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

121–130 of 173 posts

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

#121

Post by j1elo »

wongarsu wrote: post #118
nobrains wrote: post #105

Earlier quoted context omitted.

I had the opposite thought. Opposite to evolution... What if we are a CREATED (i.e. instant created, not evolved) set of humans, and evolution and other backstories have been added so that the story of our history is more believable? Could it be that humanity represents a de novo (Latin for "anew") creation, bypassing the evolutionary process? Perhaps our perception of a gradual ascent from primitive origins is a car…

We also can't rule out that Gaia or Odin made the world five minutes ago, and went to great lengths to make the world appear ancient. It certainly makes sense if you assume that the world is a simulation. But does it actually explain anything that isn't equally well explained by assuming the simulation simulated the last 13 billion years, and evolution really happened?

As long as we don't get to the point of being able to simulate a Universe ourselves, the odds are against us being in a simulation, it seems! :)

https://www.youtube.com/shorts/EeqyGquTHK4

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

#122

Post by shagie »

bbor wrote: post #117
shagie wrote: post #53

Earlier quoted context omitted.

Evolve is another beast... but for the: "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" part, hunt up a copy of "The Society of Mind" by Minsky who was both and wrote about that idea. https://en.wikipedia.org/wiki/Society_of_Mind…

Wow, you are maybe the first person I’ve seen cite Minsky on HN, which is surprising since he’s arguably the most influential AI researcher of all time, maybe short of Turing or Pearl. To add on to the endorsement: the cover of the book is downright gorgeous, in a retro-computing way https://d28hgpri8am2if.cloudfront.net/book_images/cvr9780671...

I've tangentially mentioned it before though I don't think directly (it has influenced my theory of humor).

Mentions of it show up occasionally, though it seems to be more of a trickle than an avalanche of mention. Much more so back when AI alignment was more in the news. https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...

Part of it, I suspect, is that it is a book book from the 80s and didn't really make any transition into digital. The people who are familiar with it are ones who bought computer books in the late 80s and early 90s.

Similarly, "A Pattern Language" being a book from the time past that is accessible for a lay person in the field - though more in a tangental way. "A Pattern Language: Towns, Buildings, Construction" was the influence behind "Design Patterns: Elements of Reusable Object-Oriented Software" - though I believe the problem with Design Patterns is that it was seen more as a prescriptive rather than descriptive guide. Reading "A Pattern Language" can help understand what the GoF were trying to accomplish. ... And as an aside, and I also believe that it has some good advice for the setup of home offices and workplaces.

As much as I love the convince of modern online book shopping and the amount of information available when searching, the "browsing books" in a book store for "oh, this looks interesting" and then buying it and reading it, I feel has largely been lost to the past decades.

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

#124

Post by mindcrime »

FeepingCreature wrote: post #104
mindcrime wrote: post #60

Earlier quoted context omitted.

Also: "learnings". https://dictionary.cambridge.org/us/dictionary/english/learn... "knowledge or a piece of information obtained by study or experience" "I am already incorporating some of these learnings into my work and getting better results."

That example was added in 2022. https://web.archive.org/web/20190903044149/https://dictionar... You can clearly see that the prior use was very different. Cambridge Dictionary just documents that it's in fact used that way. One may still disagree on whether it should be. "That's not English" is usually prescriptive, rather than descriptive. And though English does not have a central authority, individuals are very mu…

That example was added in 2022.

I'm very sure that using "learnings" in a way that is roughly synonymous to "lessons" predates 2022 though. It may have only been added to that specific dictionary in 2022, but the usage is certainly older.

"That's not English" is usually prescriptive, rather than descriptive. And though English does not have a central authority, individuals are very much allowed to hold prescriptive beliefs - that is how language evolves.

Very true. :-)

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

#125

Post by mindcrime »

bbor wrote: post #64
ytss wrote: post #62

Earlier quoted context omitted.

I believe that “learnings” is also a word that could be applied in this context. It seems to me “learnings” would actually be less ambiguous than “lessons”. A lesson brings to mind a thing being taught, not just learned.

Let’s take this learning offline and circle back during the next sync, team

s/team/fam/

:p

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

#126

Post by ileonichwiesz »

ted_bunny wrote: post #28
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.

Rimworld is heavily inspired by Dwarf Fortress, so if you’re looking for more complex examples you don’t have to look far. DF is pretty granular with the physical and mental states of its characters - to the point that a character might lose a specific toe or get depressed about their situation - but of course it’s still a video game, not a scientific simulation of an AI society.

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

#127

Post by BlueTemplar »

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…

Huh, so the video actually works ? It just shows up «No video with supported format and MIME type found.» for me...

Yeah, memes and genes are both memory, though at different timescales.

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

#128

Post by BlueTemplar »

Philpax wrote: post #75
caetris2 wrote: post #52

Earlier quoted context omitted.

LLMs are stateless and they do not remember the past (as in they don't have a database), making the training data a non-issue here. Therefore, the claims made here in this paper are not possible because the simulation would require each agent to have a memory context larger than any available LLM's context window. The claims made here by the original poster are patently false. The ideas here are not supported by any…

> LLMs are stateless and they do not remember the past (as in they don't have a database), making the training data a non-issue here. That's not what they said. They said that a LLM knows what elections are, which suggests they could have the requisite knowledge to act one out. > Therefore, the claims made here in this paper are not possible because the simulation would require each agent to have a memory context lar…

Voyager's claims that it's a "learning agent" and that it "make new discoveries consistently without human intervention" are pretty much wrong considering how part of that system is using GPT's giant memory of ~~all~~ a lot of human knowledge (including how to play Minecraft, the most popular game ever made).

In the same sense, LLMs "not remembering the past" is wrong (especially when part of a larger system). This seems like claiming humans / civilizations don't have a "memory" because you've redefined long term memory / repositories of knowledge like books to not be counted as "memory" ?

Or am I missing something ??

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

#129

Post by dartos »

teaearlgraycold wrote: post #80
caetris2 wrote: post #76

Earlier quoted context omitted.

You've absolutely nailed it here, I agree. To make any progress at all at the tremendously difficult problem they are trying to solve, they need to be frank about just how far away they are from what it is they are marketing. I am whole-heartedly in support of commercial interests to drum of awareness and engagement by the authors. This is definitely a cool thing to be working on, however, what does make more sense i…

It would however be very interesting to see these kinds of agents in a commercial video game. Yes they are shallow in their perception of the game world. But they’re a big step up from the status quo.

https://www.playsuckup.com/

It’s a game where you, a vampire, convince townsfolk that you’re not, so they let you in their house.

The NPCs are run by LLMs. It’s pretty interesting.

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

#130

Post by chefandy »

bob1029 wrote: post #70

I feel like there is some kind of information theory constraint which confounds our ability to extract higher order behavior from multiple instances of the same LLM. I spent quite a bit of time building a multi agent simulation last year and wound up at the same conclusion every day - this is all just a roundabout form of prompt engineering. Perhaps it is useful as a mental model, but you can flatten the whole thing…

TBH I haven't seen a single use of LLMs in games that wasn't better served by traditional algorithms beyond less repetitive NPC interactions. Maybe once they get good enough to create usable rigged and textured meshes with enough control to work in-game? They can't create a story on the fly that's reliable enough to be a compelling accompaniment to a coherent game plot. Maps and such don't seem to need anything beyond what current procedural algorithms provide, and they're still working with premade assets— the implementations I've seen can't even reliably place static meshes on the ground in believable positions. And as far as NPCs go— how far does that actually go? It's pure novelty worth far less than an hour of time. Let's even say you get a guided plot progression worded on the fly using an LLM, is that even as good, let alone better, than a dialog tree put together by a professional writer?

This Civ idea at least seems like a new approach to some extent, but it still seems to conceptually not add much. Even if not, learning that it doesn't it's still worthwhile. But almost universally these ideas seem to be either buzzwordy solutions in search of problems, or a cheaper-than-people source of creativity with some serious quality tradeoffs and still require far too much developer wrangling to actually save money.

I'm a tech artist so I'm a bit biased towards the value of human creativity, but also likely the primary demographic for LLM tools in game dev. I am, so far, not compelled.

Post reply on HN