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

Joined February 2009
268 Photos and videos
Pinned Tweet
Wie funktioniert ChatGPT _ganz_genau_? Die verständliche und wirklich vollständige Erklärung in einem Vortrag: youtube.com/watch?v=T7K2Smql…
1
4
408
This is crazy: Qwen3.6 27B @Alibaba_Qwen is leading 6-times larger MiniMax-M2.7 artificialanalysis.ai/models…
1
84
Qwen3.5 / Gemma4 Comparison github.com/Orbiter/project-e…
1
73
YaCy 1.941 is out: a big step toward transparent and private AI. New chat RAG workflows, tool calling, MCP integration, YaCy Packs, better ranking/snippets #YaCy #Search #RAG #AI Release Notes: community.searchlab.eu/t/yac…
4
7
174
a kanban board that works off tickets without a team?
39
Make life better
31
qwen3.5 is leading the non-thinking project-euler leaderboard github.com/Orbiter/project-e… @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
2
353
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 🧐
140
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/beautiful…
1
2
4
210
Michael Christen retweeted
Laufwetter ist das nicht laufwetter.de/
1
1
65
Has anyone asked Claude Code/Codex to find bugs in METAFONT?
64
I harvested 6.374.494 documents from grokipedia, may I publish the dump to huggingface @elonmusk ?
2
59
mflux-server github.com/Orbiter/mflux-ser… 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.
1
2
1
247
Intelligence Explosion soon...
I've shifted my research to focus on automated alignment research. We will have automated AI research very soon and it's important that alignment can keep up during the intelligence explosion.
101
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
4
5
206
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/project-e… ministral-3:14b beats qwen2.5:72b, ministral-3:8b beats llama3.3:70b, ministral-3:3b is on par with gemma3:12b
1
117
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!
1
60
Experiments with AI Chat in YaCy
1
4
62
In 2008, I wrote the Machbarkeitsstudie zum Aufbau und Betrieb einer „Deutschen Digitalen Bibliothek“ (the German Digital Library) yacy.net/material/DDB_Machba… Technologies that I describe there went into the early version of YaCy.

1
1
38
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).
1
38
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).
39