---
title: "AEON Systems blog: building with AI, research"
description: "How we build software with AI and how we train our own models. Written by the people who write the code."
canonical: https://structime.com/en/blog/
language: en
last_modified: 2026-10-21
publisher: "AEON Systems (SIREN 993102821)"
source_format: html
---

# Written by the people who write the code.

> How we build software with AI and how we train our own models. Written by the people who write the code.

Source : https://structime.com/en/blog/
Publisher: AEON Systems (SIREN 993102821) · StrucTime

Blog

Topics

- [Building with AI What changes when a machine writes most of the code: how to review it, how to constrain it, and how to know the result holds.](https://structime.com/en/blog/building-with-ai/)
- [Research How we train and evaluate our own models, what we can claim today, and what we deliberately do not claim yet.](https://structime.com/en/blog/research/)

Latest articles

1. [27 Aug 2026 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. Engineering](https://structime.com/en/blog/building-with-ai/reviewing-ai-generated-code/)
2. [27 Aug 2026 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. Research](https://structime.com/en/blog/research/what-is-a-world-model/)
3. [26 Aug 2026 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. Research](https://structime.com/en/blog/research/baselines-that-matter/)
4. [26 Aug 2026 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. Engineering](https://structime.com/en/blog/building-with-ai/context-and-large-codebases/)
5. [25 Aug 2026 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. Research](https://structime.com/en/blog/research/small-models-closed-tasks/)
6. [25 Aug 2026 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. Engineering](https://structime.com/en/blog/building-with-ai/tests-nobody-asked-for/)
7. [24 Aug 2026 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. Engineering](https://structime.com/en/blog/building-with-ai/parallel-agents-worktrees/)
8. [24 Aug 2026 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. Research](https://structime.com/en/blog/research/training-in-house/)