Comment by spijdar
14 hours ago
The problem isn't that people consider it boring, it's that the use of LLMs is considered essentially sacrilegious, and whatever end-result that's created is considered tainted, often regardless of the extent of LLM usage.
Which does kind of suck. Yeah, it's not nearly as cool to say "I prompted a probabilistic pile of tensors and it did the hard work for me", and I think it majorly adjusts how "impressive" projects are. There's no point pretending like decompiling a game by hand and using GPT-6.7 to do it are remotely comparable.
The suck-y part is that if you do the decomp with GPT-6.7 and produce, say, a PC port of an early 2000s console game, a large number of people will refuse to touch it and treat it as if you have committed a cardinal sin. Maybe that's justified? I dunno. It definitely goes beyond people just saying it isn't as fun.
> Yeah, it's not nearly as cool to say "I prompted a probabilistic pile of tensors and it did the hard work for me", and I think it majorly adjusts how "impressive" projects are.
Vibe-decomped projects are also… a different result.
A matching hand-decompile is useful in itself, but it also serves as a proxy for how well you understand the project; how good are the function and variable names, are the structures good, do you understand the entire flow. There are plenty of LLM-decompiles out there that just match but still every variable name is “unk14”, where every flow is total spaghetti instead of going back to something closer to what a human would have written, or even tons of __asm__ statements. The match stopped being a high-quality proxy metric for the quality of the project as a whole. (There are also LLM-assisted decompiles that are high-quality, but then usually with significant human input. And of course, you can try to ask the agent to clean up the resulting mess after you're done matching, assuming you have any tokens left.)
Of course, if you just want the binary back and collect Internet points, you don't care about any of this. But decompilation projects are often made for either a) understanding the game better (for speedruns, TASes, or just general explanation), or b) modifying it. And for both, it is much nicer to have source that is closer to the original.
Its curious the cultural differences you see in some places too, a not too uncommon Japanese one I've seen is where the cardinal sin is "stealing" other people's creative works, rather than anything specifically involving LLMs.
Meanwhile so many westerners see LLMs as "stealing IP", it becomes a bit paradoxical where the lines get drawn.
Even Japanese attitudes towards IP are not that clear cut. One of the reasons the MiniDisc format was so popular in Japan vs the rest of the world was that physical media in Japan is expensive, so there are stores which rent out CDs. Those CDs would often be copied to MD (or later to PCs.)