Paul Nguyen

Paul Nguyen

Applied AI Engineer — Safety-Critical AI Products | Building Autodidact (local-first agent that learns) | PhD (Adversarial ML & Security)

Building AI agents using LangChain

less than 1 minute read

Published:

LangChain

An open-source framework to help build applications powered by language models

You May Also Enjoy

A transformer block from scratch: demystifying LLMs by building one

13 minute read

Published:

Many people see LLMs as a magic black box. At the architecture level, they’re simpler than they look. The core of every modern LLM - GPT, Claude, Gemini, Llama - is a transformer block. Stack one transformer block N times (typically 12 to 80), add an embedding layer at the input and an output head at the output, and you have a working ChatGPT-style LLM. That’s the whole recipe.

Stop Training Your LLM Router: Zero-Shot Confidence Beats Supervised Baselines

5 minute read

Published:

TL;DR: We tested whether you actually need labeled training data to route queries between a cheap local LLM and an expensive cloud model. You don’t. Average token log-probability — available for free from the first query — matches supervised routing in-distribution and crushes it when the query distribution shifts. We tested across 3 model families, 2 datasets, ~4,500 queries, and $123 in cloud costs. All code and data are open.