Why I built a game AI library I just released AdversarialKit, an open-source Swift package that lets any turn-based game find its best move. You describe your game, pick a strategy, and get a smart AI opponent back. Game AI… Continue Reading
Minimum Cuts in Graphs — revisiting my 1998 ETH semester thesis Thomas Kausch · October 2026 In 1998 I wrote my semester thesis at ETH Zürich on one of graph theory’s classic questions: how do you split a network into… Continue Reading
If you work in medical device regulation, you know EUDAMED, the EU’s registration database for medical devices and in vitro diagnostics. It holds manufacturers, authorised representatives, importers, and UDI device records. It’s also built for humans clicking through a web… Continue Reading
Ich programmiere seit dreissig Jahren, und ich programmiere wegen eines bestimmten Zustands: Die Welt ausserhalb des Bildschirms verschwindet, die Zeit vergeht schneller, und ich bin ganz bei der Sache. Psychologen nennen das Flow. Gleichzeitig warnen die grossen KI-Firmen regelmässig vor… Continue Reading
For years, the answer to “how do I run Linux containers on my Mac?” was obvious: install Docker Desktop, OrbStack, or Colima. Apple has now changed that. On June 9, 2026, Apple released version 1.0.0 of container, its Swift-native tool… Continue Reading
Start Small, Learn Fast: How to Explore AI Without a Strategy Many Swiss companies are in the same place right now. Leadership agrees that AI matters, teams are curious, a few employees already use chatbots on the side, but there’s… Continue Reading
Today there is an AI tool for every step of the lifecycle. Requirements, stories, code, tests, reviews, security, documentation, deployment, monitoring. I checked the main candidates for each step. What still exists, what changed in 2026, and what I would… Continue Reading
An agent is a loop, a message history and a handful of tools. Here is what that looks like in Swift 6, with actors and strict concurrency. Background Thorsten Ball’s “How to Build an Agent” makes a point that is… Continue Reading
Word2Vec is fundamentally a prediction engine over context. “Given this token, what else is likely nearby?” And that predictive framing generalizes to anything sequential: next word, next product, next event, next note in a melody. The “chances are high I’ll see similar words”… Continue Reading
Word2Vec has no notion of “meaning” — it only ever predicts which words sit near which, yet semantic structure falls out of that single objective. Here’s exactly why. Background Before dense embeddings, the default word representation was one-hot encoding: a… Continue Reading