And one interesting aspect is the number of children getting these types of neutered machines as their first learning tool. I read another thread comment saying people that started with react actually feel that using straight html is more complicated. My professors say that the best textbook is the one you've read. The next generation is being indoctrinated into this way of thinking
as AI native developer I need VS code forks for AI to be pre-installed. Also every single command or work need to be vetted by AI by default. I am going hardcore now.
A few years ago I built a few small ones in my home lab. They are extremely efficient. With the right setup, have insane torque, and don’t require a lot of energy to do it. The best part for me was that they are completely brushless by design and are easily to keep clean.
I wrote my own Claude Code agent. It leverages some parts of multiple different agent stacks but using my architecture. It's layered, has long-term memory, agency to expand upon work, access to linear, access to all the models and endpoints you could possibly wish, as well as support for combining multiple providers and models into the layers so that delegation to the workers happen on the cheaper, more cost effective models. All of this runs at scale in an orchestration platform I wrote, using said agent, to create a cluster of docker containers in a JBYOS configuration, cross-cloud, k8s or swarm or whatever can run docker. It's pretty sweet and is basically an AI software development shop. I only have to give it ideas and goals.
As the 36 millionth person building something similar, I wish[0] there were better info out there on what works well. I can understand why, but it's still frustrating seeing on the one hand how deeply helpful the flywheel of this type of setup can be, and on the other hand how every blog post stops at some incredibly superficial setup to help them write more blog posts.
[0] Yes this is a plea, if anyone has the good stuff
Here's what I did, roughly, YMMV. I have a lot of experience in managing scale and web platforms as it's what I did for like a decade so, grain of salt and all. Let's assume you have access to N number of linux machines with GPU's, for the sake of argument.
I have a small RPI acting as my homelab pihole and dns so what better than to run the management UI on?! So I wrote a small bun management plane, nothing fancy, just a react app with user auth + openidconnect for those that like that stuff. From there, you have compute pool (empty at the moment because it requires a deployed agent). I added the ability to directly ssh into a machine, install the "agent" with privilege so it can manage docker, and the agent talks back to the management plane over websockets. A keep alive / health / status / resource packet every 15 seconds. Streams if you are looking at logs or accessing a container. I used Codex for most of this work but defined the protocol and everything upfront using protobuf (even though it's websockets). It helped with the "vision" and keeping the agent like Codex on the rails through completion.
Once you have a pool (agents installed on your N number of linux machines), you can deploy apps (which are my way of saying, a container with a namespace) or you can deploy agents (which is my agent, custom made for this) that are assigned to a project. I decided Org structures are a great way to delegate workloads so that's how they are modeled. Projects provide the git repo, the docker registry for images and storage of artifacts, as well as the history of all the prompts the agents have done in the project. Useful if you want to go back and search through |thinking| tags to figure out the reasoning behind a decision.
All of this was built in like maybe a month with Codex initially, until my agent was up to the task of coding w/ an endpoint configured (OpenAI API initially, now, NVidia DGX Sparks). What really works well is the delegation. The agent's have a webui that is exposed via the project urls so you can interact with the "scrum masters" of each project. They also share a stream if they are on the same project (but different subprojects).
I too wish there was more information on this but I didn't keep the lack of it from stopping me experimenting and finding what works. I came from the Mesos/DCOS era where you stop thinking about the metal and think in pools of resources. It's a distributed systems problem.
The landing page is still a "join the waitlist" placeholder and there hasn't been a single commit since one week after they announced it, ten months ago. Together with the entire repo and the ShowHN post itself being vibed through and through, it seems apparent that putting any amount of human effort into that project was never on the agenda. Which naturally leads one to wonder, what makes this project different?
If you like specific acts, sure. Or maybe some cities take independent venues more seriously than others. Growing up, ok I missed out on getting Metallica tickets because I didn't want to support clear channel (or Live Nation, or TM, etc...), but I still was able to see plenty of amazing metal bands in indie venues.
Another interesting note: Weird Al is playing three venues within driving distance from me. Only one of them is selling tickets through TM.
> Growing up, ok I missed out on getting Metallica tickets because I didn't want to support clear channel (or Live Nation, or TM, etc...), but I still was able to see plenty of amazing metal bands in indie venues.
I saw Metallica once, many moons ago, and it was at this big venue which of course was Live Nation/TM. It sucked ass. Sound was terrible, had to watch screens to see what was going on, beer was ridiculously priced and yet somehow long queues.
I decided then I wouldn't go to those venues anymore. If a band I like plays there, whatever, not worth it.
Meanwhile I've had many, many concert experiences that were 100x better than the Metallica concert for a fraction of the price of the Metallica ticket at small, local venues.
My buddy recently invited me to another such big-ass venue with some popular band, and it just cemented by view. So not worth it.
Go see Weird Al. It was a really great show. My wife only knew one of his songs (Word Crimes, she's a professional editor), and she loved the show. I loved it too.
I just saw him a couple weeks ago. It's such a fun show, people there are from ALL walks. He's no spring chicken but he gives it his all, and his band and backups do too. Just an all-around great dude.
True, I do see a thriving ecosystem here in Europe for some more fringey types of acts. There's like resident advisor ( https://ra.co ), XCEED ( https://xceed.me ) . Probably because some events don't meet ticketmaster's T&Cs (they can be a bit spicy).
In fact I have not used ticketmaster in the last 2 years, the last time was a big ticket stadium-type thing. Most of the events I attend are doing it through resident advisor and I have about 40 tickets in my history there now. I'm glad the ecosystem hold by ticketmaster is being broken, at least here in Europe.
Though even there you do see some ticketmaster crap popping up like universe.com
reply