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

11–20 of 173 posts

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

#11

Post by aleph_minus_one »

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.

> 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 will rather get crushed.

What you likely want is NPC that "behave more human-like (or animal-like)" - whatever this means.

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

#13

Post by Tiberium »

aleph_minus_one wrote: post #11
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.

> 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.

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

#14

Post by aleph_minus_one »

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 just want to watch and sometimes interfere to see how the agents react ;)

Even there, I am not sure whether if the AI bcomes too advanced, it will be of interest for many players (you might of course nevertheless be interested):

Here, the relevant comparison is to watching (the past) games of AlphaGo against Go grandmasters, where even the highly qualified commentators had insane difficulties explaining AlphaGo's moves because many of the moves were so different from the strategy of any Go game before. The commentors could just accept and grasp that these highly advanced moves did crush the Go grandmaster opponents.

In my opinion, the "typical" sandbox game player wants to watch something that he still can "somewhat" grasp.

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

#15

Post by caseyy »

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.)

Indeed sounds better for Civilization than civilization. This could be quite exciting for gaming.

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

#16

Post by dmix »

caseyy wrote: post #15
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.)

Indeed sounds better for Civilization than civilization. This could be quite exciting for gaming.

GTA6 suddenly needs another 2 years :)

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

#18

Post by kgeist »

aleph_minus_one wrote: post #11
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.

> 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…

>Even really good players don't have a chance against super-advanced NPCs

I guess you can make them dumber by randomly switching to hardcoded behavioral trees (without modern AI) once in a while so that they made mistakes (while feeling pretty intelligent overall), and the player would then have a chance to outsmart them.

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

#19

Post by m0llusk »

Interesting context, but highlights all the problems of machine learning models: the lack of reason and abstraction and so on. Hard to say yet how much of an issue this might be, but the medium will almost certainly reveal something about our potential options for social organization.
Post reply on HN