All that to say, CrankGPT, I am your target demographic and if you don't respond to my request for a demo I'll be cranking my keyboard with bad reviews online. Or cranking a rowing machine that powers an LLM to do it for me. Wait...

1. It's automatic (sure, scripting regular rsync syncs probably isn't hard, but...)

2. It's p2p across all my devices (which from what I understand is not how rsync operates)

So as long as my laptop and my desktop are both turned on I can trust they're always fully up-to-sync with each other, and in my experience they always are.

Is your "writing job" one where the end goal is like short random articles on some giant aggregate, or something like instructional content for businesses or something? Where a human typing things was just a means to an end, rather than what I'd assume OP's doing where they're writing for their own joy and/or because people love their specific voice? Because that's the only way my brain can rationalize it right now.

...but all the AMD 395+ machines I can find are even more expensive than the aforementioned cheapest Mac Studio. Mac Studio starts at $2,000 (only 32GB), AMD 395+ 128GB machines seem to start at $3,000 from what I can see.

Here's a bullet point list of the things Claude's done according to OP:

* it picked up the general path immediately

* he explicitly pushed into "lets have V0 game play loop finished, then we can compound and have fun = not giving up".

* [I gave him game design ideas,] he comes with working code.

* [I gave him papers about procedural algos,] and he comes with the implementation

* brainstorm[ed] items

* create[d] graphic assets

* he created a set of procedural 2d generators as external tools

* he even helped me build the lore.

Every one of these are plausible in isolation.

My partner on the otherhand has an M3 Max 64GB which I've had way more success with. Setting up opencode and doing a tiny spec-driven Rust project and watching it kiiinda work was extraordinarily exciting!

I'm very interested in Local LLMs but the cheapest Mac Studio right now is more expensive than 8 years of a Claude Code Pro subscription, and incomparably slower/less capable. If I get bored with it, I will have a piece of unused hardware and a couple grand less in my bank account.

Will you have the hardware to run them? Perhaps. Will enough of Anthropic's/OpenAI's large enterprise customers have the hardware to run them and the money/desire to have their own internal teams set up and maintain them?

I'd absolutely love to see exactly what you're doing (...well, maybe in a world where I had unlimited time or could clone myself...) because as tight as the usage limits are I absolutely cannot fathom hitting them THAT early.

What are the requests like, and have you noticed what is Claude doing during them? Is it reading an entire massive codebase or files that are thousands of lines long? Or are you loaded up with many MCPs or have an ever-growing CLAUDE.md?