WirelessMoves – My Thoughts on the Evolution of Wireless, FOSS and the Past, Present and Future of Computing

Signal vs. Conversations – OTT Voice Observations – Part 1

In my simple universe, I always thought that all apps using Android’s built-in WebRTC stack for voice and video calls would pretty much use the same parameters and hence, the encrypted data stream would pretty much look the same. It turns out, however, that this is not at all the case. This discovery made me go off on quite a bit of a tangent, and I decided to have a look at a number of different related things, including cellular network handover behavior and other things. But let’s start at the beginning, the use of WebRTC by different ‘Over the Top’ voice applications. Personally, I use two messengers: Signal and Conversation and it turns out they use WebRTC quite differently!

Disconnecting Mouse Moves

Here’s yet another ‘mouse’ story, these devices seem to be much more tricky to handle than they look, at least for me. So here’s the story: For the past few years, I’ve had this very strange behavior that when traveling, my mouse would work better on some surfaces than others. Particularly, when I would lift the mouse, move it and then put it down again, it would, on some surfaces, take a few seconds before it was working again. For several years I blamed this on the reflectance of the surface, as this behavior seemed to mostly happened on such surfaces. But over the years doubt has crept in if that was the real reason for this.

My AI Learning Journey – Part 12 – Kagi’s Privacy Minded LLM Search Assistant

In a previous post I’ve taken a look at how I can combine a private LLM with Internet search. My setup: An Open WebUI instance hosted at home together with Ollama, the Llama3 LLM and Brave as a search front-end. While this works well for some kinds of searches and not so well for others, I was wondering if there are also other options for private search with LLM capabilities that require less self hosting. Here’s an interesting option I came across: Kagi.

Working on the Train Like its 1988!

When I use public transportation to commute to work today or when I take longer trips with the train, every second person on the train seems to have a notebook open in front of them, while the other half interacts with their smartphone or tablet. Its 2026 after all. I’d like to think of myself as a pioneer of doing this because I used my notebook with a mobile Internet connection on a train a decade before it became popular. But actually, I’m a later adopter…

Have a look at the first 5 minutes of this Youtube video with a recording of a Beyond 2000 episode broadcast in 1988 about working and communicating on a train 40 years ago. Truly amazing then and truly amazing how far we have come since then.

My AI Learning Journey – Part 11 – AI Assisted Coding – Good or Bad?

In the previous post I’ve had a look at how I can integrate an LLM into my programming environment and use a prompt to produce and modify code, to find bugs and security issues, and to discuss options and fix issues. I find the result stunning. So is AI assisted coding a good or a bad thing? Maybe this is the wrong question to ask, it’s like wondering if programming in Python is a good or bad thing compared to programming in assembly language. Let’s dwell on this a bit.

My AI Learning Journey – Part 10 – AI Assisted Coding – VSCodium and Continue

AI Assisted Coding in VSCodium with Continue, OpenRouter and GPT-5.3-Codex

All right, I’ve touched quite a few topics in my AI learning journey so far and today it is time to have a look at a central piece of the whole exercise: AI assisted programming.

Over the past years, I’ve been using AI systems in my private programming projects a few times but it has always been separate from the programming environment and I had to copy and paste code at some point. And while this has sped up quite a number of things, it always felt quite limited. In the meantime, it seems that a number of plugins for programming environments have become available to enable LLMs to directly interact with the code. Also, I’ve heard that high end LLMs can get an overview of the complete code base of a project and suggest + implement solutions across many source files at once. That sounds all quite nice but I was not willing to give up the privacy of my tool chain and I also didn’t want any tool to create a personal profile of my activities. So I looked around a bit and came across a very nice tool chain that fit my privacy needs while giving me access to the latest LLM models for programming.

My AI Learning Journey – Part 9 – Local Documents and LLMs

Open WebUI and a local LLM answering questions from my old Wiki.

In part 7, I’ve had a look at how external search engines can be integrated into Open WebUI and combined with local LLMs to get external references when asking questions instead of having to rely just on the output of the LLM. This is referred to as Retrieval Augmented Generation (RAG). The same approach can also be used to combine local LLMs with local documents for search.

My AI Learning Journey – Part 8- OpenRouter – 350+ Models to Experiment With

After looking into local LLMs and Retrieval Augmented Generation (RAG) in the previous post, this post focuses how to experiment and use public LLMs in a privacy friendly way. The basic problem: While one can anonymously ask a limited number of questions to public LLMs such as ChatGPT, Perplexity, etc., more in depth questions require an account and often a monthly subscription. And with an account comes the loss of privacy. But there’s an interesting solution:

My AI Learning Journey – Part 7 – Combining LLMs with Web Search

For me, like most people, the everyday default use case for LLMs is to get answers to questions, i.e. I use it as kind of an enhanced search engine. So far, my experiments with local LLMs have focused on getting answers out of what the LLMs have learnt during the one time learning phase, i.e. what is ‘stored’ in their ‘weight’ parameters. While this works, there are two major shortcomings: First, information about current events is not available, as the training phase was in the past. And secondly, there are no references to check if the information returned was correct. In many cases, the information is correct, but there are also spectacular hallucinations that sound credible but are just plain false. This is why many online LLMs such as Perplexity can combine their training with web search and give references in their output, so the information that was given can be verified. This is what is referred to as Retrieval Augmented Generation (RAG). It’s not a panacea, but it helps quite a bit. So my obvious next step: How can I get RAG working with my local Ollama and Open WebUI installation in a privacy friendly way?

My AI Learning Journey – Part 6 – A Reverse Proxy for the LLM GUI

Welcome to part 6 of my LLM learning journey. Before I continue to explore the many features of Open WebUI (OWUI) in combination with Ollama, I wanted to do one other thing: By default, Open WebUI has a http frontend, there is no https port available and hence a reverse-proxy is required to use the service securely over the Internet. If the server on which OWUI runs can be reached over a public IP address, getting a reverse-proxy with Letsencrypt certificates up and running with docker compose is straight forward. Have a look at this post for the details on how to do that. In my case, the server I’m running OWUI and Ollama on does not have a public IP address so I needed to look for something slightly different.