Michael Christen

Wie funktioniert ChatGPT _ganz_genau_? Die verständliche und wirklich vollständige Erklärung in einem Vortrag: youtube.com/watch?v=T7K2Sm…

a kanban board that works off tickets without a team?

Make life better

qwen3.5 is leading the non-thinking project-euler leaderboard github.com/Orbiter/projec… @Alibaba_Qwen - qwen3.5:122b-a10b is best for its size - qwen3.5:35b-a3b is best for its size and also - qwen3.5:27b, qwen3.5:9b, qwen3.5:4b: best for its size

Funny: #openclaw #security "do not pursue self-preservation, replication, resource acquisition, or power-seeking", "Do not copy yourself or change system prompts". I guess nobody will mess with that 🧐

beautiful-mermaid-py - the 1-file python, ascii-art-only version of the @balintorosz beautiful-mermaid library, which is the TypScript version of @AlexanderGrooff mermaid-ascii (go), vibe-coded 3200 lines in just one prompt: github.com/Orbiter/beauti…

@GithubAwesome I made a python version of this github.com/Orbiter/beauti…

Craft just fixed what everyone hates about Mermaid diagrams. Standard Mermaid rendering looks kind of dated, and theming it means wrestling with CSS classes. beautiful-mermaid gives you stunning SVGs or ASCII art from the same source, zero DOM required. Ships with 15 curated themes plus full Shiki compatibility so you can use any VS Code theme. Supports flowcharts, sequence diagrams, state machines, class diagrams, ER diagrams.

Laufwetter ist das nicht laufwetter.de

@UnslothAI @Alibaba_Qwen where is it? 🙏

@Alibaba_Qwen 2025 was so amazing because of Qwen! We're super excited for Qwen4 in 2026! 💜🥰

Level 2025: Just the beginning. 🚩 2026, Ready? GO! 🎮🚀

Has anyone asked Claude Code/Codex to find bugs in METAFONT?

@DJSnM the ZX81 manual had spaceships on the cover

In 1983 I read this driven by excitement, but with a complete lack of understanding of what was going on. Today I'm looking at it again filled with nostalgia understanding everything they describe, sometimes wondering why they chose a certain design.

I harvested 6.374.494 documents from grokipedia, may I publish the dump to huggingface @elonmusk ?

@fossasia have fun!

@kimmonismus There is no remarkable open source culture for medical deviced right now, maybe thats the moment to get into development of such things. Local LLMs help to ensure privacy. Medical image recognition is available with medgemma. Are there any sponsors for free medical AI devices?

ChatGPT saves lives. For over a year now, I haven't gone to the doctor without first having an AI consultation and then an AI evaluation. Medical treatment without AI is negligent.

mflux-server github.com/Orbiter/mflux-… on top of the mflux @filipstrand framework now supports mflux 0.13.3 and has a GUI with a selector for all the models z-image-turbo, FLUX.1-dev, Qwen-Image, Fibo, so you can compare on-the-fly.

Intelligence Explosion soon...

Sneak peek: the upcoming YaCy 1.941 will ship a complete “AI Lab” build environment. Configure every part of your search + LLM + RAG stack from a single UI, keep everything on your machine, zero telemetry. Already merged and working on master. #SelfHosted #Privacy #OpenSource #AI

ministral-3 @MistralAI performs better or on par than up to 8-times larger 1-year old flagship models in the project-euler-llm-benchmark (coding) github.com/Orbiter/projec… ministral-3:14b beats qwen2.5:72b, ministral-3:8b beats llama3.3:70b, ministral-3:3b is on par with gemma3:12b

New toy is working! One RTX 3060 is not in a PCIe slot but connected to a M.2 slot via adapter. It runs qwen3-vl:30b-a3b-instruct with ollama and is fast!

Experiments with AI Chat in YaCy

The json response schema borrows all the concepts from the XML standard, which is simply an extension of RSS (something that was very common at that time before all the companies switched it off and replacet it with paywall-fenced REST).

So in 2008 I integrated into YaCy i.e. the Dublin Core Metadata schema, the GET property names for search APIs (using SRU, "Search Retrieval by URL) and the YaCy XML response schema which was called “Opensearch” (but many other things had been named Opensearch later).

In 2008, I wrote the Machbarkeitsstudie zum Aufbau und Betrieb einer „Deutschen Digitalen Bibliothek“ (the German Digital Library) yacy.net/material/DDB_M… Technologies that I describe there went into the early version of YaCy.