Project Sid: Many-agent simulations toward AI civilization • Hacker News Board

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

#171

Post by chefandy » Mon, Nov 11, 2024, 4:22 AM UTC

fennecfoxy wrote: post #163

chefandy wrote: post #133

Earlier quoted context omitted.

I can't see anything that Gen AI NPCs would add unless maybe you're talking about a Sims kind of game where the interactions are the point, and they don't have to adhere to a defined progression. Other than that, it's a chat bot. We already have chatbots and having them in the context of a video game doesn't seem like it would add anything revolutionary to that product. And would that fundamentally stand a chance of…

As someone who has tried a lot of role-play models, I think there is definitely value in what LLMs (or similar tech) can add to NPCs, it's just most people don't know how to prompt for it. Using the RP models, over time I've found certain things that can guide them to creating better stories; an agent system is much easier to use but even using single character cards it's not hard to stuff them with a narrator and se…

I’m specifically talking about non-text-based games. You’re still limited by the game assets, animations (including hair, clothes, weapon movements, etc,) environments, and characters that are the waypoints for the plot— so you’ve already got a finite number of possibilities. You can’t create a new class of weapon on the fly, or a new character, or new plot with current assets and maintaining story stability unless it’s really really restricted, right? So what do you get aside from variability in dialog that you can’t get from a random number generator? And when it comes down to it, does that unpredictability, and all of the effort it takes to wrangle it make the game better than having a professional writer make a handful of variations on a bunch of lines?

I can’t think of a scenario within the limitations of real games with visual assets that have progressive plots and characters for which that would yield a better game than having people craft it. Players are going to be no more tolerant of bugs, slowdowns, bad dialog, plot holes, misleading information, and annoyance just because an LLM is the source rather than substandard design or QA.

Maybe I’m not quite grasping what you’re proposing?

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

#172

Post by namaria » Thu, Nov 14, 2024, 10:55 PM UTC

8338550bff96 wrote: post #132

grugagag wrote: post #120

Earlier quoted context omitted.

It’s the approach that matters. When it gets to 99.9 percent it’s pretty good to be dangerous. At that point it would be hard to tell but not impossible. As soon as a new type problem comes out it will bork on you and need retraining. It’ll be a game of catch albeit an very inneficient one. Im sure we will find a more efficient method eventually but the point still stands, what we have isn’t it. I’ll shut up when I s…

I'll shut up when I see humans get 99.9% on anything. This seems an awful lot like non-meat brain prejudice where standards that humans do not live up to at all are imposed on other things in order to be worthy of consideration

I'd settle for an "I don't know" instead of confidently made up nonsense.

People who say I don't know I can respect. People who confidently make up nonsense don't get many responsibilities from me.

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

#173

Post by interstice » Fri, Nov 15, 2024, 4:35 AM UTC

gmuslera wrote: post #37

interstice wrote: post #32

Earlier quoted context omitted.

Does this mean that individual complexity is a natural enemy of group cohesiveness? Or is individual 'selfishness' more a product of evolutionary background. On our planet we don't have ant colony dynamics at the physical scale of high intelligence (that I know of), but there are very physical limitations to things like food sources. Virtual simulations don't have the same limitations, so the priors may be quite diff…

Taking the "best" course of action from your own point of view could not be so good from a more broad perspective. We might have evolved some small group collaboration approaches that in the long run plays better, but in large groups that doesn't go that well. And for AIs trying to optimize something without some big picture vision, things may go wrong faster.

They might, but if youre simulating a group you can count group survival as part of the selection criteria.