Back to writing

Tag

LLM

4 published posts under this topic.

How AI answer engines seem to pick sources

A practical explanation of query fan-out, citation drift, source bias, and why ranking in Google is no longer the same thing as being quoted by AI answers.

 Prompt Engineering Is Not a Template Library

My practical take after reading prompt engineering research: prompt templates are useful, but treating them as universal recipes is the wrong level of abstraction.

 How Expensive Is Training a Frontier Model?

A short builder-facing note on model training cost: the headline number is not only money, it is energy, hardware, operations, and risk.

 What to Expect from Vibe Coding

A practical take on vibe coding after shipping with Cursor, Claude Code, Copilot, Bolt.new, and Lovable: what AI tools accelerate and where product judgment still matters.