Kostic

Sure but that holds true for most new tech. Expensive and slow but it can only get better or stay the same. I'm thinking it's only going to get better.

Your video is showing Kimi 2.6, not 3? Once the weights are released, there might be providers that serve it without the censorship filter.

A very beautiful website and a machine. Oxide folks should be proud, you can see the love that went into it.

Time to copy&improve the niche solution.

70% of the Steam users have a PC that's weaker than the Steam Machine[0]. These things will sell out, that's not the issue. The issue is that Valve probably won't have enough power to secure hardware deals to fulfill all the orders, thus limiting the growth of their hardware side.

[0] https://www.techpowerup.com/342970/valve-claims-steam-machin...

Auth with Github Copilot and then point it to localhost[0]. Hopefully the auth to Copilot requirement will be dropped for local models at some point. Would love to use a fully open stack (VSCodium and everything) in the future. My config:

``` [ { "name": "http://127.0.0.1:8888/v1", "vendor": "customendpoint", "apiKey": "llama.cpp", "models": [ { "id": "gemma4-31b", "name": "Gemma 4 31B", "url": "http://127.0.0.1:8888/v1/chat/completions", "toolCalling": true, "vision": true, "maxInputTokens": 65536, "maxOutputTokens": 8192 }, { "id": "qwen3.6-27b", "name": "Qwen 3.6 27B", "url": "http://127.0.0.1:8888/v1/chat/completions", "toolCalling": true, "vision": true, "maxInputTokens": 180224, "maxOutputTokens": 8192 } ] } ] ```

[0] https://code.visualstudio.com/blogs/2025/10/22/bring-your-ow...

For personal needs I connected VSCode with llama.cpp running Qwen 3.6 27B or Gemma 4 31B and it's good enough to cancel my cloud subscription.

Qwen running on my 1st GPU at q4@176k context from 70 to 50 tok/s with MTP, pretty good for coding.

Gemma on the other hand is using both GPUs, running q8@64k context, doing document sentiment analysis, summarization, proofreading and translating, at consistent 25 tok/s. Somewhat slow but usable for batched workflows. Might get some more once llama.cpp starts supporting MTP with tensor split mode.

Still using frontier LLMs at dayjob since I'm not paying it and those are obviously better. Hopefully we'll have a Sonnet 4.6/Opus 4.5 level 30B model in a year or so.

EDIT: Prompt processing starts from 800 t/s and drops to 400 t/s. In most cases my starting prompts are around 16k-24k of tokens and require from 60 to 90 seconds to be processed. Not great but acceptable.

"I'm sorry" is not gaslighting but an admission of fault it learned from our texts. And if an LLM managed to delete your database, it's time to slow down the vibe train and put up some guard rails.

LLMs are awesome but not without supervision.

Taalas showed that you could make LLMs faster by turning them into ASICs and get 10k+ token generation. It's a matter of time now.

For now. These will be pretty cool Linux machines if Asahi starts supporting them at some point.

I would not go below q8 if comparing to sonnet.

I assume you're living in a city. You're already renting out a lot of things to others (security, electricity, water, food, shelter, transportation), what is different with white collar work?

At least with GitHub it's hard to hide when you get "no healthy upstream" on a git push.

I don't understand how you can ship a car without proper papers out of the country so easily. Maybe focus on that first?

Agentic editing is really nice. If on VSCode, Cline works well with Ollama.

This would be true if not for open-weights (and even some open source) LLMs that exist today. Not everything should be done for profit.

I'm spending fair amount of money on helping teachers and professors in Serbia who had their pay reduced to to absurdity because they are supporting their students in demands for justice in the case of Novi Sad canopy collapse[0].

[0] https://en.m.wikipedia.org/wiki/Novi_Sad_railway_station_can...

It's relevant from an engineering perspective. They have a way to develop a new model in months now.

I've stopped using search engines actively 18 months ago. My first stop is an LLM. Once I understand what I actually need, I do a web search to go to the product/tool website. I do this not because LLMs are that good but because web search result quality went way down in the same period.

One interesting trend that I like is that I started using local LLMs way more in the last couple of months. They are good enough that I was able to cancel my personal ChatGPT subscription. Still using ChatGPT on the work machines since the company is paying it.

This happened during 15 minutes of silence for 15 persons that died in the collapse. Everyone was silent and mourning.

That's a blatant lie. We are protesting because 15 people died in Novi Sad because of corruption, 4 months ago. We want justice.

If there's potential military use and you don't build it, you risk your adversary doing that.

If life is only hedonism to you, then sure. It would be a waste.

On a long-enough scale, this planet will die anyways. Let's first try to expand life and unlock the secrets of the Universe, as much as possible.

Chernozem.

Would starvation be a problem? Don't most countries have food reserves for these cases? At least enough food for one season?

Hopefully just EU and not the European countries outside of EU.

Default Ubuntu is still pretty good. I have been using the default Fedora Workstation for almost a decade and it works great for me. I also don't spend time on tweaking it anymore (used to be the complete opposite). The defaults work, I concentrate on my work, side projects and games.

Really like that. Just add easy versioning and some tags and we're good to go.

Just after I moved my Cloudflare task to `in progress`.

Folks who manage their Cloudflare stuff via Terraform, are you able to make changes? Or does this mean that their API is also down?