Trust,
but trace
Most of what makes ML systems trustworthy is unglamorous: traces, fixtures, contracts, replays. This is a journal of that work, written from inside production.
Topics
Areas I write about
Six threads that keep coming back. Click one to see every piece tagged with it.
On the desk
Reading list
What I’m working through this season.
- 01BookAI Engineering: Building Applications with Foundation Models
- 02PodcastLatent Space — Artificial Analysis on independent LLM evals
- 03BookMultimodal, Real-Time AI Agent Systems
- 04ReferenceEU AI Act — Article 15: Accuracy, Robustness, Cybersecurity
- 05BookHands-On Large Language Models
- 06PaperConstitutional Classifiers
- 07PodcastPragmatic Engineer — Inside engineering at frontier labs