memory of past interactions between agents and mentioning those earlier events later)...
So they added code to "simulate memories and experiences", and then claim it's not pre-programmed when the agents show "memory of past interactions"?
Re: (Score:2)
The memories aren't the spontaneous things, it's what the agents are doing with the memories.
I mean, your computer knows you visited the hub two weeks ago, but it's not casually mentioning that it thought the blonde was pretty hot.
Finally! (Score:1)
This is great news! Finally we've got bots who can do all that tedious game playing for us, freeing up our time to go play outside or read a book or whatever. Yay, progress!