Is git2go any good? Have been building with the rust bindings , doing tricky worktree/branching and no surprises yet

Just allocate a couple weeks for mandatory psychosis and constant distraction, followed by reflection and recovery, and then you can try again. Worked for me.

How do you get yours to say anything is bad or stupid? That's the real killer app.

Yeah, I have a review loop built on top of GSD that makes the local llm much more effective. I just need to replace GSD with something else. Making the review more complicated is an easy extension.

I have a cloud subscription and a 4090, and just trying to keep the gpu busy creates more code than I can handle. So I guess that's the problem to solve.

Still have an agent running constantly, but trying to focus on a single project, which has grown larger than all my other projects, and actually ship the thing.

I'm in the 'ran out of dopamine for the code slot-machine, other people shipping my early abandoned project ideas' phase of LLM adoption.

Maybe just me but i sling code a lot faster than infra, and LLMs are great for it. It's all copy-paste anyway. I even had local qwen admin my NAS supervised. Not going back.

I don't know who you mean, but there's no need to verify the outputs with type systems after the compiler already did that for me, so this is a confusing statement.

Congrats, you're more dependent on a specific toolchain and vendor than others, I guess. Quite the moat.

update: this is not ready for prime-time

I can't wrap my head around elitism people have for shipping the most vibe-slop. It's not that everyone else is worse at slinging markdown. It might be that the skill issue is taking the sycophancy at face value. I tried it out and got bored after 3w. Figuring out what's worth building is harder.

GitHub - gsd-build/gsd-2: A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of th... A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture - gsd-bui...

Been wanting something like this for the last few weeks I've been catching up to LLM things, which feels like an eternity. I started by building on top of beads/opencode, then adopted gsd v1, but I still didn't want to be the one driving state transitions.
github.com/gsd-build/gs...

What's the next phase of AI adoption after using up all my dopamine over 2 weeks catching up on agent TUI and subagent frameworks?

Why bother contributing upstream if claude can just make my fork better? Why accept a contribution instead of rewrite it if you like it?

I've been rewriting open source projects I see in rust for just to learn the tools over the last few weeks and I don't know why anyone would ship new open source for other people to use a year from now.

Everyone's going to be forking and maintaining everything themselves. I'm not sure what open source will be in a year.

The LLM game is instead of doing the thing you want to do, you build the CPU in Minecraft to run the bespoke compiler for an esoteric language specialized to your task, then eventually using that to do the task, just in case you get a similar task again.

Folks going to get rate limited by mental health providers

Swearing at Dr Sbaitso was my jam

I am at the stage of vibe coding where I create new projects to solve my own inability to juggle multiple projects.

Code craftsmanship might be dead, but I don't ever need to really learn CSS.

What if Yegge nonsense is not farfetched in a year?

Ah neat, didn't catch that core.async worked with this. Is it related to future plans to rip out IOC in newer jvms with virtual threads?

Bambu a1 mini is pretty cost effective and good, just small. You might want a bigger one later depending on what you're into.

It depends on if you want your hobby to be tinkering with the 3d printer or printing things. I liked learning on the Ender 3 V3 SE. It printed fine out of the box, but I enjoyed understanding the process and making it work better.

Spec-kit feels like a major productivity boost on day 1 despite apparently being just a bunch of prompt templates. I'm sold on the idea that a lot of code is just going to be throwaway now when you can just regenerate a viable implementation from a clear spec.

The difference is taking on a new library or tool is usually amortized over a long period of time of constant human process, and this is a massive change all at once.

I guess slop tooling is fine? I'm less excited about slop production code.

To be fair, the CPU I have today is 2x faster. I think Rust compilation speeds are good enough on a 16-core ryzen 5 to match my own ability to optimize or break things into smaller projects, but on my 2015 macbook pro it's barely tolerable.