Novel compression method: we take all the textures in the game and describe them as AI image generation prompts.
Then, at load time, we run the generative image AI on the user's computer and thus generate them fresh.
The text descriptions are tiny compared to the images, so we get amazing gains in file size!
@foone as the image generative AI is in general just a weird decompressor, I doubt it's very effective. (and if it is, it should be easy to extract the (de)compression steps which are the most valuable)
Realistically I should be training it on, like, all 90s FPSes, as otherwise the generators model is going to be WAY bigger than the textures themselves would be.
Plus it'd be funny to see Half Life texture influences showing up in Wolf3D
@foone in all seriousness the procedural elements to define a material in something like blender are probably a small amount of text, so while I don't think packaging blender with your software makes a ton of sense I wouldn't be surprised if something like this has been done on some level (sans LLM fuckery)
@foone A few years back I made a joke that NFTs for carbon offset certificates would be a great business idea, and then half a year later I saw some startup doing this.
So, and I mean this very kindly, please for the love of Cthulhu SHUT UP!
@foone replacing phone calls by personal speech trained models.
You have to train a model once so that it can replicate your speech. While having to distribute the weights once to so your contacts, in the following you can use highly compressible text instead of audio.
In interstellar space flight this approach has been the modus operandi more or less since the first interplanetary voyage - especially with response delays ruling out interactive communication anyway
@foone We literally actually tried something like this last summer this for some robot planning algorithms at my company. It works alarmingly well, although less well than other, less stupid tricks.
@foone i've legit thought about something similar before, i think it would actually be a pretty legit use of ML tech - though i was imagining not turning them into prompts, but just a blob of inputs for the network. it would be like the ML version of that demoscene FPS kkrieger