Writing
Notes from the workbench.
Practical notes on AI adoption and local models, from someone who runs both in production. New posts land here first; there is also an RSS feed.
-
The missing 90 percent of AI adoption
73% of surveyed enterprises use AI but only 10% run on it. The gap is not model quality. It is ownership, sign-off paths, and measured workflows
-
The open-weight frontier arrived in June
In one June window, open weights reached the coding frontier. What I'd build on, what I'd admire from a distance, and which numbers to trust
-
Local LLMs on a 64GB Mac Studio
The awkward middle tier of local AI in mid-2026, the capacity and bandwidth math that governs it, and the honest 75 percent verdict
-
The week the cloud blinked
Fable 5 vanished for 18 days under an export-control order. Frontier model access is now a dependency risk you have to engineer against
-
Routing work between local and cloud
Model rankings churn monthly; a routing policy survives. Classify work by risk, privacy, latency, and volume, and keep the decision log.
-
Self-refinement that knows when to stop
Nous Research's Autoreason finds naive self-refinement makes output worse, and fixes it with a blind tournament where doing nothing can win