Viewing profile — proxysna

Really hoped to see their hw out in the wild one day

You can run it on a anything. Now officially. About a year back i had proxmox cluster on 3 orange pi 5+. As long as you have a some sort of Debian it's pretty seamless.

> My primary concern is the risk that authoritarian governments—not solely the Chinese Communist Party (CCP), although the CCP is clearly the most capable threat—build AI models th…

Never used HyperCard, but from descriptions and screenshots in the article reminds me a lot of Delphi/Pascal/Lazarus IDE’s. Appeal is understandable, because it is so cool to be sn…

Deploying and building OpenTTD if my favourite exercise when i am trying to learn new CI tool or orchestrator or packaging format. Simple enough, yet fun.

Nice. Thanks for the insight!

I've been using deepseek for some development at home and it is really good for the price. It is at the point where i am ok with using it as a tool that i can rely on and not an ex…

I'd would assume that this is not a monolithic cluster of 40k vm's but at least tens of clusters. Which puts it in the realm of capabilities of Proxmox.

Great time to migrate off VMware. All the migration paths are well-trodden by now, but goddamn 40k vm's. A lot of work ahead.

Alpine is my go-to nowadays for everything in my homelab except desktop (I use Void btw), because of how dirty the setup to make GPU's work with musl kernel.

Looks really nice, but 10 fps in Firefox.

It's just a DGX spark with faster memory and a windows boot?

There is a docker registry under the same name. https://zotregistry.dev

I think hashicorp still have an implementation for vaults seal/unseal process. Unless something changed ofc

Feels about right. I've launched an internal demo of Claude Code and Deepseek on the same day and we burned through our monthly allowance for Claude in just over a week, with more …

“Expert” that does not know what a Terraform is. lol, lmao even

Cool, i am mostly a plumber for these things, but do you have any sort of reading that i can go through to wrap my head around it to some degree?

I've used only Qwen3.5 so far for work and was, after initial struggles, successful with GPU setup, no mlx. Ngl the fact that they are using `presence_penalty: 0` and no `max_token…

You need to set sampling parameters for the llm. Had the same issue with Qwen3.5 when i first started. You can grab them off the model card page usually. From Qwen3.6 page: Thinkin…

OpenWebUI with postgres and vllm for inference, searxng for websearch a few other mcp's for tools.

This is from an example from my Nomad cluster with two a5000's, which is a bit different what i have at work, but it will mostly apply to most modern 24G vram nvidia gpu. "--tensor…

We do make Claude and Mistral available to our developers too. But, like you said, security. I, personally, do not understand how people in tech, put any amount of trust in busines…

Qwen3.5-27B with a 4bit quant can be run on a 24G card with no problem. With 2 Nvidia L4 cards and some additional vllm flags, i am serving 10 developers at 20-25tok/sek, off-peak …

Yeah, my thought exactly, execution lacked, but i do admire the attempt.

What a great write up, and a video too! Even though Minecraft stuff ofc was a bit of a bait, it would be interesting see the answer to "Can it run Doom?".