Michael Christen (@orbiterlab) 's Twitter Profile
Michael Christen

@orbiterlab

Open Source and Search Engine Developer, AI Research, Maintainer of YaCy.net, laufwetter.de and Searchlab.eu
Also on sigmoid.social/@orbiterlab

ID: 21938231

linkhttps://github.com/orbiter/ calendar_today25-02-2009 23:48:57

1,1K Tweet

638 Followers

316 Following

FOSSASIA (@fossasia) 's Twitter Profile Photo

Get hands-on with self-hosted LLMs and learn how to build powerful LLM agents tailored to your needs — from setup to real-world deployment with Michael Christen at #FOSSASIASummit2025 🔗 Click here youtu.be/-9ubB1jzBYE?si… to watch on the FOSSASIA YouTube channel #LLM #AIagents

Get hands-on with self-hosted LLMs and learn how to build powerful LLM agents tailored to your needs — from setup to real-world deployment with <a href="/orbiterlab/">Michael Christen</a> at #FOSSASIASummit2025

🔗 Click here youtu.be/-9ubB1jzBYE?si… to watch on the FOSSASIA YouTube channel

#LLM #AIagents
Michael Christen (@orbiterlab) 's Twitter Profile Photo

LLM Model Release Map (red: ChatGPT-3.5-class, blue: GPT-4-class models; guessed). Current progress is about five new major models every month!

LLM Model Release Map (red: ChatGPT-3.5-class, blue: GPT-4-class models; guessed). Current progress is about five new major models every month!
Michael Christen (@orbiterlab) 's Twitter Profile Photo

Vortrag: "Superhuman AI - Wie und wann ist KI nützlich" Wie übermenschlich muss Künstliche Intelligenz sein, um unseren Alltag zu verändern? Dieser Vortrag zeigt, dass wir übermenschlichen Super-KI teilweise bereits nutzen können. youtube.com/watch?v=sk6Afs…

Michael Christen (@orbiterlab) 's Twitter Profile Photo

The Project Euler Benchmark (test how good LLMs perform at code generation) has now a nice graph to show which problems (out of 1..200) can be solved: purple = in all 4 languages (python, java, rust, clojure), blue = in 3, green = in 2, yellow = in 1. github.com/Orbiter/projec…

The Project Euler Benchmark (test how good LLMs perform at code generation) has now a nice graph to show which problems (out of 1..200) can be solved: purple = in all 4 languages (python, java, rust, clojure), blue = in 3, green = in 2, yellow = in 1. github.com/Orbiter/projec…
Michael Christen (@orbiterlab) 's Twitter Profile Photo

Can someone make an #AI that composes and plays #music live that gets more and more dramatic while I do #programming and produce code? It should run only locally because it would require to read what I am doing.

Michael Christen (@orbiterlab) 's Twitter Profile Photo

AI Done Right! YaCy is the idea that we don't surrender control: p2p search built on openness, autonomy, and trust. Now, as AI becomes the next layer of our digital world, the same principles must hold true. "AI Done Right" - in YaCy -> patreon.com/posts/ai-done-…

AI Done Right!

YaCy is the idea that we don't surrender control: p2p search built on openness, autonomy, and trust.

Now, as AI becomes the next layer of our digital world, the same principles must hold true.

"AI Done Right" - in YaCy -&gt;
patreon.com/posts/ai-done-…
Michael Christen (@orbiterlab) 's Twitter Profile Photo

Open Data in KI nutzen / Workshop für lokale LLMs mit RAG Schritt für Schritt die OpenAI-API auf der Kommandozeile kennen lernen. (repost mit besserem Ton/kürzerem Schnitt von den Chemnitzer Linuxtagen 2025) youtu.be/YU-aUtzrg_Y

Open Data in KI nutzen /
Workshop für lokale LLMs mit RAG
Schritt für Schritt die OpenAI-API auf der Kommandozeile kennen lernen.

(repost mit besserem Ton/kürzerem Schnitt von den Chemnitzer Linuxtagen 2025)
youtu.be/YU-aUtzrg_Y
Michael Christen (@orbiterlab) 's Twitter Profile Photo

Excellent article on running YaCy #DecentralizedSearch #WebScraping in a professional, secure, and scalable way for web scraping and data extraction: scrapingant.com/blog/decentral… It covers everything needed for serious deployments.

Michael Christen (@orbiterlab) 's Twitter Profile Photo

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!

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!
Michael Christen (@orbiterlab) 's Twitter Profile Photo

ministral-3 Mistral AI 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

Michael Christen (@orbiterlab) 's Twitter Profile Photo

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

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