Nostr notes by Michael Christen / YaCy Search

gpt-6.1-sol-think saturates PE-Bench-200-Java from ...

2026-10-18T12:28:50Z

gpt-6.1-sol-think saturates PE-Bench-200-Java from https://github.com/Orbiter/project-euler-llm-benchmark : Python 99%, JavaScript 99.5%, Java 100%, Rust 99%, Clojure 87%. The first model in this benchmark to solve all of Project Euler’s first 200 problems from https://projecteuler.net/

vcoding useless? game 4 YaCy... ...

2026-09-25T14:39:48Z

vcoding useless? game 4 YaCy...

mflux-server #image #generation for #mac with support for ...

2026-09-22T16:54:07Z

mflux-server #image #generation for #mac with support for qwen-image-2.1 using mflux 0.20.0 https://github.com/Orbiter/mflux-server
Start the server with
./run.sh --model qwen-image-2.1
Example below uses image editing of the #YaCy logo

mflux-server 0.19.2 https://github.com/Orbiter/mflux-server ...

2026-09-20T11:50:00Z

mflux-server 0.19.2 https://github.com/Orbiter/mflux-server #imagegeneration #mflux #server

The new YaCyStats! https://new.yacystats.de/ ...

2026-09-02T17:42:54Z

The new YaCyStats!
https://new.yacystats.de/

ich habe meinen Mitschnitt hochgeladen ...

2026-08-20T19:58:18Z

In reply to nevent1q…98sm
_________________________

ich habe meinen Mitschnitt hochgeladen https://sigmoid.social/@orbiterlab/117129599447071900

quoting
note1wtg…a05v

FrOSCon 2026: Baue deine eigenen KI-Agenten mit lokalen LLMs

Mitschnitt vom Workshop zu den KI-Agenten-Tools aus https://github.com/Orbiter/cognitive-utilities

https://www.youtube.com/watch?v=oJ2JXCQTRUk

Wenn ihr wissen wollt wie man mit kleinen Scripten LLMs abfragt, Ergebnisse programmatisch auswerten kann, Linux-typische kognitive Filter baut und auch 1-Script Coding Agents schreibt und eine Stunde Zeit übrig habt...

FrOSCon 2026: Baue deine eigenen KI-Agenten mit lokalen LLMs ...

2026-08-20T19:57:30Z

FrOSCon 2026: Baue deine eigenen KI-Agenten mit lokalen LLMs

Mitschnitt vom Workshop zu den KI-Agenten-Tools aus https://github.com/Orbiter/cognitive-utilities

https://www.youtube.com/watch?v=oJ2JXCQTRUk

Wenn ihr wissen wollt wie man mit kleinen Scripten LLMs abfragt, Ergebnisse programmatisch auswerten kann, Linux-typische kognitive Filter baut und auch 1-Script Coding Agents schreibt und eine Stunde Zeit übrig habt...

stl looks great ...

2026-08-02T20:59:49Z

In reply to nevent1q…sud5
_________________________

stl looks great

Do you know SketchForge? This is a free/open Tinkercad clone that ...

2026-08-02T18:06:01Z

Do you know SketchForge? This is a free/open Tinkercad clone that runs on your own computer. It has a MCP server inside, I attached it to codex and prompted "create a house with garden and a car in front". This is amazing! https://sketchforge3d.com/

without moving to Jetty 12, we are stuck with Solr 9. So it has ...

2026-07-14T07:00:46Z

In reply to nevent1q…v9st
_________________________

without moving to Jetty 12, we are stuck with Solr 9. So it has to be done.

This weekend I did major work deep down in the basement of YaCy: ...

2026-07-12T15:27:26Z

This weekend I did major work deep down in the basement of YaCy: I replaced Jetty 9 with Jetty 12. Very exciting! Really, this was hard work. And it will enable to move to Solr 10, once we want to use JDK 21.

I thought it's time to freshen up the use case images after ...

2026-07-10T17:52:24Z

I thought it's time to freshen up the use case images after 20-some years - https://yacy.net gets a new look

YaCy has now a complete interface translation for German, French, ...

2026-07-09T16:46:31Z

YaCy has now a complete interface translation for German, French, Spanish, Italian, Greek, Slovak, Ukrainian, Turkish, Russian, Polish, Chinese, Hindi, Japanese, and Korean.

https://github.com/yacy/yacy_search_server/commit/57d188e69a17788ff78fd1b9ad1afa2b232f6536
https://github.com/yacy/yacy_search_server/commit/55956c502b00274edc99888c42a21e2985928fff

I was planning to make Tutorials but I could not find time and my ...

2026-06-27T11:33:45Z

In reply to nevent1q…lvec
_________________________

I was planning to make Tutorials but I could not find time and my english is not that shiny. Lets see.

yeah, I have a heap of RPi 4 and RPi 3, what should I do with ...

2026-06-21T21:27:29Z

In reply to nevent1q…ews3
_________________________

yeah, I have a heap of RPi 4 and RPi 3, what should I do with them?

ein RPi 5 16GB, ein RPi4 8GB, zwei RPi 4 4GB. 16 Cores, 32GB Ram. ...

2026-06-21T21:16:56Z

In reply to nevent1q…zgnq
_________________________

ein RPi 5 16GB, ein RPi4 8GB, zwei RPi 4 4GB. 16 Cores, 32GB Ram. Und ein Mini-Switch.

hatte ich alles rumliegen

2026-06-21T20:55:51Z

In reply to nevent1q…6kjt
_________________________

hatte ich alles rumliegen

preis?

2026-06-21T19:15:12Z

In reply to nevent1q…j003
_________________________

preis?

Cyberdeck?? Cyberserver!! ...

2026-06-21T17:43:16Z

Cyberdeck?? Cyberserver!!

YaCy Skill for OpenClaw Control and manage a local YaCy search ...

2026-04-05T20:28:29Z

YaCy Skill for OpenClaw

Control and manage a local YaCy search engine instance with OpenClaw.

https://github.com/openclaw/skills/tree/main/skills/qsmtco/yacy

KI Chat in YaCy - Vortrag von den Chemnitzer Linuxtagen ...

2026-03-29T14:49:15Z

KI Chat in YaCy - Vortrag von den Chemnitzer Linuxtagen https://media.ccc.de/v/clt26-322-ki-chat-mit-eigener-suchmaschine-rag-in-yacy

YaCy 1.941 is out: a big step toward transparent and private AI. ...

2026-03-29T10:05:53Z

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: https://community.searchlab.eu/t/yacy-release-1-941-the-ai-release/3376

it made itself

2026-03-20T16:44:10Z

In reply to nevent1q…kw3k
_________________________

it made itself

a kanban board that works off tickets itself? ...

2026-03-20T15:02:26Z

a kanban board that works off tickets itself?

yes, a command shell

2026-03-12T10:38:33Z

In reply to nevent1q…m2ny
_________________________

yes, a command shell

I understand the phrase could smell like this. However I am ...

2026-03-12T10:27:50Z

In reply to nevent1q…9fvg
_________________________

I understand the phrase could smell like this. However I am optimistic overall and like to believe in a paradise utopia supported and build with free software. We want to create usefull tools and maybe we should stop to offer technical terms as benefit of libraries, instead show what could be an outcome that is good for everyone, not just nerds.

the one that gives you superpower

2026-03-12T09:09:03Z

In reply to nevent1q…yu2d
_________________________

the one that gives you superpower

with free software

2026-03-12T09:06:01Z

In reply to nevent1q…3vu2
_________________________

with free software

Nostr event nevent1qqsrag6scu6fs24ajxa6ee4vfec0c59d3u4u26ruzau28mwutaf2f0gzypjjwdncatcmkx5w38dsyxcrg4s9ztdtmpnk4hlxxzjxpdfpqlr9vkjnjvv

2026-03-12T08:46:13Z

Make Life Better

Funny: #openclaw #security "do not pursue self-preservation, ...

2026-02-17T10:23:45Z

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 🧐

YaCy Vortrag bei den Chemnitzer Linuxtagen ...

2026-02-03T17:26:05Z

YaCy Vortrag bei den Chemnitzer Linuxtagen [@clt_news](https://mastodon.social/@clt_news ) : "KI Chat mit eigener Suchmaschine: RAG in YaCy" - Das "KI Release" ist zwar noch nicht fertig, aber wir werden dann unseren eigenen KI Chat zeigen... https://chemnitzer.linux-tage.de/2026/de/programm/beitrag/322

beautiful-mermaid-py - the 1-file python, ascii-art-only version ...

2026-02-01T17:18:24Z

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

mflux-server https://github.com/Orbiter/mflux-server on top of ...

2025-12-22T12:29:32Z

mflux-server https://github.com/Orbiter/mflux-server on top of the mflux 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.

Welchen der vier folgenden Vortragstitel soll ich für die ...

2025-12-21T11:56:47Z

Welchen der vier folgenden Vortragstitel soll ich für die Chemnitzer Linuxtage 2026 einreichen?
•⁠ ⁠Lokale Multimodale KI zur Erzeugung synthetischer Massendaten: Praktische Werkzeuge für hochwertige Datensätze
•⁠ ⁠KI mit Edge-Computing: Datenhoheit durch lokal betriebene LLMs in mini Cluster
•⁠ ⁠Systemadministration mit KI: Automatisierung von Linux-Tasks mit lokalen LLMs – sichere, eigenständige Workflows
•⁠ ⁠KI mit LoRA: Lokales Fine-Tuning von LLMs für datenschutzkonforme Anwendungen

10€

2025-12-18T21:08:53Z

In reply to nevent1q…w4z4
_________________________

10€

der m.2 adapter ist billig

2025-12-14T09:39:56Z

In reply to nevent1q…uxhx
_________________________

der m.2 adapter ist billig

I made pre-defined adapters for Ollama, LMStudio, OpenAI and ...

2025-12-06T18:52:38Z

In reply to nevent1q…6tz8
_________________________

I made pre-defined adapters for Ollama, LMStudio, OpenAI and OpenRouter but you can attach anything that speaks the OpenAI API. But... we meanwhile have a full transformer in java in YaCy, it's just not ready yet but will be another option (and its not fast and can only load llama3.2:1b for now). I am also thinking about the option to share your local LLM over the p2p network, so using a "any peer" option might be there in the future.

Sneak peek: the upcoming YaCy 1.941 will ship a complete “AI ...

2025-12-06T18:38:55Z

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. Chat interface included, it's the first AI tool to try out in YaCy. Already working on master. Check out your YaCy dev system and open /AILab.html #SelfHosted #Privacy #OpenSource #AI

Ministral-3 (@MistralAI) performs better than, or on par with, ...

2025-12-05T11:21:29Z

Ministral-3 (@MistralAI) performs better than, or on par with, flagship models up to 8 times larger (from just one year ago) on the Project Euler LLM Benchmark (coding):
https://github.com/Orbiter/project-euler-llm-benchmark
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 ...

2025-12-04T14:14:11Z

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 ...

2025-11-25T13:59:00Z

Experiments with AI Chat in YaCy

A lot of technical details from this paper went into the early ...

2025-11-19T13:17:30Z

In reply to nevent1q…uem7
_________________________

A lot of technical details from this paper went into the early version of YaCy in 2008, 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). The json response schema borrows all the concepts from the XML standard, which is simply an extension of RSS.

In 2008, I wrote the Machbarkeitsstudie zum Aufbau und Betrieb ...

2025-11-19T13:16:57Z

In 2008, I wrote the Machbarkeitsstudie
zum Aufbau und Betrieb einer
„Deutschen Digitalen Bibliothek“ (the German Digital Library)

Here is a thread in the YaCy forum about a request for "Semantic Web" and related technologies.

https://community.searchlab.eu/t/can-or-could-yacy-do-conceptual-indexing-or-be-the-search-engine-for-the-semantic-web/70/26?u=orbiter

It also contains a link to the original paper.

Excellent article on running YaCy #DecentralizedSearch ...

2025-11-18T21:01:36Z

Excellent article on running YaCy #DecentralizedSearch #WebScraping in a professional, secure, and scalable way for web scraping and data extraction:

https://scrapingant.com/blog/decentralized-web-scraping-data-extraction-yacy

It covers private/Robinson setups with WireGuard, public-edge reverse proxies (Caddy), container hardening (NIST SP 800-190), crawl profiles, index lifecycle management, performance tuning, and monitoring, JVM/IO tuning, SLOs, ethical scraping, sitemaps-first — everything needed for serious deployments.

Open Data in KI nutzen / Workshop für lokale LLMs mit RAG ...

2025-11-15T13:44:29Z

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)
https://youtu.be/YU-aUtzrg_Y

After many years attending the congress I will have family time ...

2025-11-15T12:13:16Z

In reply to nevent1q…s42w
_________________________

After many years attending the congress I will have family time this year, so I'm not there this year. But a YaCy meet-up is a fantastic idea and you can meet Marc [@m2c_n3e](https://mastodon.xyz/@m2c_n3e ) most probably at the #fossasia table and chat with him about YaCy. I hope that my AI pieces I am working on made it into YaCy until end of december so we can have a chat about it together i.e. with jitsi.

I know that many people reject AI-enriched answers and other ...

2025-11-09T17:16:10Z

In reply to nevent1q…tegw
_________________________

I know that many people reject AI-enriched answers and other services. All of that is optional. You can switch it on if you want to have it, you don't need to do that. YaCy will continue to work without AI.

The "smell" the models have is related to the specific model. You can choose your own. They will improve over time.

Yes, to have the AI functions, you need a (local - good!) provider, which can be ollama or LMStudio. Other options are any OpenAI-compatible APIs.

AI Done Right! YaCy is the idea that we don't surrender ...

2025-11-09T13:51:08Z

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 ->
https://www.patreon.com/posts/ai-done-right-143053426

maybe this is a break in the coding adventure journey that could ...

2025-10-22T20:39:39Z

In reply to nevent1q…mhft
_________________________

maybe this is a break in the coding adventure journey that could be filled with "elevator music" or some chiptunes.

Can someone make an #AI that composes and plays #music live that ...

2025-10-22T13:25:10Z

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.

The Project Euler Benchmark (test how good LLMs perform at code ...

2025-10-15T21:43:47Z

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. https://github.com/Orbiter/project-euler-llm-benchmark/blob/main/README.md

most functions are now implemented: pack generation, pack ...

2025-08-22T00:22:52Z

In reply to nevent1q…chxc
_________________________

most functions are now implemented: pack generation, pack download and pack management servlets are ready, a demo pack exists at huggingface and the pack downloader can find and download that pack from huggingface. All datasets at hf with name ' YaCy-Pack' will appear automatically at the downloader servlet. A detailed documentation will be made but is not ready yet.

my impression was that a global index over the fediverse is not ...

2025-08-11T23:41:18Z

In reply to nevent1q…zk9u
_________________________

my impression was that a global index over the fediverse is not wanted

We have a YaCy Pack Process Workflow: packs can be added or ...

2025-08-02T05:54:43Z

We have a YaCy Pack Process Workflow: packs can be added or removed from the search index and therefore are usable both as whitelist and blacklist.

A first demo pack is now available at https://yacy.net/packs/ and ...

2025-08-01T17:30:46Z

In reply to nevent1q…chxc
_________________________

A first demo pack is now available at https://yacy.net/packs/ and such packs can be imported in YaCy by placing them into DATA/PACKS/load (only with latest YaCy from yesterday). We will provide a more convenient way as well. Pack download locations can be also elsewhere, at huggingface etc.

Idea: YaCy data packs - an alternative to web crawling to fill up ...

2025-07-24T04:03:57Z

Idea: YaCy data packs - an alternative to web crawling to fill up your search index with pre-packaged well-curated search packages. You could mix and merge those. Everyone could create them. What do you think?

Vortrag: "Superhuman AI - Wie und wann ist KI nützlich" ...

2025-06-29T14:11:43Z

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.

https://www.youtube.com/watch?v=sk6AfsF9QlM

every peer published itself every two minutes to a some (say 10, ...

2025-06-22T15:33:12Z

In reply to nevent1q…788r
_________________________

every peer published itself every two minutes to a some (say 10, cant remember niw exactly) random other peers. Those return another small number of peers they have seen recently. That distributes peer changes very quickly.

New docker release for YaCy - after 8 months (sorry) after a ...

2025-06-22T14:38:07Z

New docker release for YaCy - after 8 months (sorry) after a failure of the old release mechanism. Also: new images are now about 400MB instead of 1.3-2GB because of enhanced packaging. And they are multi-arch!

With docker you can run YaCy simply with:
docker run -d -p 8090:8090 yacy/yacy_search_server:latest

LLM Model Release Map (red: ChatGPT-3.5-class, blue: GPT-4-class ...

2025-06-16T18:06:17Z

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!

Wie funktioniert ChatGPT _ganz_genau_? Die verständliche und ...

2025-04-22T12:18:26Z

Wie funktioniert ChatGPT _ganz_genau_? Die verständliche und wirklich vollständige Erklärung in einem Vortrag: https://www.youtube.com/watch?v=T7K2SmqlzOI

slightly off-topic - I made a thing: ...

2025-04-12T16:01:02Z

slightly off-topic - I made a thing:
https://www.thingiverse.com/thing:7007980
Pick and Click Bit Rack Reversed

Video vom Vortrag "Open Data in KI nutzen" von den ...

2025-03-23T14:39:51Z

Video vom Vortrag
"Open Data in KI nutzen"
von den Chemnitzer Linuxtagen 2025 [@clt_news](https://mastodon.social/@clt_news ) https://media.ccc.de/v/clt25-269-open-datafreie-daten-in-ki-chatbots-nutzen#t=559

Folien vom Vortrag "Superhuman AI - Wie und wann ist KI ...

2025-03-23T13:56:40Z

Folien vom Vortrag
"Superhuman AI - Wie und wann ist KI nützlich"
bei den [@clt_news](https://mastodon.social/@clt_news ) Chemnitzer Linuxtagen 2025 https://yacy.net/material/20250322_CLT2025_Superhuman_AI_Wie_und_wann_ist_KI_nuetzlich.pdf

Today, 14:30 (+07) at #FOSSASIA Bangkok: "The Complete ...

2025-03-13T01:50:57Z

Today, 14:30 (+07) at #FOSSASIA Bangkok:
"The Complete Anatomy of ChatGPT: A Precise Breakdown of LLMs and Transformers"
Tune in live at
https://eventyay.com/e/4c0e0c27/session/9472
Slides can be downloaded from
https://yacy.net/material/20250313_FOSSASIA_2025_The_Complete_Anatomy_of_ChatGPT.pdf

its Solr, it always takes all the given RAM, thats what it does ...

2025-02-22T16:34:20Z

In reply to nevent1q…ahrs
_________________________

its Solr, it always takes all the given RAM, thats what it does to be efficient.

DietPi (lightweight Debian OS for SBCs) comes with #yacy ...

2025-02-15T11:06:24Z

DietPi (lightweight Debian OS for SBCs) comes with #yacy https://dietpi.com/docs/software/distributed_projects/

Mit #YaCy auf den #CLT2025 / Chemnitzer Linuxtage - Blog Post von ...

2025-02-14T15:46:57Z

Mit #YaCy auf den #CLT2025 / Chemnitzer Linuxtage - Blog Post von Frank:
https://do3eet.pages.dev/post/clt2025yacy/

New #LLM "PE-Bench" benchmark results for coding, incl. ...

2025-01-09T16:45:50Z

New #LLM "PE-Bench" benchmark results for coding, incl. different quantizations and languages: #python, #java, #rust, #clojure using Project Euler challenges: https://github.com/Orbiter/project-euler-llm-benchmark/blob/main/README.md

#DeepSeek-V3 Leading in Superhuman Coding: new leading position ...

2024-12-28T14:52:12Z

#DeepSeek-V3 Leading in Superhuman Coding: new leading position in the PE-Bench-Python-100, showing a 15.58-fold #superhuman performance.
See: https://github.com/Orbiter/project-euler-llm-benchmark

YaCy meetup at #38c3 - I will be at the FOSSASIA table in the ...

2024-12-27T14:08:10Z

YaCy meetup at #38c3 - I will be at the FOSSASIA table in the Critical Decentralization Cluster, watch out for the YaCy flag! If you want to meet me, just come by. See also: https://community.searchlab.eu/t/yacy-meetup-38c3/1705

You can meet me now or any time in the next four days at 38c3: ...

2024-12-27T14:01:25Z

In reply to nevent1q…ksw2
_________________________

You can meet me now or any time in the next four days at 38c3: see my posting in https://community.searchlab.eu/t/yacy-meetup-38c3/1705

The PE-Bench-Python-100 test results (checking LLMs ability to ...

2024-12-26T19:12:24Z

The PE-Bench-Python-100 test results (checking LLMs ability to code the Project Euler problems) are so far in this table. Read about it in https://github.com/Orbiter/project-euler-llm-benchmark/

ah yes, I just replied this. Your ideas are welcome if you want ...

2024-12-25T21:47:57Z

In reply to nevent1q…wh6f
_________________________

ah yes, I just replied this. Your ideas are welcome if you want to contribute.

However my target is to use the test results in a follow-up project where I want to make a auto-coder which reads tickets and provides pull requests. So we can collect here best practices.

the current prompt does not use any COT on purpose because I want ...

2024-12-25T21:44:25Z

In reply to nevent1q…eshl
_________________________

the current prompt does not use any COT on purpose because I want to measure also how much different prompt strategies influence the result, so this comes later. Templates are here: https://github.com/Orbiter/project-euler-llm-benchmark/blob/main/templates/template_python.md

my computer is already cooking hard and I want to make a large ...

2024-12-25T21:33:57Z

In reply to nevent1q…j989
_________________________

my computer is already cooking hard and I want to make a large table. Currently the largest models are first in the queue.

I also want to measure the influence of different quantization levels, because at this time I doubt that usage of a large model with strong quantization is better than a smaller one with less quantization. I don't know any benchmark which shows that.

yes, project euler is around since about 10 years and started ...

2024-12-25T21:27:31Z

In reply to nevent1q…7mex
_________________________

yes, project euler is around since about 10 years and started with ca. 160 problems. I also believe that most LLMs have seen solutions, however probably mostly in python. I don't think this is too influencing to other programming languages, so benchmarks to java etc. may be more significant.

My target is to evaluate the ability of LLMs to perform in an auto-coder engine and there I would not mind if those models perform because of some 'cheating'.

I am creating a LLM benchmark series ...

2024-12-25T19:32:06Z

I am creating a LLM benchmark series "PE-Bench-Python-100" to measure how good LLMs are at coding of the Project Euler Challenges compared to humans. The series will include also other languages than python, like java.

The first result so far is interesting because even the small model llama3.2 (3B) has a two-fold super-human performance (score: 2.14)

Source: https://github.com/Orbiter/project-euler-llm-benchmark/

good idea, at #38C3 I am with the #FOSSASIA community and I ...

2024-11-29T15:46:47Z

In reply to nevent1q…ksw2
_________________________

good idea, at #38C3 I am with the #FOSSASIA community and I usually also bring a small YaCy flag to mark where you can find me. We can also do a meetup!

Nostr event nevent1qqsxs2cvhdcp6twetv0hqmue6uhtvs7x5jcy6cd3vw3mnmgupxjq04gzypjjwdncatcmkx5w38dsyxcrg4s9ztdtmpnk4hlxxzjxpdfpqlr9v96qflz

2024-11-26T14:16:01Z

only 30 days left until day-0 #38c3 !!1!

host your own FLUX.1 server: ...

2024-11-15T15:37:57Z

host your own FLUX.1 server:
https://github.com/Orbiter/mflux-server

This provides image generation with FLUX on a Mac in a multi-user environment. Very easy to set up. Runs fast!

2025 is supposed to become the year of "AI Agents". I ...

2024-10-23T14:57:20Z

2025 is supposed to become the year of "AI Agents". I collected use cases into a repository that I want to use for lectures. It is still incomplete but it outlines major aspects:

- Inference Building Blocks
- Structured Data Generation
- Agents with internal/external/local data
- Process Automation
- Reasoning and Decision Making
- Robot Steering
- Autonomous Agents

Please have a look:

https://github.com/Orbiter/generative_ai_agents

I would love to get suggestions and maybe help if you want to fill gaps!

voila: https://laufwetter.de/ort/Wipperfuerth/ Nicht dem Link zur ...

2024-10-12T19:22:01Z

In reply to nevent1q…v9ar
_________________________

voila: https://laufwetter.de/ort/Wipperfuerth/

Nicht dem Link zur DVD-Koordinate im Dokument trauen, der DWD publiziert nur zwei Dezimalstellen der Koordinate der Station.

Happy Running!

Sehr gerne .. leider gibt es in Hückeswagen keinen Messpunkt des ...

2024-10-12T10:14:30Z

In reply to nevent1q…2y2a
_________________________

Sehr gerne .. leider gibt es in Hückeswagen keinen Messpunkt des DWD, die nächsten sind in Remscheid, Wermelskirchen, Radevormwald und Wipperfürth. Welchen soll ich nehmen? Tolle Landschaft habt ihr da übrigens!

I made an API server for FLUX, the new image generator model. ...

2024-09-10T19:41:00Z

I made an API server for FLUX, the new image generator model. There is a very good implementation for Mac Metal, called MFLUX and my server pull request is here: https://github.com/filipstrand/mflux/pull/29
pls give it a thumbs up!

Wie funktioniert ChatGPT ganz genau? Video vom Vortrag bei der ...

2024-08-19T13:25:00Z

Wie funktioniert ChatGPT ganz genau?

Video vom Vortrag bei der FrOSCon (npub1nxl…jpt0) ist nun hier: https://media.ccc.de/v/froscon2024-3054-wie_funktioniert_chatgpt_ganz_genau

Wie funktioniert ChatGPT ganz genau? Die Folien zum Vortrag bei ...

2024-08-17T16:39:33Z

Wie funktioniert ChatGPT ganz genau?

Die Folien zum Vortrag bei der FrOSCon (npub1nxl…jpt0) sind nun hier: https://yacy.net/material/20240817_Froscon_2024_-_Wie_funktioniert_ChatGPT_ganz_genau.pdf

Linux macht Spaß uns alles viel besser! Der Demo-Satz für ...

2024-08-16T13:43:27Z

Linux macht Spaß uns alles viel besser!

Der Demo-Satz für meinen Vortrag:

"Wie funktioniert ChatGPT ganz genau"

morgen bei der FrOSCon (npub1nxl…jpt0) https://programm.froscon.org/2024/events/3054.html

Mathematik für Neuronale Netze und Transformer ist wirklich ...

2024-08-07T17:43:15Z

Mathematik für Neuronale Netze und Transformer ist wirklich einfach, fast primitiv: das allereinfachste aus Linearer Algebra. Man muss nur wissen was Vektoren und Matrizen sind und was das Skalarprodukt ist:

Wir werden das in meinem Vortrag "Wie funktioniert ChatGPT ganz genau?" bei der #FrOSCon FrOSCon (npub1nxl…jpt0) benötigen: https://programm.froscon.org/2024/events/3054.html

Hier ein kleiner Spickzettel. Mehr braucht man nicht um Transformer und damit ChatGPT/LLMs zu verstehen!

Save the Date! FrOSCon 2024-08-17 16:30 @npub1nxl…jpt0 Sankt ...

2024-08-01T11:32:22Z

Save the Date!
FrOSCon 2024-08-17 16:30
FrOSCon (npub1nxl…jpt0)
Sankt Augustin (DE)

"Wie funktioniert ChatGPT ganz genau?"

Ich halte mal wieder einen Vortrag und erkläre wie LLMs funktionieren, inklusive (kurzem) Code Review! Alle Open Source Devs sollten das verstehen!

https://programm.froscon.org/2024/events/3054.html

Does anybody know how to measure the speed of progress in AI ...

2024-07-31T18:02:29Z

Does anybody know how to measure the speed of progress in AI development?

Or a statistic like days per achievement?