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

11–20 of 33 posts

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

#11

Post by MacsHeadroom »

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.

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

#12

Post by nm980 »

theaiquestion wrote: post #7
AgentK20 wrote: post #6

Earlier quoted context omitted.

EDIT: Actually there's apparently been a lot of progress recently that I hadn't kept up with; see the replies to this comment. Original message: From a quick peek at the source, this depends on the ChatGPT API for the underlying LLM. It could probably be modified to use a local copy of an LLM, but most models I've seen are 300GB+ and require significant computational resources to operate (think several $15k NVIDIA A1…

> most models I've seen are 300GB+ and require significant computational resources to operate (think several $15k NVIDIA A100 compute nodes). What? Where have you been the last 3 months? > the quality of the responses from the model are correlated with how large (and therefore how much compute) the model has There's a lot more to this including the model structure, training methods, number of training tokens, quality…

> EDIT: It actually says in the readme they plan to support StableLM which is interesting because at least at the moment that's not a well performing model

I chose StableLM because that's the only other model I knew of besides ChatGPT. I'm open to adding support for other models after I fix some bugs first.

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

#13

Post by theaiquestion »

nm980 wrote: post #12
theaiquestion wrote: post #7

Earlier quoted context omitted.

> most models I've seen are 300GB+ and require significant computational resources to operate (think several $15k NVIDIA A100 compute nodes). What? Where have you been the last 3 months? > the quality of the responses from the model are correlated with how large (and therefore how much compute) the model has There's a lot more to this including the model structure, training methods, number of training tokens, quality…

> EDIT: It actually says in the readme they plan to support StableLM which is interesting because at least at the moment that's not a well performing model I chose StableLM because that's the only other model I knew of besides ChatGPT. I'm open to adding support for other models after I fix some bugs first.

You might consider supporting ooba's api which would give you a lot of support for different things really quickly.

https://github.com/oobabooga/text-generation-webui/

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

#14

Post by nullsense »

theaiquestion wrote: post #13
nm980 wrote: post #12

Earlier quoted context omitted.

> EDIT: It actually says in the readme they plan to support StableLM which is interesting because at least at the moment that's not a well performing model I chose StableLM because that's the only other model I knew of besides ChatGPT. I'm open to adding support for other models after I fix some bugs first.

You might consider supporting ooba's api which would give you a lot of support for different things really quickly. https://github.com/oobabooga/text-generation-webui/

Yeah, I second this. I use this frequently and lots of models downloaded that I test out with it. I'm keen to see a more API led approach.

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

#17

Post by woah »

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.

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

#19

Post by nullsense »

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 was starring in a reality TV show playing pranks on people.

As generality increases to Infinity I'm not sure there's actually a way to solve this particular problem. It might just be a failure of imagination on my part.

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

#20

Post by newswasboring »

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…

Please tell me the name of this documentary. That sounds insane!
Post reply on HN