Articles for people who
ship the stack
Original rewrites on React, Node.js, TypeScript and AI — practical notes from the same engineering practice behind our operator software. Article bodies are in English.
Tagged: transformers
Practical notes: When Should an AI Use Its Memory? An Experiment on Persistent
Operable walkthrough of Practical notes: When Should an AI Use Its Memory? An Experiment on Persistent: contracts, checks, and drop-in code slots for teams shipping this pattern.
2969 wordsRead articleLLM Inference End to End: Prefill, Decode, KV Cache, and Sampling
A whiteboard-ready tour of tokenizer through streaming—why prefill is compute-bound, decode is bandwidth-bound, and how GQA, paging, and speculation change the economics.
9177 wordsRead articleBuild AI-native web apps with JavaScript and WebGPU in the browser
Run transformers locally with WebGPU, workers, streaming tokens, and optional client-side RAG—while planning model size, VRAM, battery, and fallbacks.
1166 wordsRead article
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.