Tagged
#architecture
3 articles
tools
The modern AI app stack, end to end
A clear map of the layers that make up a real AI application — model, orchestration, retrieval, evaluation, and the unglamorous glue that holds it together.
#ai-stack#architecture#llm-apps
05-29 09:14·7 min read
research
The transformer architecture, explained without math
The transformer is usually drawn as a wall of equations. Strip that away and it is one elegant idea: let every word decide which other words matter.
#transformers#architecture#attention
04-15 10:54·7 min read
models
Mixture-of-experts models, explained simply
Mixture-of-experts lets a model be huge yet cheap to run by using only a slice of itself per input. Here is the idea, plainly, and why it matters.
#mixture-of-experts#architecture#efficiency
04-11 13:35·7 min read