Deep dive · · 5 min read
Your AI system's biggest problem is probably not the model
Six days of production AI notes, and the model choice never once turned out to be the thing that broke.
Topic
In the glossary: Threat model, MCP (Model Context Protocol), Model gateway, what each means and how to say it in a review
Part of AI & Models: all AI & Models entries · the AI & Models lens on the map
Deep dive · · 5 min read
Six days of production AI notes, and the model choice never once turned out to be the thing that broke.
Explainer · · 2 min read
The practical reason LLM behavior needs constraints, validation, and repeatable output design.
Explainer · · 2 min read
Why production AI succeeds or fails in the system around the model, not in the model choice alone.
arXiv · Deep dive · The transformer paper. Still the right starting point for understanding what the model underneath is doing.