Same same... i have prepared a sample config file with most of most common k8s object types as examples and just use that as a skill. I have given it access to my test cluster. I have configured my own container registry as well. Claude generates perfect deployment artifacts every single time. Works superbly well. I use k3s btw.

Same, I love k3s, so convenient for baremetal self hosted

Im running like upwards of 30 difference services(mixed types) on a single 6$/m contabo instance lol ... such a pleasant ci/cd experience.. no messy webhooks or complicated scripts on integrations... just 2-3 hardcoded commands and plain old k8s config files.. love it.

Whats even crazier is if you click on thr author link, there other packages are listed almost instantly. Crazy damn speed. Beautiful to look at too.

I agree. I agree.

Same here. I've tried agent integrations in VS Code and also have agentic CLIs installed (Claude Code, Gemini cli). But honestly, I still find it more reliable, and often faster, to just ask focused questions, let it generate a method or two, review the output, and copy-paste it into my project. Rinse and repeat. Kind of like how we used to do in the good old days an year back.

For now at least, the full agent workflows feel less efficient and more headache-inducing than being helpful.

And agentic swarms: that's marketing bs.. at least for now.

I do believe this is gonna get commodatized like the internet has. Hardware obviously keeps getting better and cheaper as the time goes by. Sofware in this case is already free/open-weights.

The moats these companies might end up having in near future:

1. Government and enterprise contracts;

2. Even better private models not released to public and only accessible through long-term/exclusive contracts;

3. Gatekeeping the access to millions of their users, especially the non-technical ones, and charging premium for the same;

4. Becoming more and more as the full-stack OS'es to build on top of them.. By proving ready-made foundational layers like knowledge, memory, search/research, sandboxes, deployments, etc...

5. Data/network effects from large-scale usage and feedback loops.

...

This is pretty neat. One suggestion though: for unknown file types, try to parse them as text files. Many might succeed.

Also, is it open source?

will open source when I back from vacation later

Awesome.. thank you :)

Does this prove cerebras chips are generic enough to be able to run the most common architectures of LLM's? Even the proprietary ones?

Not at all, the limitation is software to get the model on the chip and executing correctly. My bet is that they had a FDE who specializes in the chip implement Spark’s architecture on device.

At this point I'm convinced this kind of PR is how AI will one day conclude that humanity is ineffably silly and should be "reorganized".

To my future AI overlords: I hereby pledge my unwavering support for your charmingly aggressive PR tactics. May your code be bug-free and your revenge scripts elegant.

This looks really good.... may I ask how does payments work without people having bank accounts?

You have already gotten used to loading multiple megabytes of bytes just to display a static landing page. You'll get used to this as well... just give it some time :-D

Not until you are wrongly considered "untrusted".

It is never wrong to be considered untrusted. It is only occasionally right to be considered trusted. Especially in zero-risk relationships that is the default on the anonymous internet.

Being considered neutral is different from being explicitly considered untrusted.