FeaturedessaySunday, 11 October 2026
One year from doubting that AI assistants were any use to me and worrying about what they cost in energy, to using one every working day, told in order from my own record, with the doubts that stayed.
Read it, 8 min / AI / ai, machine-learning, learning, craft
An assistant given a real engineering task, and where it failed.
From zero 11
A PhD engineer learning Python and machine learning: what to learn first and what to skip.
note11 Oct 2026
note11 Oct 2026
Private retrieval over my own papers
note11 Oct 2026
Testing a skill with planted errors and a run without the skill
essay3 Oct 2026
Prediction and interpretation are two different uses of a fitted model
essay23 Aug 2026
Telling a skill exactly which files it may read
4 Oct 2026
A venv does not survive being copied to another machine
21 Feb 2026
The first chart to learn is predicted against actual
10 Feb 2026
My local model failed on its first long document because it was loaded with a 4096 token context
16 Nov 2025
When a long chat hit its limit I had it write a handoff file for the next one
9 Nov 2025
Al Sharah et al. (2024), Machine learning in chemical engineering, outlook and perspectives
Chowdhury et al. (2026), AI and machine learning in process systems engineering
Özdemir and Yildirim (2025), Past, present and future of machine learning in chemical engineering