← All interesting reads
Teaching nanochat to count r's in strawberry
A full guide to adding a capability to a tiny LLM: synthetic tasks, tokenization traps, and why a honeybee-sized model needs the data over-represented.
AIEngineering
Related reads
Company skills as a GitHub plugin
@startupideaspod
Greg Isenberg's whole company runs on skills in a repo. Add a marketplace URL in Claude Code, split by department, auto-update.
Aug 20, 2026
IndieAIEngineering
24/7 app maintenance as a software factory
@dabit3
Nader Dabit on high-ROI agent workflows: four you can stand up in a minute, and forty more once the language is clear.
Aug 19, 2026
EngineeringAgentsAI
The bottleneck moved
@arpit_bhayani
Writing code used to be expensive, so process protected engineering time. Arpit Bhayani on what breaks when that assumption dies.
Aug 6, 2026
EngineeringAI
How loop engineering actually works
@adxtyahq
Mental model, production loop, and why the hardest part of AI is no longer the model. Video plus a write-up.
Jul 2, 2026
AIAgentsEngineering
