Thank you to the effort of building this game in the first place (I'm sorry that I never got to try it then), and thank you for re-introducing it to us today. I'll give it a proper play in my leisure time.
Thanks! would love to hear your feedback.
Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assembly
71–80 of 147 posts
Re: Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assembly
#72[flagged]
Re: Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assembly
#73A few weeks ago I downloaded a memory dump of a zx81 game, and ask Claude to build it in Go. It nailed it. Converted the binary back to basic and then to go. My idea was that the game would be unknown to llm training and perhaps a nice bench. What a crazy thing it is to be first at the advent of personal computing, and then in the inflection point where AI treats that first experience as archeology.
Curious if you had to do any follow up prompts. How large was the binary and which model did you use?
Re: Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assembly
#74Neat project.I've been experimenting with making reusable console porting frameworks since last October. Opus 4.6 was my first success with the NES 6502. Since then I've done static/native ecosystems for the Super NES, GBA. Nintendo DS, Playstation (most popular) and even Sega Genesis, such also uses the 68k. https://github.com/mstan/segagenesisrecomp I even extracted the 68k decoder to its own repo because I wanted…
Cool. I wonder how much additional harnesses would improve the porting process. In my case, I gave more freedom to Fable 5. The model was able to figure things out. I am hearing that the latest models works better with less restrictions. Curious to know the progress on the above.
If you want to see a bit more in depth, some shameless plugs but here's a few articles I've written as I've made progress:
https://1379.tech/building-enhancing-recomps-ecosystem-updat... https://1379.tech/recomp-ai-5-months-later/
Ultimately, Sega Genesis has been low priority. I've been focusing mostly on community feedback for my existing ones. Playstation is by far the most popular and the one I get the most PRs on. SNES is second. And right now Nintendo DS is newer, but has a very popular Metroid Prime Hunters I've been working a ton on.
NES and Sega Genesis get little attention. CDI and VirtualBoy [understandably] get no real attention.
I have an early original Xbox LLE prototype. Hoping to do more with it soon, but I'm all tapped out of usage at the moment. I got a lot done during all the crazy resets with OpenAI there for a while.
Re: Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assembly
#75[flagged]
Re: Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assembly
#76[dead]
Re: Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assembly
#77> Please post any questions. Since Claude did the port, wrote the article, and apparently understands it better than you do at this point, can we ask Claude? Is there a git repo we can point Claude at to interrogate it on the way things were done? Maybe you can share the transcripts you used to port it? It's marvelous that software can be written with minimal human input, but I guess I'm confused about why I would ta…
> ... confused about why I would talk to the human that prompted the AI, rather than the AI that did the work.
One reason is because you can't talk to the AI that did the work, not unless the human who prompted it is able to hand you a file with the complete session and/or context data. (And I'm not at all certain whether Anthropic would allow users to obtain that kind of thing, since it would probably be extremely useful to people trying to distill their models. It's possible they might allow user A to say "Hey, allow user B" (or anyone with the link) "to access my session with GUID ba5eba11-1234-5678-abcd-0decafc0ffee", but I doubt they'd ever allow context data to be downloaded and passed around).
Without the context, you're talking to a different instance of the AI that doesn't have the memory of the instance that ported the code, so the answers you get won't be nearly as useful.
Re: Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assembly
#78From the article:
move.l #$dff000,a0 ;Base for hardware registers
lea save(pc),a1 ;Get the system
move.w #$4000,intena(A0) ;from the AMIGA
Crude, although perfectly fine in practice. The system-friendly way is to call the function exec.library has for the purpose, Disable()[0].
0. http://amigadev.elowar.com/read/ADCD_2.1/Includes_and_Autodo...
Re: Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assembly
#79From the article: move.l #$dff000,a0 ;Base for hardware registers lea save(pc),a1 ;Get the system move.w #$4000,intena(A0) ;from the AMIGA Crude, although perfectly fine in practice. The system-friendly way is to call the function exec.library has for the purpose, Disable()[0]. 0. http://amigadev.elowar.com/read/ADCD_2.1/Includes_and_Autodo...
Thanks. I wonder if that was documented in the Amiga Hardware Reference Manual :) that was the only book I had back then. I remember it was mostly registers and assembly language.
Re: Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assembly
#80Wow, that's gorgeous for something written in assembly, running in 512k, nice work!
Looks like a pretty de-facto Amiga game of the era, to be honest.
Amiga 500 (and 1000 prior to it) supported smooth scrolling by simply setting the screen-visible pointer in memory.