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

Show HN: Smallville – Create generative agents for simulations and games

github.com

Post reply on HN
Print view View original

21–30 of 33 posts

Re: Show HN: Smallville – Create generative agents for simulations and games

#21

Post by ehnto »

woah wrote: post #17
philipov wrote: post #4

Uh... is there some way to use this without connecting to a server? Like, for a game that can be played offline? Finding a way to make the machine learning piece a completely self-contained library that can be shipped at scale to run on individual computers is the big hurdle to making AI like this practical for games. If I have to rely on your service staying up for my game to work, that's an unacceptable supply chai…

Dunno. I only ever play games that require an internet connection. I doubt this is an issue for most players.

Games are increasingly moments in time, moments where all the services are working, and other people are playing. Get it while it's hot or you'll be playing a dead world.

Do I think that's good? Absolutely not, I think it's terrible. But the commentor I'm replying to is right, "most players" won't care at all, else we wouldn't be in this position.

Re: Show HN: Smallville – Create generative agents for simulations and games

#22

Post by kleene_op »

YesBox wrote: post #5

Pretty neat. I'm creating an isometric, pixel art city builder game, though I imagine this wont scale to 10K or 100K units?

I'm interested in this as well.

I would like to know if the part of the LLM that stores the experience of interacting with the player is separate from the base model, and if so how heavy that specific part is?

Are we talking Mb or Gb?

Re: Show HN: Smallville – Create generative agents for simulations and games

#23

Post by holografix »

MacsHeadroom wrote: post #11
philipov wrote: post #4

Uh... is there some way to use this without connecting to a server? Like, for a game that can be played offline? Finding a way to make the machine learning piece a completely self-contained library that can be shipped at scale to run on individual computers is the big hurdle to making AI like this practical for games. If I have to rely on your service staying up for my game to work, that's an unacceptable supply chai…

7B parameter models are more than enough for this and run faster than talking pace on even a low end CPU. Even a finetuned 3B model would be excellent for generative agents and only use about 2GB of RAM to at high speeds on even a single core CPU.

Can you share some examples Of what models you’re referring to?

Re: Show HN: Smallville – Create generative agents for simulations and games

#24

Post by bayesianbot »

newswasboring wrote: post #20
nullsense wrote: post #19

Earlier quoted context omitted.

>Is there any way to protect against prompt injection here? Looking at the architecture I am thinking it would be possible for users to tell an agent what to do directly by tricking them. Not a solved problem in humans either. I remember watching a documentary on North Korea recently where they covered how his brother got murdered at an airport in Singapore by a woman who had been conned for months into believing she…

Please tell me the name of this documentary. That sounds insane!

Sound like this: https://www.imdb.com/title/tt11394276/

Re: Show HN: Smallville – Create generative agents for simulations and games

#25

Post by oreally »

nullsense wrote: post #19
green_man_lives wrote: post #3

This is so cool! I have been wanting to see something like this for a few years now. I tried making a demo of something similar (but much more primitive) in Unity back in 2021, but small transformers weren't good enough at the time. Is there any way to protect against prompt injection here? Looking at the architecture I am thinking it would be possible for users to tell an agent what to do directly by tricking them.…

>Is there any way to protect against prompt injection here? Looking at the architecture I am thinking it would be possible for users to tell an agent what to do directly by tricking them. Not a solved problem in humans either. I remember watching a documentary on North Korea recently where they covered how his brother got murdered at an airport in Singapore by a woman who had been conned for months into believing she…

Got the place wrong, it's an airport in malaysia, not singapore.

Re: Show HN: Smallville – Create generative agents for simulations and games

#26

Post by dekervin »

green_man_lives wrote: post #3

This is so cool! I have been wanting to see something like this for a few years now. I tried making a demo of something similar (but much more primitive) in Unity back in 2021, but small transformers weren't good enough at the time. Is there any way to protect against prompt injection here? Looking at the architecture I am thinking it would be possible for users to tell an agent what to do directly by tricking them.…

I love to see how things progress over time. Any chance you could post a link to your 2021 project ?

Re: Show HN: Smallville – Create generative agents for simulations and games

#27

Post by jheriko »

its interesting, but given the quality issues with this sort of tech, i can see it lowering the bar for games even further.

can you imagine trying to QA this?

in any case... getting this to go anywhere /for anyone else/ imo would require a tight native code library without network dependency, as others have said.

building on what you have looks like and awesome project though, and i wish you the best with it.

Re: Show HN: Smallville – Create generative agents for simulations and games

#29

Post by nullsense »

oreally wrote: post #25
nullsense wrote: post #19

Earlier quoted context omitted.

>Is there any way to protect against prompt injection here? Looking at the architecture I am thinking it would be possible for users to tell an agent what to do directly by tricking them. Not a solved problem in humans either. I remember watching a documentary on North Korea recently where they covered how his brother got murdered at an airport in Singapore by a woman who had been conned for months into believing she…

Got the place wrong, it's an airport in malaysia, not singapore.

Right you are!

Re: Show HN: Smallville – Create generative agents for simulations and games

#30

Post by nullsense »

newswasboring wrote: post #20
nullsense wrote: post #19

Earlier quoted context omitted.

>Is there any way to protect against prompt injection here? Looking at the architecture I am thinking it would be possible for users to tell an agent what to do directly by tricking them. Not a solved problem in humans either. I remember watching a documentary on North Korea recently where they covered how his brother got murdered at an airport in Singapore by a woman who had been conned for months into believing she…

Please tell me the name of this documentary. That sounds insane!

It was this one:

https://youtu.be/9qRxNYuR2c4

Post reply on HN