Featured note
September 8, 2026
Stop Ranking Models — Rank Cost Per Finished Job
Fable 5.1’s 75% cache-read cut plus Qwen3.8-Max-0902 topping Code Arena WebDev — why I’m ranking cost per finished job, not leaderboard screenshots.
Read article ↗
The notebook
Notes
What I’m reading, building, and thinking about in AI and development.
OpenAI Cut Cursor Loose — Claude Fable Is My Default Now
Last week I wrote about the model race — GPT-6 Astra, Claude Fable, Cursor, Grok. This week the story got sharper. OpenAI is winding down direct model access fo...
GPT-6 Astra, Claude Fable, Cursor, and Grok: The Model Race Right Now
If you build on the web for a living, this week is loud in a useful way. OpenAI just shipped GPT-6 Astra, Anthropic is leaning hard on Claude Fable (and the loc...