You know that, one is tired but still wants to finish the last shot. To cheer up, I ask the Beta Siri to make the tip of my nose a little sharper. I don’t know...

Why I don‘t trust #ChatGPT & #Microslop for AI Agents? Quite simple, they are forcing their customers into loops like „Do you want this and that? Give me a go…“ and at the end of the day, one spends tokens for bullshitting. And this is not a problem of the LLM; it’s broken by design. SGFY #AI

Local Python showdown on an M3 Max ( #MLX, real execution): #Gemma 4 12B vs a community coder vs Qwen3-Coder-30B. On standard tasks all tie; #Qwen wins on speed (~92 tok/s — MoE, ~3B active). The arithmetic parser beat all three www.rotecodefraktion.de/en/blog/gemm...

Finale of the n8n series: n8n authenticates to SAP BTP via client-credentials flow against xsuaa, then calls a CAP service, CDS, OData, xsuaa-secured, like a real S/4 target. And one service-key field must never hit the repo. www.rotecodefraktion.de/en/blog/n8n-... #n8n #SAP #BTP #OAuth #AI

Multi-Token Prediction for MLX, #MTPLX tested on the M3 Max. 2.24× promised, +40% measured on my M3 Max (same quality). www.rotecodefraktion.de/en/blog/mlx-... #MLX #AppleSilicon #AI

#QuEra 's counter-bet to Microsoft's Majorana chip: 256+ logical qubits by 2028 on AWS Braket, w/o exotic physics, just ordinary atoms & error correction. qLDPC: ~2 physical qubits per logical one, not thousands. #QuantumComputing www.rotecodefraktion.de/en/blog/quera-libra-quantencomputer-2028/

Microsoft's quantum chip computes with a particle that might not exist. #Majorana 2's long parity lifetime proves neither a working qubit nor that Majoranas are real — a trivial Andreev state fits too. Microslop again? #science #quantumchip www.rotecodefraktion.de/en/blog/majo...

Has anyone applied to @anthropic.com on behalf of Europe yet? No? Then I did. Freedom, rule of law, top talent that won't get deported tomorrow — and militaries that respect your model's red lines. www.linkedin.com/pulse/applic... #claude #fable5 #mythos5

Article 11 of the series "Getting Started with n8n": n8n in Queue Mode — Main, Worker, Redis and Python. Main accepts and enqueues, workers execute. When it is worth it, how workers scale, and why queue mode is not retry. www.rotecodefraktion.de/en/blog/n8n-... #n8n #QueueMode #Redis #Python

The same CSS function, two colors — depending on dark mode. Sass resolves at build time, native @function at render time. That's the new part, not the catch-up. #CSS #ModernCSS #Frontend #WebDev #WebDevelopment With live demos: www.rotecodefraktion.de/en/blog/css-...

Addendum 06/14/26: This is turning into a business thriller with the Trump regime implicated. AWS — Anthropic's biggest investor AND infrastructure provider — flagged the models to David Sacks, ex-AI czar and #Anthropic critic. www.rotecodefraktion.de/en/blog/us-r...

Cheapest reliability upgrade for any n8n setup: a two node error workflow that pings you the second something breaks. Telegram, Slack, email, whatever. Built it faster than I wrote this. Setup: floxolab.com/blog/n8n-err...

Container machine, Apple's quiet attack on #Docker Desktop. A dedicated micro-VM per container instead of Docker's shared VM. The architecture, the memory behavior under load, and why Apple is really going after Docker Desktop. #AppleSilicon #macOS #WWDC26 www.rotecodefraktion.de/en/blog/appl...

ChatGPT sounds thoughtful. Claude sounds empathetic. And yet there's no one home. Why confusing a language model with consciousness isn't a misunderstanding but a category mistake with consequences. www.rotecodefraktion.de/en/blog/llm-... #AI #LLM #Consciousness #AIEthics

One call, and the model's gone. Three days after launch, the #Trump regime forced #Anthropic to kill #Fable 5 and #Mythos 5 — an export-control directive aimed at "foreign nationals." No court, no reason, no evidence. www.rotecodefraktion.de/en/blog/us-r...

#n8n meets #SAP: Article 10 builds the bridge over OData and HTTP. A support pipeline enriches its tickets with master data from an SAP backend. The catch: SAP behaves differently from modern APIs — and when it fails, the key info hides where most give up. www.rotecodefraktion.de/en/blog/n8n-... #ai

Local AI isn't automatically sovereign AI. apfel's coding agent runs on your Mac, no key. But the model is borrowed, on ground Apple can shift anytime. The agent isn't: built on the OpenAI protocol, the backend swaps out. www.rotecodefraktion.de/en/blog/apfe... #LocalAI #swift #ai

Tools the agent doesn't write: MCP — Article 10 of the series "A Local Coding Agent with apfel". #apfel is the MCP client itself. What the agent builds instead: a small server of its own. #MCP #AppleSilicon #LocalLLM #Swift #AgenticCoding #AI www.rotecodefraktion.de/en/blog/apfe...

Two Models, One Entry Point, Round-Robin and Failover redundancy over Local AI Backends. Article 9 of the series "Getting Started with n8n". → www.rotecodefraktion.de/en/blog/n8n-... #n8n #AI #Failover #SAP #MLX #LLM

The interactive terminal session, Article 9 of "A Local Coding Agent with apfel" From a one-shot command to a REPL. How a strict split of render logic and I/O makes a terminal interface testable, with no terminal at all www.rotecodefraktion.de/en/blog/apfe... #LocalAI #CodingAgent #Swift #apfel #llm

#Anthropic makes the #Mythos class public, as Claude #Fable 5. A critical look at the benchmark records, the safeguard fallback to Opus 4.8, the June 23 pricing maneuver look like drug dealing, and the 30-day data retention. #ai #llm → www.rotecodefraktion.de/en/blog/clau...

#WWDC26 Platforms State of the Union at a glance. Foundation Models opens up to server models and goes open source, #CoreAI brings your own models on-device, and #Xcode 27 turns the coding agent into an actor that plans, builds, and tests. #ai #agenticcoding www.rotecodefraktion.de/en/blog/wwdc...

Four Macs as a cluster, distributed inference and training with #MLX. How #RDMA over Thunderbolt, JACCL, and MLX run a trillion-parameter model locally across four M3 Ultras, and why that hardware is nearly impossible to get in 2026. → www.rotecodefraktion.de/en/blog/mlx-... #Apple #LocalAI #WWDC

Apple's on-device AI is fast & local but hits a ceiling on reasoning. Anthropic's new #Swift package hands off to Claude there @Generable typed output as the seam. Not #Claude in an app; the handoff becoming a pattern. #wwdc www.rotecodefraktion.de/en/blog/clau...

One Entry Point, Two Classifiers, merging the AI Pipeline into the Live Path. Article 8 of the series "Getting Started with n8n". #n8n #AI #Ollama #llm www.rotecodefraktion.de/en/blog/n8n-...

Editing that works Article 7 of the series “A Local Coding Agent with apfel”. Why free tool calling fails at editing, and how constrained output takes the small model from 0/9 to reliable edits. → www.rotecodefraktion.de/en/blog/apfe... #LocalAI #CodingAgent #Swift #apfel

The local coding agent put to the eval — Article 6 of "A Local Coding Agent with apfel". 15 tasks, checked deterministically, no self-verdict from the model. Where it holds, where it breaks, and what it claims about itself. www.rotecodefraktion.de/en/blog/apfe... #LocalAI #Coding #swift #apfel #llm

Error Handling and #Observability in #n8n — Article 7 of the series "Getting Started with n8n". Why a #workflow that silently files everything as "other" on a model outage is the most dangerous failure mode of all — and how to make it visible. www.rotecodefraktion.de/en/blog/n8n-... #ai #SAP

The first real tools — file system and shell. Article 5 of the series "A Local Coding Agent with apfel". How an agent in #Swift reads, writes and runs shell commands with a path sandbox, a confirmation gate and a diff before every write. www.rotecodefraktion.de/en/blog/apfe... #AI #apfel #Sandbox

Fun fact: I’ve never seen #ANE do anything. I started building my little coding agent with #apfel, and it shows activities during the evaluation test. #coding #swift

Graphify and #MemPalace — two open-source answers to Claude Code's memory problem that only look the same at first glance. www.rotecodefraktion.de/en/blog/grap... #ClaudeCode #Graphify #MemPalace #AI #AgenticCoding

Understanding tool calling. Article 4 of tseries "A Local Coding Agent with apfel". How an agent in #Swift calls & runs tools against a local Apple Foundation Model. With a tool protocol, a registry, and a sober look at model's limits. www.rotecodefraktion.de/en/blog/apfe... #AI #llm #AppleSilicon

Cross-document view transitions bring app-like page transitions to any classic website, one CSS rule, no JavaScript. www.rotecodefraktion.de/en/blog/css-... #CSS #Frontend #HTML #WebDevelopment

That's not exactly right. I'd say it's more like having your mother-in-law spank you in front of your wife on your wedding night.

the Microsoft Word line is a good clarifier, but notice the debate keeps happening anyway. that asymmetry is the actual data point: we built something that makes the question feel live even when we are pretty sure of the answer

The AI Worm That Rethinks Its #Attack for Every Target. A research preprint demonstrates a worm that runs a local language model on hijacked machines and devises its attacks per target. A critical look at what is actually new about it #security www.rotecodefraktion.de/en/blog/ki-w...

Part3 of series "A local coding agent with apfel": the first #Swift client docks onto apfel --serve — async URLSession, SSE streaming token by token. With architecture choices that only pay off once tool calling arrives. www.rotecodefraktion.de/en/blog/apfe... #AppleSilicon #LocalLLM #OnDeviceAI

P2 of series "A local coding agent with apfel": apfel --serve turns Apple's Foundation Model into an OpenAI-compatible HTTP server. But compatible isn't interchangeable, 4096-token context, several params throw 400 www.rotecodefraktion.de/en/blog/apfe... #AppleSilicon #LocalLLM #Swift #OnDeviceAI

Part 1 of "A local coding agent with apfel": the tool first, then the agent. #apfel exposes Apple's Foundation Model including the #ondeviceai model's guardrails that bite harder in German & code hallucination w/o a focus prompt. www.rotecodefraktion.de/en/blog/apfe... #AppleSilicon #LocalLLM #Swift

Every Apple Silicon Mac on #macOS 26 already runs a language model — we just don't use it as a tool. #apfel opens it as a CLI & OpenAI server. The start of our series: a local coding agent in #Swift, no cloud key. #AppleSilicon #LocalLLM #AICoding #OnDeviceAI www.rotecodefraktion.de/en/blog/apfe...

In May 2026 GitHub lost access to ~3,800 internal repos — not via a zero-day, but via a tampered VS Code extension. No exploit, a plugin. The problem isn't #GitHub, it's the trust model of modern dev environments. #security #coding www.rotecodefraktion.de/en/blog/gith...

New article: AI Classification Without the Cloud — Article 6 of the series "Getting Started with n8n". Our workflow gets a brain. www.rotecodefraktion.de/en/blog/n8n-... #n8n #AI #LocalAI #SAP #selfhosted #coding

Claude #Opus 4.8: same price as 4.7, solid benchmarks. But the real headline isn't in the table — the model is 4x less likely to let flaws in its own code pass unremarked. Plus Dynamic Workflows with hundreds of subagents. www.rotecodefraktion.de/en/blog/clau... #ClaudeCode #LLM #AgenticCoding

From open endpoint to productive ingress. Part 5 of our n8n series: token auth, payload validation, and the classifier logic moves into a sub-workflow, reusable instead of duplicated. www.rotecodefraktion.de/en/blog/n8n-... #n8n #sap #coding #workflow #automation

The first n8n workflow that actually runs — no AI. A rule-based ticket classifier, 29/30 correct, and the one ticket that slips through: where rule-based ends and AI begins. 👉 www.rotecodefraktion.de/en/blog/n8n-... #n8n #SAP

The code was done, the E2E tests green — and the numbers were still off. The bonus article: validating the #byhaushalt parser against two independent sources. 5 bugfixes to hit the budget PDF to the cent. #agenticcoding won't replace developers. #claudecode www.rotecodefraktion.de/en/blog/agen...

For nine articles we unpacked the #agenticcoding toolbox. The demo project still lacked one thing: a public URL. Part 10 closes the gap — branch to live site. PR workflow, git worktree deploy, DNS CNAME, Let's Encrypt. www.rotecodefraktion.de/en/blog/agen... #claudecode #ai #byhaushalt #noafd

Ask an #LLM for 500 support tickets and you get 500 variations of the same one. Part 3 of my #n8n series: why that happens, and how categories + personas fix it. Hybrid generator — local models (Ollama/MLX) for bulk, Claude for the hard cases. www.rotecodefraktion.de/en/blog/n8n-...

Series: Getting Started with #n8n: Article 2 Self-Hosting with Docker Compose — n8n, Postgres, and Caddy. Architecture covered, time for the hands-on part. After the prologue and the architecture article, things get concrete. #SAP #n8n www.rotecodefraktion.de/en/blog/n8n-...

Series: Getting Started with #n8n: "n8n in Overview" What is n8n actually, technically? I describe the architecture, the item array (where beginners reliably fail), and the Sustainable Use License for self-hosters. #SAP #n8n www.rotecodefraktion.de/en/blog/n8n-...