Blog

Writing from Sophon

Notes on office agents, the products their work lands in, and how the company runs. Each post carries its publication date and is corrected in place when the facts change.

  1. Local by default, cloud as fallback: how Cue's polish step ended up on the user's machine

    Cue's dictation polish step was designed cloud-first with a local fallback. A 227-sample benchmark reversed that. What the case study records about the decision.

  2. What the DeepMind case study says about Cue, and what it does not

    Google DeepMind published a case study on Cue in 2026: what it measured, what runs where, how we quote it, and the claims it does not support.

  3. Counting installs: why the home page says 1.41M+ and not a larger number

    Google Play publishes install ranges, the App Store publishes none, and estimators publish figures nobody can check. How the home page numbers are built from that.

  4. How the voice-agent benchmark landscape was built, and why it is not a leaderboard

    Thirteen public benchmarks, one row each, with capability coverage and licences from first-party sources. What the dataset answers and what it refuses to.

Follow new posts with the RSS feed.