Blog

Notes from the model lab.

Engineering writing on latency, evaluation, privacy, and running AI in production. The first posts are on the way.

  • Evaluation · Soon

    How we benchmark a model before it ships

    Coming soon
  • Latency · Soon

    Cutting p99 in half without touching accuracy

    Coming soon
  • Privacy · Soon

    Irreversible face templates, explained

    Coming soon
  • Infrastructure · Soon

    Serving five models behind one API

    Coming soon

Want these in your inbox?

We’ll send new posts when they’re published — no noise, just the engineering.

Get notified