Skip to content
StrucTime

Blog

Written by the people who write the code.

Two subjects only: what changes when a machine writes most of the code, and what we can claim about the models we train.

Topics

Latest articles

  1. Reviewing code you did not write: what catches problems

    The bottleneck moved. Writing code stopped being the slow part around 2025; reading it never got faster, and that is where the hours go now.

  2. What a world model is, and what it is not

    The term covers work as different as video generation and industrial forecasting. Stripped of marketing, it means one thing: a learned representation of how a system changes.

  3. The baselines that decide whether a forecast is any good

    A model that predicts an industrial signal with two percent error sounds strong until you learn that repeating yesterday's value gets one and a half.

  4. Why coding agents get worse as the codebase gets bigger

    Agents demo well on a new project and disappoint on a real one. The gap comes from what the model was shown before it started writing.

  5. Small language models on closed tasks: the case for narrow

    Most business uses of a language model repeat the same five operations on documents that follow a known shape.

  6. Tests written by a machine: when they help and when they lie

    A generated test suite arrives with the feature and every test is green. That tells you less than it appears, and sometimes nothing at all.

  7. Running several coding agents at once without them colliding

    Four agents on one working copy give you four processes overwriting each other's files, with no record of who won.

  8. Training your own models: what it buys and what it costs

    Calling an API is cheaper on day one, and that comparison is the one everyone runs. The interesting comparison is the one at year three.