The joy of FUSE is that anyone can make a file system pretty easily.
dan
joined 3 years ago
You don't absolutely need a central repository for Git. It's decentralized. You can learn the basics (committing, branching, rebasing, amending, merging, resolving merge conflicts) entirely on your computer.
My advice would be to get familiar with using Git locally first. Simulate things like merge conflicts - have two branches that both change the same line in a text file, then merge them together and resolve the conflict.
Once you're more comfortable with using it locally, learn about code forges like Github or Forgejo.
It's called a "merge request" in Gitlab, which is a much better name.
Right?? $250,000 worth of equipment just sitting in a box in people's front yards. Crazy.
At least it's open source so anyone can look at the code and figure out why it asks for the permissions.
It's the same with public transit. Some people think the government shouldn't invest in it because it won't be profitable, but... it's not supposed to be. It's a public service, just like libraries, firefighters, parks, public schools, road maintenance, etc. That's literally what taxes are supposed to be for.
Gamers Nexus made a great video about this. https://m.youtube.com/watch?v=ZoYeJwN7Rkw
It's such a crazy idea. They're doing this because data center power capacity can't come online quick enough, data centers need permits, etc.
Residential power grids aren't designed to handle every house continuously pulling so much electricity.
Even if you don't consider power... They want to put over $250,000 worth of equipment in a box in people's front yards. 16 x RTX 6000 Pro GPUs, 4 AMD EPYC processors, 3TB of RAM, a 15kWh battery, and a 3 ton heat pump and liquid cooling powerful enough to keep all of that cool. I wonder how many will go "missing" 👀
Oops! You're right!
Not really. The state of the art models are huge, even the open-weight ones. You really don't want to quantize below 4-bit, and even that's a bit of a stretch... Ideally you'd use at least 8-bit to get good results with these models when used for coding.
GLM-5.1 needs around 400GB VRAM at 4-bit quantization. Apple aren't making the Mac Studio with 512GB unified RAM any more, so you'd need something like 5 x Nvidia A100 80GB to run a model like this.
Kimi K2.6 is around the same size.
The AI agents do a lot more than write code though. They can summarize meetings and emails, prepare project plans, create interactive design mockups, keep track of what you work on and write weekly/monthly summaries, create reports based on A/B test data, etc. If someone is heavily using AI, coding is just one part of it.
I use it quite a bit for planning and partially implementing side projects at work. Stuff that isn't my normal day-to-day project. They're usually APIs or internal webapps that I'd find useful but don't have time to do all the work myself.
For example, we use Google Chat at work, but its management of custom Emoji isn't great. I created an internal tool that shows all custom Emoji sorted by how frequently they're used, and allow people to vote on deletion (since we have a bunch of duplicates). I used AI to plan it, build the entities, write the code to hit Google's API, etc. I had it running in the background while working on other more important projects.
I treat it like an intern or a new grad. Assume the code won't be great, but I can guide it to do the right things.
I know people at work that spend much, much more than this. They're what I'd describe as "fully AI native". Honestly I don't know how they handle it since it seems like a lot of work.
They have over a dozen agents, all using Claude Opus in fast mode. The agents have roles - for example, one for technical architecture, one for UI design, one for building overall plans, one for coding, one for security review, one for code review, etc. They run codemods (automated code cleanup and migration to newer APIs) using AI. Their backlog/wishlist tasks are completed using AI. They have several OpenClaw-style bots that respond to Google Chat messages, run periodic jobs, summarize emails, etc.
If you want an extreme example... The developer of OpenClaw is "spending" $1.3 million per month on its development: https://www.businessinsider.com/openclaw-peter-steinberger-ai-token-bill-2026-5. He works at OpenAI so of course he doesn't have to pay for it.
You could build a significantly better, higher quality product if you spent that much on actual humans...
Debian is the universal operating system, and I'm sure OP's computer exists in some universe. File a bug.