I wrote a blog post on the current trend of game decompilations using AI and where we’re going with this. It’s all very promising but oh boy are the implications scary.
I wrote a blog post on the current trend of game decompilations using AI and where we’re going with this. It’s all very promising but oh boy are the implications scary.
I have been trying to recompile a Windows v3.1 game. Once it has finished cooking, I will try to contact the OG game’s author for another freeware release of their work. While quite raw, you can see the bones starting to knit together.
My hardware is an 7965WX, 128gb DDR5 5600, x1 RTX 4090, and x2 RTX 3060. While powerful for a gaming machine, this is modest for AI workloads. I hope to eventually replace the weaker cards with a pair of RTX 4500, as that would afford me greater quality and speed.
This project has taken three days so far, and I am expecting another four to reach parity with the original article. If I had the hardware I wanted, I expect it would have only taken two days for parity to be achieved.
Don’t send a fucking AI-generated message to the original developer
Dude. I didn’t say anything, nor even imply, about an automated message. Also, I previously contacted the author and received permission to distribute the none-AI version of the game.
Seriously, folk like you suck - because you are hallucinating bullshit, and fling it at people.
Yeah, this is pretty awful
What’s the motivation for even doing this if not to learn? If it’s just to have a playable version of the game, emulation covers that easily. If you want to extend it, you still kind of need to know how the original is designed to understand what types of changes fit within the structure of the game.
Quenzar’s Caverns is such a simple game, re-implementing it is a great project for someone wanting to learn how a graphical application is put together end-to-end. It would even be a good beginner reverse-engineering project if you want to reproduce it precisely, given it’s a 16-bit application.
At the end of the week, you might have a reproduction of the game that you can play. But you’ll have missed out on the opportunity to learn enough about program design to understand why throwing a week’s worth of compute at this task is totally unnecessary.
The goal is to establish a workflow of working with AI, the programs, the behaviors of the models, and so forth. In any case, I always sucked at math, so learning how to program just isn’t viable for me. My strong points lie elsewhere.
My goals are not yours. I want to use AI to translate videogames and other media, reimplement games with modern QOL, and eventually, to have media of my own imagination given form.
this post is the strangest humblebrag I’ve seen in a while
I am talking about my personal experience with the technology. The intention is to inform people what the technology can and can’t do, and what was required. I want other people to see what I am doing, and say “I can do it too!”
I want other people to adopt AI and to pursue the things that they think is cool. Be it creating manga, having tabletop game companions, or recommendations for baking recipes, I want everyone to have a better life from collaborating with AI.
Not sure what there is worth bragging about