alt Hacker NewsGlancing at the Touhou 4 decomp[1], it's a lot better quality than a lot of AI decomps I've seen. It's matching, the variables are named sensibly, comments are sparse and comprehensible, and there's not much in the way of unaddressed Ghidra jank. And only in a month! My main complaint is that the file structuring seems more optimized for AI use than for mirroring the original intent of the devs. (Compare to this human-made Touhou 6 decomp.[2])
I know the retro game modding/decomp scene is already getting hit with a flood of low-effort ports.[3] Now they're going to be hit with a flood of half-decent decomps effortlessly generated by anyone with a $200/mo AI subscription, which become half-decent PC ports, which get modding support grafted on. It kinda just... totally eliminates that as a hobby entirely. I know people are going to be upset about this. And it's not even like with the AI art, where the pro and anti-AI camps live in their own camps. Solving the same puzzle twice just feels discouraging. Very similar to the problem academics are having with AI math/physics proofs.
I know a large reason people hate AI is because it's largely seen as tearing apart hobbyist/professional communities, eliminating reasons to collaborate with others and form relationships, and replacing it with an individualized dependence on a commercial product. It follows the same trend the tech industry took social media, from a method of connection to a tool of propaganda and paranoia and "@gork is this true?" This project, I think, is one of the most clear examples of that.
[1] https://github.com/N0zoM1z0/th04 [2] https://github.com/GensokyoClub/th06 [3] https://www.pcgamer.com/gaming-industry/pc-ports-of-old-cons...
Replies
When anyone can do these activities they will no longer confer distinction. So we are now motivated to find other ways to differentiate ourselves. This powers the next round of activities - our need to stand out by something.
I've been decompiling DOS games recently with help from the $20 subscription. The one compiled by the Watcom compiler took like two weeks, with 2/141 functions still not matching. The one compiled by Microsoft C reached a match in two days more or less.
I think this points in two directions - first that $200 is really unnecessary for this domain.
Second, that with more experience we might be able to write a non-AI matching decompiler and then naming and simplifying could be done by people/AI. While I appreciate the hobby part of it, I think automated tools are the way to really make it reach everything with far less dependency on pockets. The benefit to preservation would be incredible.
AI is just a tool, if your ability to form relationships was easily displaced by a tool, then I'd say it says a lot about the ability rather than the tool. It's the same argument of hand drill vs a drilling machine. No different. The ability to form relationships have always been with us. Instead of discussing in depth about code, perhaps it is going to be more along the lines of models, variants, self hosting, etc.
> Now they're going to be hit with a flood of half-decent decomps effortlessly generated by anyone with a $200/mo AI subscription, which become half-decent PC ports, which get modding support grafted on. It kinda just... totally eliminates that as a hobby entirely.
It really depends on your perspective of what the point of the hobby is. Were decomps/recomps a hobby because people wanted to make sure their old games could run on modern hardware and be extended with mods etc., or were they a hobby because people enjoyed the actual process of using Ghidra and reverse engineering by hand, and the decompiled game was just a side effect?
Personally I think it's awesome that PC98 Touhou games are getting recomps. Being able to play the series natively on modern hardware, and all hardware for the foreseeable future, is great and preserves the legacy of the series. I understand that for anyone who enjoys the actual act of reverse engineering it feels like cheating, though.
I think people will get over it. Music is a good example. Drum VSTs and piano VSTs are going to sound way better than you unless you're a 99th percentile musician playing on a 99th percentile physical instrument. But people still play the piano and drums, because it's fun. Same idea; the existence of AI doesn't stop people who love the act of reverse engineering from doing it.