My eternal advice to anyone doing heavily LLM assisted projects is to do them a bit less LLM assisted. You should still use LLMs, in my opinion, they're wonderful tools. But I know reading this page that this text is mostly LLM-generated, and that leaves there to be little hope that much else of the project isn't.

It's one thing if your code is really truly "co-authored by" Claude. It's another thing if it isn't even really co-authored by you.

Evidently the majority of people see no problem with LLM prose, but me and many others think it is some of the most annoying crap possible. Please consider speaking in your own voice.

I know this gets repetitive, but it is important.

I ran NetBSD 0.8 on my Amiga 500 (with a 68030 w/MMU, 68881, and SCSI hard drive sidecar), which co-existed in the same timeframe as Commodore's release.

Other than just than "we can" and historic interest, I can't imagine why anyone would choose to run System Vr4 over 4.4BSD, especially since the latest NetBSD 11 release still fully supports Amiga[0]

[0] https://wiki.netbsd.org/ports/amiga/

Being an owner of Apollo V4 ITX UEB, I wondered what about 68080. With 64-bit and AMMX vector extensions. But the website briefly mentions "and on today's accelerator hardware". MiniMig is also not mentioned, but at least PiStorm is.

With regards to 68080, the toolchain that can make use of all features of 68080, is based on some old GCC and currently hosted on Linux amd64 which is a shame. And if original Amiga target is desired, this toolchain can do it too, and it is told to be more optimal than other compilers, especially self-hosted ones. GCC first lost ability to run on Amiga, then lost ability to generate m68k code.

Would it be possible to just focus on the project rather than on LLMs?

I get pet-cemetery vibes from these AI powered resurrections.

As in ... "the AI brought it back to life, but it came back /wrong/".

I like that the screen recordings are ‘Real time, with the long waits taken out.’

I mean, Debian 3.1 (sarge) supported Amiga hardware. The support was dropped in 2007 (the next release), because not enough people were maintaining it. I would assume that it would be easier to re-start that effort, unless compatibility with actual Amix was important for some reason?

This project might run into some trademark issues.

[dead]