Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Project Sid: Many-agent simulations toward AI civilization

github.com

Post reply on HN
Print view View original

21–30 of 173 posts

Re: Project Sid: Many-agent simulations toward AI civilization

#21

Post by bbor »

NoboruWataya wrote: post #12

This seems very cool - I am sceptical of the supposed benefits for "civilization" but it could at least make for some very interesting sim games. (So maybe it will be good for Civilization moreso than civilization.)

Yeah, I was dissapointed (and thrilled, from a p(doom) perspective) to see it implemented in Minecraft instead of Civilization VI, Humankind, or any of the main Paradox grand strategies (namely Stellaris, Victoria, Crusader Kings, and Europa Universalis). To say the least, the stakes are higher and more realistic than "lets plan a feast" "ok, I'll gather some wood!"

To be fair, they might tackle this in the paper -- this is a preprint of a preprint, somehow...

Re: Project Sid: Many-agent simulations toward AI civilization

#22

Post by grugagag »

airstrike wrote: post #6

I've thought about this a lot. I'm no philosopher or AI researcher, so I'm just spitballing... but if I were to try my hand at it, I think I'd like to start from "principles" and let systems evolve or at least be discoverable over time Principles would be things like self-preservation, food, shelter and procreating, communication and memory through a risk-reward calculation prism. Maybe establishing what is "known" v…

Many of these projects are inch deep into intelligence and miles deep into the current technology. Some things will see tremendous benefits but as far as artificial intelligence we’re not there yet. Im thinking gaming will benefit a lot from these..

Re: Project Sid: Many-agent simulations toward AI civilization

#23

Post by com2kid »

Tiberium wrote: post #13
aleph_minus_one wrote: post #11

Earlier quoted context omitted.

> Honestly I'm really excited about this. I've always dreamed of full blown sandbox games with extremely advanced NPCs (which the current LLMs can already kinda emulate), but on the bigger scale. I don't believe that you want this. Even really good players don't have a chance against super-advanced NPCs (think how chess grandmasters have barely any chance against modern chess programs running on a fast computer). You…

Oh, I should've clarified - I don't want to fight against them, I just want to watch and sometimes interfere to see how the agents react ;) A god game like WorldBox/Galimulator, if you will. Or observer mode in tons of games like almost all Paradox ones.

I'm working on something similar, https://www.generativestorytelling.ai/tinyllmtown/index.html a small town where all NPCs are simulated using a small LLM. They react to everything the hero does, which means no more killing a dragon and having no one even mention it.

Once I release it, I'll have it simulate 4 hours every 2 hours or so of real time, and visitors can vote on what quest the hero undertakes next.

The simulation is simpler, I am aiming to keep everything to a size that can run on a local GPU with a small model.

Right now you can just watch the NPCs try to figure out love triangles, hide their drinking problems, complain about carrots, and celebrate when the hero saves the town yet again.

Re: Project Sid: Many-agent simulations toward AI civilization

#24

Post by jsemrau »

aithrowawaycomm wrote: post #5

Reading the paper, this seems like putting the cart before the horse: the agents individually are not actually capable of playing Minecraft and cannot successfully perform the tasks they've assigned or volunteered for, so in some sense the authors are having dogs wear human clothes and declaring it's a human-like civilization. Further, crucial things are essentially hard-coded: what types of societies are available a…

You are on the right track in my opinion. The key is to encode the interface between the game and the agent so that the agent can make a straightforward choice. For example, by giving the agent the state of a nxn board as the world model, and then a finite set of choices, an agent is capable of playing the game robustly and explaining the decision to the game master. This gives the illusion that the agent reasons. I guess my point is that it's an encoding problem of the world model to break it down into a simple choice.

[1] https://jdsemrau.substack.com/p/evaluating-consciousness-and...

Re: Project Sid: Many-agent simulations toward AI civilization

#25

Post by jsemrau »

isoprophlex wrote: post #3

Now these seem to be truly artificially intelligent agents. Memory, volition, autonomy, something like an OODA loop or whatever you want to call it, and a persistent environment. Very nice concept, and I'm positive the learnings can be applied to more mundane business problems, too. If only I could get management to understand that a bunch of prompts shitting into eachother isn't "cutting-edge agentic AI"... But then…

>If only I could get management to understand that a bunch of prompts shitting into eachother isn't "cutting-edge agentic AI"...

It should never be this way. Even with narrow AI, there needs to be a governance framework that helps measure the output and capture potential risks (hallucinations, wrong data / links, wrong summaries, etc)

Re: Project Sid: Many-agent simulations toward AI civilization

#26

Post by jsemrau »

airstrike wrote: post #6

I've thought about this a lot. I'm no philosopher or AI researcher, so I'm just spitballing... but if I were to try my hand at it, I think I'd like to start from "principles" and let systems evolve or at least be discoverable over time Principles would be things like self-preservation, food, shelter and procreating, communication and memory through a risk-reward calculation prism. Maybe establishing what is "known" v…

Memory is really interesting. For example, if you play 100,000 rounds of 5x5 Tic Tac Toe. Do you really need to remember game 51247 or do you recognize and remember a winning pattern? In Reinforcement Learning you would based on each win revise the policy. How would that work for genAI?

Re: Project Sid: Many-agent simulations toward AI civilization

#27

Post by semanticc »

echelon wrote: post #4

All of their domains and branding are .aL I had no idea .aL was even a domain name. That's wild. I wonder how many of those are going to take off.

.al is just the TLD for Albania, similarly as .ai is for Anguilla. No idea why anyone would choose the former.

Re: Project Sid: Many-agent simulations toward AI civilization

#28

Post by ted_bunny »

Tiberium wrote: post #8

Honestly I'm really excited about this. I've always dreamed of full blown sandbox games with extremely advanced NPCs (which the current LLMs can already kinda emulate), but on the bigger scale. In just a few decades this will finally be made into proper games. I can't wait.

Game designers have barely scratched the surface of NPC modeling even as it is. Rimworld is considered deep but it's nothing close to it.

Re: Project Sid: Many-agent simulations toward AI civilization

#29

Post by catlifeonmars »

This looks like it is a really cool toy.

It does not strike me as particularly useful from a scientific research perspective. There does not appear to be much thought put into experimental design and really no clear objectives. Is the bar really this low for academic research these days?

Re: Project Sid: Many-agent simulations toward AI civilization

#30

Post by gmuslera »

They probably will fall fast into tragedy of the commons kind of situations. We developed most of our civilization while there was enough room for growing and big decisions were centralized, and started to get into bad troubles when things became global enough.

With AIs some of those "protections" may not be there. And hardcoding strategies to avoid this may already put a limit on what we are simulating.

Post reply on HN