Lab notes
Questions worth pursuing.
Proposed engineering notes, research questions, and experiment outlines. These are directions for future writing — not published findings or completed experiments.
01 · Engineering note
Small Language Models for Specialized Applications
When a smaller, adapted model beats a frontier model — on cost, latency, privacy, and control.
Lab note · proposed topic
02 · Engineering note
Fine-Tuning vs. RAG: Choosing How a Model Learns Your World
Two ways to make a model know your domain — and why the answer is often both.
Lab note · proposed topic
03 · Engineering note
Designing Reliable AI Agents for Production
Reliability comes from constraints, evaluation, and observability — not from a better prompt alone.
Lab note · proposed topic
04 · Experiment
Reinforcement Learning for Agent Behavior
Exploring whether reward-shaped training can make agents more reliable at multi-step tasks.
Lab note · proposed topic
05 · Opinion
How Claude and Codex Are Changing Software Engineering
AI coding tools shift where engineering effort goes — towards specification, review, and verification.
Lab note · proposed topic
06 · Experiment
Evaluating AI Systems Beyond Demo Quality
A demo proves possibility once. Evaluation proves reliability repeatedly. The gap between them is the work.
Lab note · proposed topic