Blog
2026
- Postgres with CloudNativePG on Hetzner Cloud and Kubernetes
Commit latency, data loss and downtime compared between Cloud Volumes and local NVMe with synchronous replication
- SQLite with Litestream on Hetzner Cloud
SQLite’s commit latency on local NVMe and on a Cloud Volume, Litestream’s data loss and time to recover after a hard power-off, a warm standby with its follow mode, and DRBD and rqlite as zero-loss options, with rqlite as the fastest-failover alternative.
- Export ChatGPT Conversations as Markdown
Today I learned about Rashid’s solution to export ChatGPT conversations to Markdown or even PDF if you like. I prefer Markdown as I can use it to continue the conversation with Claude for example, or change the content and use it in other contexts.
- Hardware for local coding models is still affordable. For how long?
The recent RAM price hikes have pushed GPU prices up as well. The only systems that have not yet been affected to the same extent are Macs and high-end GPUs (RTX 6000 Pro and above). However, I would already classify GPUs as out of reach: running coding models with sufficiently large context windows would require one …
- MCP and A2A Attack Vectors for AI Agents
Christian Posta from Solo.io has written an interesting Deep Dive into MCP and A2A Attack Vectors for AI Agents.
- Try vibe coding (again)
In case you haven’t tried vibe coding, recently, you should probably try it (again). Their performance has increased quite a bit thanks to recent models like Opus 4.5. Here are some recent takes on vibe coding:
- The Van Halen Test can check if an agent knows it's context
Here’s a trick from the 80s that’s still useful, today: Van Halen’s live shows were potentially dangerous. To make sure the local crew read the rooster, they asked for a candy bowl with M&Ms and added:
- From 8 Lines with Dokku to 200 with Kubernetes – Why I'm Still Switching
So far, my web apps run on a Dokku server. I haven’t tried Vercel or Fly because I didn’t want to deal with complex pricing models that incur more costs with every additional project.
- What Takes Time in Vibe Coding
Vibe scripting, for me, is when I develop small tools for myself with the help of coding agents. It works extremely well, especially for command-line tools.
2025
- MCP in ChatGPT Developer Mode Beta
OpenAI just releasesd MCP connectors and ChatGPT developer mode beta. In this post, I describe the process of connecting MCP servers to ChatGPT, show how they look and feel right now in a chat session and give an overview of their current limitations.
- Claude Code in Devcontainers
Development Containers or just “devcontainers” add a layer of security, simplify developer onboarding enables developing in parallel with isolated environments.
- Tipps for Migrating to Hugo
In this article, I document some non-technical things I’ve learned migrating my blog from Jekyll to Hugo. The gist is to keep it as simple as possible:
- Evals for Voice Agents (Session Notes)
Notes of a whirlwind intro to evals for voice agents by Kwindla and swyx
- Coding Agents as Slot Machines
After reading a nice post via HN about On Stepping Back, I habitually scrolled through the comments and found this nugget by
- Pipecat Cloud Latency for EU Users
Pipecat Cloud is located in the US. Is its latency ok for voice agents for EU Users.
- K/V Cache Quantization in Ollama
A somewhat hidden feature of Ollama is K/V Cache quantization. This is relevant for local AI as it reduces memory consumption, especially for small LLMs with large context windows.
- Deploying Voice Agents to Production
Here are my notes on the session about deploying voice agents to production which is part of the Voice Agents Course.
- The Fast Solopreneur
In The Batch 300, Andrew Ng shared some insights about the importance of speed for startups and how to move fast as a startup. I think they apply well to ideas for a fast solopreneur:
- An Overview of the Voice AI Landscape (Session Notes)
I’m so happy to be part of the Voice Agents Course by Kwindla and swyx. Yesterday, Kwindla kicked it off with an overview of the voice AI landscape. The pace, insights, and questions from the audience were …
- Installing Docker on Raspberry PI
How to Install Docker and Docker Compose on Raspberry Pi OS (rootful and rootless).
- A note on the hidden complexities of WebSockets
AI Apps are often expected to be realtime. On the web, realtime communication can be implemented with WebSockets. I’ve started with WebSockets to create chatbots and other live-updated interfaces, but then switched to SSE and now mostly follow these rules of thumbs:
2024
- RTX 5090 for Local AI
A look at the NVIDIA RTX 5090 specs for local LLM inference.
- ChatGPT can use information from internal sites
The ChatGPT search feature can also search and use information from intranet websites.
- AI as Repository of Human Knowledge
An interesting statement by Yann LeCun.
- Dokku SSH Alias
A quick tip to make working a bit easier.
- Deploy a Static Site on Dokku
This article describes how to deploy a static site on Dokku, including activating Let’s encrypt signed certificates for the domain.
- Launch VS Code from the Command Line
A quick tip to make your life a bit easier with VSCode and Python.
- Deploying a SaaS Pegasus Based Django App on Dokku
In this post I’ll share the steps I did to deploy a SaaS Pegasus bootstrapped Django app (Scriv from the SaaS Pegasus marketplace to be precise) with Celery, Redis and Postgres on a Dokku host. There were some hickups along the way, but I believe, when you go step-by-step, it is quite straightforward.
- The Furo Sphinx Theme Looks Good with Small Documentations
A quick note about the Furo theme for the Sphinx documentation system.
- A Script to Export Models from Ollama
A workaround for transferring models to air-gapped Ollama instances.
- Ollama on Windows
A tutorial and video about installing and using Ollama and OpenWebUI on Windows.
- Summarizing Large Texts with LLMs and a Tree of Summaries
How to summarize texts with LLMs that are too large for their context window.
2023
- Hands-on ChatGPT in Excel (Book)
Example Excel workbooks for a book about using OpenAI models in Excel Formulas.
- ChatGPT Image Inputs Use Cases
Practical use cases of ChatGPT’s / GPT-4’s image input feature.
- Prompting Small LLMs.
What are small LLMs good at and how to get good results from small LLMs.
- Fetching Data from REST APIs with Python and httpx
How to install and use httpx.
2022
- What is new in Excel in Q1 2022
Microsoft keeps adding new exciting features to Excel all the time. Here is an overview of new features added in the first quarter of 2022.