• Home
  • Author
  • Privacy Policy & Terms

Swift & Small Pieces

ARTICLES ABOUT SWIFT , OBJECTIVE-C, ALGORITHMS and Cryptography BY THOMAS KAUSCH

Get in Contact

Menu Close
  • Home
  • Author
  • Privacy Policy & Terms

Vor dem KI-Weltuntergang warnen und gleichzeitig den Dark Flow verkaufen

September 28, 2026tomkausch Leave a Comment

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 →

Uncategorized AI, Flow, VibeCoding

Apple Container: Linux Containers on the Mac

September 25, 2026tomkausch Leave a Comment

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 →

AI, Artificial Intelligence, Containers, MacOS, Security, Swift

start-small-learn-fast-ai-without-strategy

September 21, 2026tomkausch Leave a Comment

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 →

Uncategorized

AI in the Development Process: Which Tools Are Worth It

September 13, 2026tomkausch Leave a Comment

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 →

Uncategorized

A Claude Agent in 235 Lines of Swift: One Actor, One Loop, Two Tools

September 11, 2026tomkausch Leave a Comment

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 →

Uncategorized

Word2Vec versus Attention & LLM

July 17, 2026tomkausch Leave a Comment

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 →

Uncategorized

Word2Vec from Scratch: How Neighbor-Prediction Turns Words into Geometry

July 17, 2026tomkausch Leave a Comment

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 →

Uncategorized

Running Qwen2.5-Coder Locally with MLX and Wiring It Into OpenCode

July 11, 2026tomkausch Leave a Comment

An OpenAI-compatible endpoint on localhost:8080 is all it takes to turn an agentic coding tool into a fully offline one — here is what the stack actually does, and where it leaks. Background Agentic coding assistants are, architecturally, thin clients.… Continue Reading →

Uncategorized

REST Client Code Generation in Kotlin Multiplatform

May 8, 2026tomkausch Leave a Comment

Von der Spec zum Client — auf allen Plattformen Wer heute eine mobile App baut, baut meistens zwei: eine für Android, eine für iOS. Und irgendwo dazwischen schreibt man denselben HTTP-Code zweimal. Kotlin Multiplatform verspricht, dieses Problem zu lösen, aber… Continue Reading →

Uncategorized

Sunday afternoon Problem: Lazy Sequences as a Dynamic Programming Primitive in Kotlin

April 26, 2026tomkausch Leave a Comment

Dynamic programming is usually taught with mutable arrays and index arithmetic — Kotlin’s generateSequence and sequence { } let you express the same recurrences as infinite, lazily-evaluated streams.   Background Classic dynamic programming (DP) involves filling a table bottom-up: allocate… Continue Reading →

Uncategorized

Post navigation

← Older Articles

Thomas Kausch

Recent Posts

  • Vor dem KI-Weltuntergang warnen und gleichzeitig den Dark Flow verkaufen
  • Apple Container: Linux Containers on the Mac
  • start-small-learn-fast-ai-without-strategy
  • AI in the Development Process: Which Tools Are Worth It
  • A Claude Agent in 235 Lines of Swift: One Actor, One Loop, Two Tools

Recent Comments

    Categories

    AI Algorithms Artificial Intelligence Augmented Reality Code Blocks Concurrency Containers Dev Tools Effective Objective-C Encoding & Decoding Date iOS Languages MacOS Objective-C Pyhthon Security Swift Uncategorized Virtual Reality XCode
    © 2026 Swift & Small Pieces. All rights reserved.
    Fashionista by aThemes