I planed to make something like this as a skill for my self, but pasting this into any agent chat works like a charm. I just had my local model (Qwen3.6 27B / pi) make a list of all the required standards an older hugo site of mine was missing, make a todo list and then run through the whole thing one by one, giving me chance to review each change.

It even made the missing favicon by cropping out the symbol from the logo, and it looks good!

Context: I have a $20 Claude Code subscription, and have used it for a handfull of small-ish projects the last year, in parallel with local models on my AMD 9700XTX (24GB) at home. Mostly Ministral 14B and more recently Qwen3.6 27B Dense 4q.

Historically, the tooling (interferens engines and harness) has been the biggest challenge when using local models, a lot of the benefits from Claude Code was a rather unified and well oiled agent system. Local setups often bring with them sutle incompatibilities between models, inference engines and agent systems that are not obvious from initial testing, but cause trouble on projects larger than a couple of files.

The Spark setup at work is now at a point where I do not miss Claude, like at all. A big part of this is the harness and the tools available to the agent, most critically a good tool for searching online. I use my Kagi subscription to allow the models to fetch up-to-date information, and the Kagi MCP I use also has a summarizer which is very helpful in avoiding rapidly filling up the context window.

I mostly use Zed and it's native agent, which only recently got muuuch better, and on the terminal I use Pi with a minimal selection of extensions (currently pi-kagi-search, pi-smart-fetch, pi-btw and pi-diffloop). I also have Pi in Zed via the ACP, but it does not work so well with some of the extensions, especially the lack of a built-in permission system is a problem, when YOLO-mode is the only mode :)

Honestly, as long as you have a model that is decent at tool calling, your good. Having a solid and stable frame around your model makes a huge difference. The only caveat in all of this is that I spend most of my time on smaller projects and debugging on linux base systems, not huge and complex code bases, so your mileage might vary.

The next phase at work is to set up a chatGPT-like webinterface, and so far LibreChat is at the top of my shortlist. We had OpenWebUI for a while, but it is so bad at using MCP tools that it is practically non-functional for us. LibreChat is a bit more work to set up, but the interface and it's MCP story is much more solid. The goal is to plug in our internal helpdesk, docs and task manager system to LibreChat via MCPs to give us a quick way to query and gather information that is currently very time consuming to do on your own.

This works for us and will work for years to come. It is not SOTA, but it works darn well for our purposes, and we control the compute and data flowing through it, so totally worth it.

Come to think of it, this could be a nice model to have as the first pass in a more complex agent system where Needle hands of the results of a tool call to a larger model.

I will defiantly play around with this!

It is incredible how far you get with a single HTML-file, containing styles and JS, when building dashboards, small apps and other utilities that can interact with an API or otherwise fetch data from somwhere.

I just drop it on my personal ~ folder on the shared server at work and voilà, everyone can check it out and use it immediately!

hefenricæs = himmelrikes (no)

uerc = werk (nl)

eci = evig (no) / eeuwig (nl)

ærist = eerst (nl)

barnum = barn (no)

sceppend = schepper (nl)

EDIT: Hearing the poem read also gives dutch / germanic vibes: https://gutenberg.org/files/19677/ogg/19677.ogg

They are also super fun to drive and, although they have small batteries, the can charge at 40-50kWh, which translates to 10 minutes to ~85% full. We have used a eUP 2013 model to travel across europe (~900km) in two days, many times! One charge last between one and two hours, depending on speed and weather. We usually cruse at about 90km/h, and the car is basically sipping electrons! The newer model have double the range, but I have not owned or testet them, but might be a decent compromise for longer travels.

  services:
    llama:
      image: ghcr.io/ggml-org/llama.cpp:server-vulkan
      container_name: llama-qwen3.6-27b-dense
      ports:
        - 4201:8080
      volumes:
        - ./Qwen3.6-27B-Q4_K_M.gguf:/models/model.gguf:ro,z
        - ./mmproj-BF16.gguf:/models/mmproj.gguf:ro,z
      devices:
        - /dev/dri
      group_add:
        - video
      command: >
        -m /models/model.gguf
        --mmproj /models/mmproj.gguf
        --alias "Qwen3.6 27b Dense"
        -ngl 99
        -c 98304
        -b 2048
        --host 0.0.0.0
        --port 8080
        --parallel 2
        --kv-unified
        --ubatch-size 2048
        --flash-attn on
        -cb
        --jinja
        --no-webui
        -ctk q8_0
        -ctv q8_0
        --image-min-tokens 1024
        --temp 0.6
        --top-k 20
        --top-p 0.95
        --repeat-penalty 1
        --presence-penalty 1.5
        --reasoning auto
      restart: unless-stopped

The original kind was genuinely connecting people and adding value. The current one is in effect isolating and driving people and groups apart.

Luckily, the original kind did not vanish. I find a lot of joy hanging out on the fediverse. I spend far less time on it than what I did on Twitter of FB back when I still had accounts there, but that is a good sign.

Social media is too generous term to use when describing products from Meta, TikTok, Snap, X etc. It is an ad platform that also, occasionality, shows you what your friends are up to.

We should come up with a better term than 'social media' when describing platforms that has reached the last stage of enshitification.

The goal is not instant world domination, but a organically grown network, providing an off-ramp for those that have had enough and are ready to take some action. Facilitating real world meet-ups would help, I think!