The Guardian Legend on the NES

I definitely prefer recompilation over ROMs. For me, I want to play the best version of a game possible - be it content, QOL, modding, or technical compatability.

Right now I have an small experiment running with my local AI (Qwen-Next, via Strata+Hermes Agent), to attempt recompiling a Windows v3.1 game into being a native modern application. Whether it works, and how much QA is required to get the gameplay and aesthetic into good order, remains to be seen. Personally I expect this AI model to fail, but this is more about seeing how many months I should wait before trying again.

As to games I want recompiled, the Magic Carpet games could use modern technicals and interface, maybe a progression checklist for goodies in Vampire Survivors fashion. A shortlist of other games needing love:

• The Jupiter Incident
• Solo Joe
• Star Trek: 25th Anniversary & Judgment Rites
• Tyrian 2000
• The Quest for Glory series, with AGDI's QfG2 as a blueprint.
• ...and more.

There are many games ignored by the retro community, so it is up to me and fellow AI advocates to give them TLC. Frankly, "soul", "humanity", "suffering for art" and other such bullshit doesn't deserve respect. That is elitism designed to gatekeep and make people feel like special snowflakes.

Results are what matter, not the pain of the process.

@Denjin@feddit.uk Hi a new Blast Corps recompilation project appeared a few days ago: https://github.com/djultra64/Power-Dozer Unlike retroplastic's project, this is a recompilation with Ai, not a full decompilation.

Right now I have an small experiment running with my local AI (Qwen-Next, via Strata+Hermes Agent), to attempt recompiling a Windows v3.1 game into being a native modern application. Whether it works, and how much QA is required to get the gameplay and aesthetic into good order, remains to be seen. Personally I expect this AI model to fail, but this is more about seeing how many months I should wait before trying again.

I'm curious as to your progress on that

Results are what matter, not the pain of the process.

Not related to what you're doing, but be very careful with that mindset, because it's used to excuse all sorts of exploitation and abuse

When it comes to the progress, the biggest roadblock is probably the vision capability of the model. It seems to miss assorted details from game screenshots that are provided, such as aesthetic flourishes and the layout of panels. The AI can replicate most words, identify monsters and furniture and make a game bible that includes information from decompiling the game and the manual.

Establishing the gameplay and the functionality of the interface is coming a bit more easily. With that, you can simply play the OG game and the recompile side by side in identical scenarios, then see where they diverge. For example, how the buttons interact with items on the floor. The AI made it so that the player can use the Holy Hand Grenades found on the floor. The OG only allies them to be used during combat. It is easy to iterate on such QA issues.

In some ways we were able to establish some QOL features as we went. One such example is an indicator for how many grenades and 'parleys' the player has, alongside with making the Blast spell a button option. In the registered version of the game, you could sacrifice health to cast a spell, but you had to use ALT+F1. Now we got a dedicated button, that also tracks how much health it costs to take this action.

The second picture here, is a mockup that improves over the AI's own attempt at replicating the OG, which I then passed back to the AI to be implemented. The AI botched it, as you can see from the strikethrough and mismatched furniture picture. That sucks, it takes the AI from half an hour to a couple hours to investigate and implement changes on my hardware.

To get more visual authenticity and cleanliness, probably requires a better vision projector, or perhaps remastering the assets inside ComfyUI. Hopefully, Qwen4 Flash can remove the need for visual remastering.