Sooner or later a Greater Depression will come. Hopefully I will have sold my old PC, ditched my debt, and saved up enough Euros or Yuan to buy myself some Blackwell GPUs.

AI is the future. Anthropic is a dinosaur, doomed to become a historical curiosity.

Thank you. :)

Hopefully my projects make the lives of other people a bit better, alongside my own.

00000

I am thinking about starting up a $5 tip jar at Patreon, with my files free for anyone to download. If I can get enough money saved, I would be able to decrease the amount of time it takes for a project. So far, my projects take 3-7 days to succeed or fail, bottlenecked by the AI speed.

Unfortunately, my projects are pretty niche. Bastion, TEVI, System Shock 2, Ast Libra, Shrift, Sailing Era, The Humankind Odyssey, Alpha Protocol, The Jupiter Incident, and many others are probably too obscure to interest people.

Currently, using the Strata backend with Qwen-Flash-Next. It has successfully made 4 save game editors, 2 plugins, and did some work on La-Mulana 2006 to make the controls and graphics play nice with Windows 11, plus my gamepad. The DLC restoration mod is largely successful, I am doing QA for making the DLC accurate to what was offered in the ad copy.

000000000

Hermes Agent is my model of choice, and I have Strata using 256k context, on a IQ3. I find that Next-Flash is much faster than the smaller 27b, and has more personality. Sometimes it can get a bit loopy. I typically have the AI keep a bible of findings, and start a fresh Hermes session - then tell it to condense the information from the old workspace and session into a more relevant version. Save on context, and makes it more effective since it discards findings that have been superseded.

Hardware wise, a TRX50 AI TOP motherboard, 7965WX CPU, RTX 4090 and x2 RTX 3060, with 128gb of 5600 RDIMM. Down the line, I might try some GPU unlockers when other folk have tested them for bugs. So about a month or two?

https://github.com/JustAResearcher/gpu-unlock-ada

https://github.com/Zagitta/gpu-unlock

https://github.com/impacifist/Windows-GPU-UNLOCK

00000000

I bought my memory and the CPU from Ebay, for prices a bit lower than at Newegg. If I could redo my GPU purchases, I would have gone with a RTX Pro 4500 Blackwell. That has 32gb of VRAM, and occupies a single double-width PCIe slot, and sips energy. The RTX 4090 is only 24gb, and takes up 1 and 1/2 of my slots.

00000000

Qwen-Flash-Next is an experimental model, the official version might come out in a month or so. If it is the same size or smaller, I will switch to that as my main driver. My current AI model feels useful to me, but clearly has raw aspects to it. Vision is a big one, since this AI can fail to see or understand details.

I want the personalization…without Big Brother. My personal and local AI, should work solely for my interests. I have been using my local AI for creating an customized cookbook, making save editors, and right now, an restoration mod.

Never before have I had so much agency in my life. AI has great potential for self actualization, but corporations and government will be working to undermine it. Hopefully, everyday people will recognize that and make local AI the norm.

Personally, I am all right with this. Eventually those cards will be obsolete at the data farms, and be resold to everyday people. We little folk will want all the local AI power we can muster, and odds are these cards will get modded to have more VRAM onboard and slim enough to only take double-width slots.

My own RTX 4090 takes one and a half double-width slots, preventing me from having a third RTX 3060 to support my projects.

I think they would do “genital inspections”, as an excuse to violate women. For fun.