> I have actually tried giving Claude binary files of games and it was able to reverse engineer to GoDot!
Oh wow...I hadn't even thought of trying something like this. There are soooo many games from that era that I'd love to play again without the hackery of emulation.
Just grab any game, especially old rom files form the 80s (I tried TimePilot and Road Fighter from MSX era). The model extracted the graphics, the sounds and then built the whole game. It takes less than 1 hour to port a 16kb rom file, in one shot. You will get a playable game, but you need a few follow up prompts to get it back to its original form. Usually some sprites or sounds issues, but very easy to fix, if you have played the original game.
So by old ROM files, you mean still PC games or MSX, Sega, NES, SNES? And when you have them in place what do you specifically ask Claude? This is interesting and I'd love to see if it can get me porting old games with zero coding knowledge.
this is the closest thing I could find. do you have a link to the reverse engineered RA2? I am surprised I do not get any recent repositories or forum posts about this, you'd think it would be more talked about
I didn't get this at all from the parent. They're simply stating that LLMs aren't entirely trustworthy, and that the responsibility is ultimately ours, not the LLM's.
> This is really what a lot of people need, a return to learning about something 2-3 weeks after it happens and more details are known.
I agree. Aside from emergencies or other truly circumstance-changing news, I am not sure there's really any value in being immediately informed vs. days or perhaps even weeks later. I just hadn't thought in these terms before.
I can't help but imagine how much healthier our society would be...
We don't have a local newspaper anymore but there are a couple of bloggers who follow city council meetings and other local happenings. I read those fairly frequently. National/world news I have stopped following at all, as 99.5% of it doesn't affect me and I have no influence over any of it.
> The pro argument is always quantity based, yet we never get to see the actual gain in quality. It's always "I'm doing SO MUCH more". Never "I'm doing better, with less effort."
For me, it's "I can do this now; yesterday I could not."
I am not a developer - I am a hack with some experience in a smattering of languages who hits very real obstacles very quickly. AI has allowed me to overcome those obstacles and build things that literally I could not do before.
Yesterday I could not differentiate quake 3 matches within a single demo file.
Today I can split them into separate files and have the server stream them to me so I can watch them on demand.
It’s basically the same thing as AI generated art, whichever side of that you fall on.
I do IT, I can’t make any kind of art to save my own life. The art the AI generates is neat to me because I get to feel in control of making something beyond my own skills.
The flip side is equally true, though. The things I make are derivative, and not particularly neat to other people (and actively irritate actual artists).
AI software is a lot like that. I’m happy people who aren’t software engineers can make their own thing and be totally in control of that. I’ve also yet to see much AI software that blows existing stuff out of the water. Most of is derivative of something that already exists, if not an outright clone with a slightly different emphasis (think Jira but for a very specific workflow).
I'm not going to show you but I'll tell you, because I'm hoping you're asking in good faith and not just being snarky.
With AI, I now have tools to analyze recorded demos from quake 3 and pull metadata from them, match them against recorded match statistics, and most importantly, split a large multi-match demo file into multiple separate matches/files which are all self-contained.
Doing this required the LLM to review the source for q3 to determine how to re-create gamestate and correct various aspects that were non-trivial due to huffman encoding.
I also patched the server to be able to stream demos to attached clients, so multiple people can watch a demo simultaneously. It can now seamlessly switch between demo-playing and game-serving. I've had multiple PRs to the main repo merged for this.
All these are far, far beyond my ability to do by myself, and none of these features/functions were really available in 2026. There are some long-abandoned demo tools out there, but they either don't work, don't compile, or otherwise are windows-only. My demo tools are python, and of course the q3 server code is c++.
These aren't great new things. They're not ground-breaking. They're merely new things I made for me and my friends. And I think it's great.
My spouse works in the DOI and while there maybe some inefficiencies, particularly in process, it isn't the people themselves which are the problem. Her group operates on razor-thin budgets and personnel constraints. They suffer the frustrations because they believe in the work.
Government doesn't turn a profit, so the main way for middle management to gain influence and seniority is to have more employees. Thus you have the interesting situation that they always have razor-thin budgets for employees in order to maximize the employee count under them and they spend a huge portion of time doing inefficient processes.
This is a profoundly dismissive and even circular take...or at least an intentional misrepresentation of what I said.
When I say personnel constraints, I mean there are almost not enough people to do the work that needs to be done.
When I say budget constraints, I mean the budgets and projects are funded so lean, that they're always having to cut sections out of projects to get what they can done with the budget they're given.
I have no idea where you've gotten this idea that the waste in government is from employing too many people, but in the areas I am familiar with, it's nowhere close to an accurate read.
I'm referring to things like the DOI rescinding the 2024 Conservation and Landscape Health Rule that allowed private ecologically minded conservation groups to restore and preserve land through leases -- something exploitive resource extracting private entities were already able to do.
Instead the DOI declared their "lean" and "constrained" force would revoke letting private entities lease for conservation. Something at odds with lean employees trying to maximize conservation ROI. Why would they be begging to rip away conservation from private hands into unavailable public hands if they didn't already have the manpower, unless they're playing a political fuck-fuck game?
That reveals the true fuck-fuck game. DOI employees claim they are lean, out of employees, etc while actively pursuing actions that are counter to how those acting in such circumstances are in the interest of acting. But actually their management are rescinding rules that help offload conservation to private actors happy to do it, instead diluting the ability of the DOI to preserve resources by instead tossing additional tasks on already overloaded employees at which point they'll have their spouses on forums complaining and stirring up the voters to try and bring more employees under their grasp. Presuming they're successful, they will then again swamp said employees, and the cycle starts anew.
Which brings me back to my assertion:
>. Thus you have the interesting situation that they always have razor-thin budgets for employees in order to maximize the employee count under them and they spend a huge portion of time doing inefficient processes.
If they were actually trying to unload tasks from employees they'd be happy that environmental groups were trying to take the load off DOI employees and paying them leasing fees to do it, but that's not in the interest of management, as that could reduce their headcount and ability to beg for more money. Thus you can witness from actual acts of the DOI, it doesn't matter how many resources and people they get, their management are acting in ways it will appear to employees like they're broke and thin on people because they're run on ragged edges (something not unique, seen in many other areas of government, that will keep expanding task for current employees to the point they always seem broke and stretched out and then those associated with the organization will beg for more to start the cycle over again).
The attack here is neither of those things.
reply