It's pretty amazing what you can do when you embrace LLMs, figure out how to build one high-quality rigorous project with them, and then start working on more projects.
You become a machine with your workflow, once again limited only by your time/energy, tokens, and your discretion on how to spend it.
Mildly related, but I have been waiting for goldeneye to be decompiled for a while but before that process has finished there is has been a spiritual successor(?) made that has scratched the single-player itch for me: https://store.steampowered.com/app/1574480/Agent_64_Spies_Ne...
Worth a look if you want a bit of nostalgia.
I’m surprised the game companies themselves aren’t interested in these projects.
Seems like easy money to just decompile a retro game, add some quality of life improvements and stick it on steam.
Are their hands tied by legal or what other factors are preventing this?
> One small but useful improvement was to give every task an explicit deadline and expose that deadline to the agent.
I’m really curious about trying this myself. Recently I’ve been handing off tasks for agents to complete on their own more and more. While their work is acceptable I’ve found them to not only take a long time to complete it, but they often add too much complexity and tests.
I don’t remember this game at all - and there weren’t many N64 games, especially in the first couple of years.
What's the legal status of these?
Historically there was a notion of "clean room" reimplementation.
These days it seems people translate the actual game code into a different representation of that same code and that makes it open source? Github is full of these.
LLMs are truly amazing and I hope those decomp will keep coming! I am currently watching the Test Drive Unlimited decompilation project, which seems to use a mix of LLM decomp and actual engine improvement (porting the game to Vulkan and a new physics engine instead of Havok): https://github.com/opentestdriveunlimited/OpenTestDriveUnlim...
It's especially annoying that LLMs/agents are a logical starting point for decompiling old games but there is a significant backlash against it as the gaming community is very anti-AI and consumers of the benefits decompiling offers tend to be noncoders who don't believe that AI can do more than slop. I've seen takes such as "they're too lazy to learn C++" and accepting a PR from someone using Claude taints the project irrevocably.
I think Marx is rolling in his grave over the tirelessly expended human to recreate what almost definitely already exists on a floppy sitting in some “IP - Do Not Touch” lock box. But maybe endless puzzles for ever cleverer people is the point of it all.
Its really great how we can breathe new life into older games like this. I'm currently working solo on a Tales of Symphonia gamecube decomp. My aim is to let AI do everything of substance. currently about 3400 functions are exact out of about 4800. So still a way to go. But I haven't written a single line yet.
Awesome. Hopefully AI will allow more games to be decompiled in the future. Anyone working on a decomp of Perfect Dark?
I love the game Monster Hunter2 so much that I once practiced decompiling it. I worked on it for about two months and got maybe 5% done. Sometimes I really admire people who do this kind of decompilation work.
Unfortunately, the community will not accept an AI-assisted decomp. Gotta do it for real.
I've been absolutely loving the decomp projects that have been coming out lately. Huge props to the writer for this, Snowboard Kids is a real gem.
I'd also encourage people to check out the Legend of Dragoon recomp [1]. It's a real labor of love that has breathed new life into a largely abandoned game. You can play it fully vanilla, or with improved graphics, fixes to cumbersome design choices, bugfixes, etc.
[1] https://legendofdragoon.org/projects/severed-chains/