7 notes
August 2026
Showing latest 3 of 7 notes
View all 7 notesNotes
Short observations, experiments, and ideas on AI, product judgment, discovery, careers, and modern tools.
Latest notes
An Archive Is a Retrieval Product
Aug 25, 2026
Keeping old work is easy. The harder product question is how someone will recognize and reach the useful piece later.
Skip the Lecture and Play Darts
Aug 11, 2026
A neural-network lesson became a standalone 3D darts game because explanation and play do different jobs.
My Laptop Has Been Demoted
Aug 8, 2026
After 34.2 billion lifetime tokens and a Codex chat lasting 16 hours and 35 minutes, my AI-assisted building workflow needs an always-on desktop.
Learning to Aim: How Neural Networks Learn
Aug 6, 2026
Learning to Aim starts with one fixed dart throw and introduces a neural network only when the target, wind, and distance begin to change.
Please Approve the Staffing Plan
Aug 3, 2026
Codex turned a project execution goal into my first staffing-plan review for a workforce of AI agents.
I Gave Codex a Resource Budget. It Treated It as Context.
Aug 2, 2026
Two nights of memory pressure taught me that operating limits for AI agents need to be enforced by the system, not merely explained in a prompt.
When Codex Starts Before I Say Go
Aug 2, 2026
Codex needs to distinguish between work it is asked to prepare and work it has been authorized to begin.
Browse by month
Move through the notes archive by publishing month, with each month kept small enough to scan.
14 notes
July 2026
Showing latest 3 of 14 notes
- This Time, It Was an iPhone: Autonomy Is Not Authority
- Computer, Make It So
- When One Second Was Too Long
10 notes
June 2026
Showing latest 3 of 10 notes
View all 10 notes13 notes
May 2026
Showing latest 3 of 13 notes
- Codex Shouldn’t Have to Steal Focus to Get Work Done
- From Chat History to Execution History
- AI Won’t Fix Bad Logic
24 notes
April 2026
Showing latest 3 of 24 notes
View all 24 notes