AI: holden vy-l36-060a-enhanced-asm-patches github public

KingAustraliaggGG
Posts: 51
Joined: Fri Nov 15, 2024 2:19 pm
cars: 323i 1999 e46 sedan m52tub25 ms42 hx35w
328ci 1999 e46 coupe m52tub28 ms42
vy 2002 holden wagon executive l67 bottom end/36 top swap corn fed boost manifold ex44 external turbo hx40 holset
vs holden sedan turbo gt3582r

AI: holden vy-l36-060a-enhanced-asm-patches github public

Post by KingAustraliaggGG »

work in progress. to many ideas not enough skill on my end and dont want to pay for ida pro.

one you fellas would know exactly how to patch the bin and fix my errors here.

"https://github.com/KingAiCodeForge/king ... m-patches/"
User avatar
Knackersjewels
Posts: 155
Joined: Thu May 05, 2022 10:24 am
cars: Stock VZ SV6
Cammed VZ SV6 (sson to be 6L45 converted and twin turbo)
VY SS L98 ute
VZ V6 AWD One Tonner
Location: Maffra, Vic

Re: holden vy-l36-060a-enhanced-asm-patches github public

Post by Knackersjewels »

More AI slop? Use ghidra if you don't want to pay for IDA
KingAustraliaggGG
Posts: 51
Joined: Fri Nov 15, 2024 2:19 pm
cars: 323i 1999 e46 sedan m52tub25 ms42 hx35w
328ci 1999 e46 coupe m52tub28 ms42
vy 2002 holden wagon executive l67 bottom end/36 top swap corn fed boost manifold ex44 external turbo hx40 holset
vs holden sedan turbo gt3582r

Re: holden vy-l36-060a-enhanced-asm-patches github public

Post by KingAustraliaggGG »

can you explain how to set it up to work. $0000 cpu offsets or do i use the offset for the xdf calibration?
KingAustraliaggGG
Posts: 51
Joined: Fri Nov 15, 2024 2:19 pm
cars: 323i 1999 e46 sedan m52tub25 ms42 hx35w
328ci 1999 e46 coupe m52tub28 ms42
vy 2002 holden wagon executive l67 bottom end/36 top swap corn fed boost manifold ex44 external turbo hx40 holset
vs holden sedan turbo gt3582r

Re: holden vy-l36-060a-enhanced-asm-patches github public

Post by KingAustraliaggGG »

Knackersjewels wrote: Sat Jan 17, 2026 3:57 am More AI slop? Use ghidra if you don't want to pay for IDA
my TunerPro exporter actually works the one on github, and solved a real bug that Mark Mansur then fixed in TunerPro itself. That's the opposite of slop mate stop with the jealous bullshit and getting my posts deleted on facebook with ya arguing and drive by comments
User avatar
pman92
Posts: 667
Joined: Thu May 03, 2012 12:50 pm
Location: Castlemaine, Vic

Re: holden vy-l36-060a-enhanced-asm-patches github public

Post by pman92 »

KingAustraliaggGG wrote: Sat Jan 17, 2026 6:27 pm That's the opposite of slop mate
In the nicest way possible I tend to agree with Knackers.

AI has got you thinking it's created all these great patches. But you dont even know what address to load it in ghidra? So how do you know what it's generated holds any value and isn't just slop?

And all the AI generated markdown is eye watering to try read. If you want anyone to help the first thing I would do is delete the whole lot of it, read it and summarise it YOURSELF (not using AI). So it sounds like a human wrote it and isn't inflated to the moon with filler and padding and useless information - keep it sharp and to the point. And tell AI to stop generating you markdown for everything (claude is especially bad at this, you dont need a summary and implementation guide with every response. Tell it you want the code only).

And I'm not sure what the bug with Tunerpro was, but it sounds like just making Mark aware of it could have had it fixed? I seriously doubt that AI actually fixed tunerpro since it's closed source.

Again this is constructive criticism and not having a go. I understand AI is a great tool. But it is also a trap.
And I value this forum as one of the last places on the internet that hasn't been taken over by a wave of AI generated crap
User avatar
antus
Site Admin
Posts: 10014
Joined: Sat Feb 28, 2009 10:34 am
cars: TX Gemini 2L Twincam 8psi
TX Gemini SR20 18psi
Datsun 1200 Ute
Subaru Blitzen '06 EZ30 4th gen, 3.0R Spec B
Subaru WRX 2007

Re: holden vy-l36-060a-enhanced-asm-patches github public

Post by antus »

Ill leave this up for respectful discussion but i've also looked through the repo and can see a lot of errors and things missing in the documentation. Assuming AI generation I think its not there yet to create trustworthy documentation and it's going to lead people up the garden path if they try to base their projects on it. Suggestions like 12p but then fails to mention our nvram? Suggesting 11P on MAF cars? Suggesting to purchase 16kb memcals for 12p 32kb code.... havt dug in to the suggested code patches but if that has similar errors through the code it'll almost be a re-write to validate and fix each line of the code.
Have you read the FAQ? For lots of information and links to significant threads see here: http://pcmhacking.net/forums/viewtopic.php?f=7&t=1396
KingAustraliaggGG
Posts: 51
Joined: Fri Nov 15, 2024 2:19 pm
cars: 323i 1999 e46 sedan m52tub25 ms42 hx35w
328ci 1999 e46 coupe m52tub28 ms42
vy 2002 holden wagon executive l67 bottom end/36 top swap corn fed boost manifold ex44 external turbo hx40 holset
vs holden sedan turbo gt3582r

Re: holden vy-l36-060a-enhanced-asm-patches github public

Post by KingAustraliaggGG »

This repository is intentionally WIP and research-focused.
I’m the only maintainer and it’s been live for ~48 hours.
If there are errors, please identify specific faults in the assembly: address conflicts, incorrect assumptions, ISR context issues, or RAM misuse.
Claims without technical detail will be ignored.
Corrections with evidence are welcome.
KingAustraliaggGG
Posts: 51
Joined: Fri Nov 15, 2024 2:19 pm
cars: 323i 1999 e46 sedan m52tub25 ms42 hx35w
328ci 1999 e46 coupe m52tub28 ms42
vy 2002 holden wagon executive l67 bottom end/36 top swap corn fed boost manifold ex44 external turbo hx40 holset
vs holden sedan turbo gt3582r

Re: holden vy-l36-060a-enhanced-asm-patches github public

Post by KingAustraliaggGG »

pman92 wrote: Sat Jan 17, 2026 9:23 pm
KingAustraliaggGG wrote: Sat Jan 17, 2026 6:27 pm That's the opposite of slop mate
And all the AI generated markdown is eye watering to try read.
[quote/]
Markdown is the only format that is diff-native and reviewable at speed. People can comment line-by-line, submit PRs, and every change is attributable and reversible. PDFs, Word docs, and spreadsheets are fine for final releases but they are hostile to rapid iteration and community correction. I can auto-generate PDF and spreadsheet outputs later from the same source. For now I am keeping the repo in a format that supports fast review, fast fixes, and clear history
User avatar
pman92
Posts: 667
Joined: Thu May 03, 2012 12:50 pm
Location: Castlemaine, Vic

Re: holden vy-l36-060a-enhanced-asm-patches github public

Post by pman92 »

It's not the format that is the problem, it's the content represented by it. Don't try and auto generate PDF and spreadsheets, I think you missed the point.

My recommendation would be get these patches loaded up in ghidra or IDA yourself and see what you can come up with.

Use AI to help you learn how to get ghidra setup, rather than asking it to write the patches for you.
KingAustraliaggGG
Posts: 51
Joined: Fri Nov 15, 2024 2:19 pm
cars: 323i 1999 e46 sedan m52tub25 ms42 hx35w
328ci 1999 e46 coupe m52tub28 ms42
vy 2002 holden wagon executive l67 bottom end/36 top swap corn fed boost manifold ex44 external turbo hx40 holset
vs holden sedan turbo gt3582r

Re: holden vy-l36-060a-enhanced-asm-patches github public

Post by KingAustraliaggGG »

pman92 wrote: Sun Jan 18, 2026 12:29 pm It's not the format that is the problem, it's the content represented by it. Don't try and auto generate PDF and spreadsheets, I think you missed the point.

My recommendation would be get these patches loaded up in ghidra or IDA yourself and see what you can come up with.

Use AI to help you learn how to get ghidra setup, rather than asking it to write the patches for you.
i am having trouble with exporting within ghidra cause the .sla processors and the file being 128kb isnt letting it work. should i split the high and low banks and try that?