2nd June 2026
Draft: This is a draft post. Please do not share this URL with anyone else.
I've been a bit disappointed with Opus 4.8 in the Claude.ai app - it seemed to answer extremely slowly, massively over-thinking everything.
Then I noticed I've been running it with the thinking effort set to "Max". I dropped that back down to the suggested default of "High" and it's behaving much, much better.
Recent articles
- Running the full server-side Datasette Python app in the browser with service workers and Pyodide - 17th November 2026
- Locating the source of a mysterious beep with Claude - 9th November 2026
- Hide your slop PR descriptions behind <details><summary> - 9th November 2026
- Qwen 3.8 27B on my laptop can interpret model weights, too - 3rd November 2026