this post was submitted on 14 Mar 2024
33 points (92.3% liked)
Emulation - Retro Gaming In Style
942 readers
16 users here now
A community for discussing emulation and preservation of retro games. This community is intended for discussing the art of emulation, the tooling involved and retro gaming in general; it is not intended as a dump of ROM files.
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
What does "more capable AI" have to do with this?
I could see AI being very helpful in the painstaking original target console RE'ing effort. A capable system could make short work in a process that takes years manually
But AI has no actual intelligence of it's own. It's not going to magically just figure things out. All it can do is spit back what it has been fed.
That's 100% not how AIs work. Not even LLMs.
The whole point of AIs is they work beyond their training data. Otherwise they couldn't do anything.
Those who say these things severely underestimate what AI is capable of or will be in short order or just don't understand how they work and why.
But setting that aside, I'm not saying we'll be able to feed AI a raw decompiled firmware and have it spit out a fully functional emulator in an hour.
But, in the near future we might be able to feed it raw decompiled firmware and it'll be able to map proprietary undocumented syscalls in a few minutes, that would be a big chunk of work that could take months of not years
A decent AI model could significantly lower the barrier to entry for emulator development from "A handful of elite hackers and programmers"
I see you don’t understand what an LLM is, how they operate or comprehend the kind and volume of training data that is required.
So you do not believe AI will eventually be able to near instantly code anything you desire including an emulator?
With current models? No. See my points above especially the one about the volume of data required.
Reverse engineering firmware is extremely niche, even more so for emulation. There are so few examples that current AI models wouldn’t have enough training data to work off of.
AI is the future of everything tech and while today it is stumbling to really deliver on the promise, it is clear that the trend is towards more and more powerful AI. Given that it can code fairly well already and near instantly means someone is likely already using it in their emulator development to help speed things up. I personally use AI for coding daily and over the past year it went from hardly usable to some dang impressive responses on even larger scripts and even multiple interdependent scripts. Still has a ways to go but if this trend continues as is, there is a point in the near future where an AI agent will be able to make you anything with code you desire including an emulator.
From my experience anything beyond hello world and the simplest scripts AI is absolute garbage. Even if what AI makes compiles it will commonly give either the wrong output or is so poorly optimised that it's easier to start from scratch than try to fix what AI cobbled together.
Then you are using it wrong. I use it everyday at work and it's really good most of the time.
I have had those experiences too…especially early to mid last year, but today, I am having AI write and edit scripts over 400 lines of code and it is very good. So good that I have not personally written any code for months as it is just so much easier to just have AI write it in seconds. I have written all the code for my award winning VR app with AI so yes…it really is getting very good.
I tried it for an API I was making for work last month. It took like 6 attempts before it even compiled and then it completely screwed up the data it's transferring.