Hacker News new | ask | show | jobs
by SamBam 822 days ago
The Infinite Craft game was sending queries up to ChatGPT to make the new items, if I recall correctly. This one is happening so quickly it must be happening locally. Is that right? Is it using a local Javascript LLM?
5 comments
luto 822 days ago
It just has a giant database of concepts and their splits built-in. Most of the time it's pretty unnecessary to run an LLM (directly).

https://lantto.github.io/hypersplit/assets/index-DhIQc66H.js

link
free_bip 821 days ago
Does it use ChatGPT thought? I thought Infinite Craft actually uses a fine-tuned LLama2 model.
link
KomoD 821 days ago
> I thought Infinite Craft actually uses a fine-tuned LLama2 model.

Yeah, it does.

link
hobofan 822 days ago
Infinite Craft was only sending queries to ChatGPT when it encountered a new combination. Otherwise it was hitting a remote cache, and I think also a local cache before that.

I am assuming that this game can fully pre-load everything, as all splits are predictable.

link
DannyPage 822 days ago
There aren't any network calls; It's all pre-fetched and stored in the javascript file. The file itself seems to be tagged to the build, but it's in the ./hypersplit/assets/index-<ID>.js file.
link
xnx 822 days ago
There are no network requests when splitting, so I believe it's all local. Not sure a local LLM would be necessary if all the splits are deterministic and pre-computed.
link