Someone recently asked me how many tokens I used after my Qwen 3.8 27B experiment. I had no idea, nor did I know how to verify it. This post explains how to count tokens, how prompt caching works, and tools to help analyze sessions.
All Posts
- Qwen3.8 27B just got released, a week after Meta's Muse Glimmer 30B. Alibaba advertises benchmark scores on par with Opus 4.6. This post compares Qwen3.8 27B with Muse Glimmer 30B, Sonnet 5 and Opus 5.
- I compared Meta's new Muse Glimmer 30B against Gemma4 26B-A4B and Qwen3.6 35B-A3B on a simple agentic search task, running locally on an M3 Max. Muse Glimmer tries harder than any of them, and that is exactly what makes it unusable.
- I have been using Claude Code personally and professionally for about six months. This post explains how I set it up, including plugins, tools, MCPs and CLI.
- Producing app store screenshots for OnTrack took me around 18 hours in GIMP. I attempted to automate it and decided to build a new web app for my needs: simple, free and multilingual. Building a new tool is also a good excuse to experiment with AI tools, so this post covers how my usage of Claude Code evolved.
- What 25 talks and panels at LDX3 London 2026 said about engineering teams in the AI era.
- Anthropic just launched Claude Design, a new research-preview product for generating interactive prototypes, slide decks, and more. I took it for a spin by designing a new analytics screen for my habit tracker app OnTrack, then handed the result off to Claude Code. Here's how it went.
- From Gemini 1.5 Flash to Gemini 3.1 Flash Lite, Google has increased the pricing by an order of magnitude, somewhere between 5x and 20x depending on the use case. This post retraces the pricing history over the past year.
- In this post, I share my experience building a cross-platform habit tracker mobile app using AI coding tools, highlighting the stark contrast between lightning-fast development and the surprisingly slow bureaucracy of Apple and Google's release processes.
- This article retraces how we scaled translating millions of user-written products at Mercari using Generative AI. It covers the various models, prompts and mechanisms implemented over two years.