Comment by xpct
14 days ago
I think GTA6 will be the real test for how capable these agents are. Some of these mods use well-known emulation methods, and some of these binaries have probably been ingested by the LLM numerous times.
I don't mean to discredit LLM capabilities, it's just that these examples are heavily favored by what's already documented online.
Wine-style PS5 emulation has advanced far enough that I would bet money on there being a pirated GTA6 PC release based on the PS5 version available within six months.
Six months is a long time! I was honestly prepared to see more aggressive timelines when I wrote this comment :)
I'm currently working on OpenBFME[0] and I can assure you, enough LLM power guessing at the code in the binaries is enough to get the code for anything
[0] https://github.com/Open-BFME/
love to see it
btw this is the actual solution, not that whole stop killing games movement. not regulation.
It doesn't stop the need for the other things.
1 reply →
yeah for sure, and more modern games will probably be more difficult as well. but even so, games feel like one of the harder things to reverse engineer compared to most business software. yes there is the backend component, but that's mostly just crud.
LLMs have changed the obstacle of doing something from (time, attention, expertise) to (time, attention, tokens).
I don't see what's unique about GTA6. It's just larger in scope if you wanted to decompile or greenfield a custom engine.
But at the end of the day you'll be able to unpack the assets yourself and immediately have the worldmap running in a browser in Three.js. And once you're there, you can vibe-code any game you want on top of it.
At the very least, it will be a binary that hasn't yet been consumed by the LLM, so it's an interesting test!