skip to content
Topic

coding-agents

5 essays on this topic.

Papers
  1. Assume the LLM never ran

    A 208 MB log, 59,356 retries, and zero LLM calls. A debugging story about what happens when the symptom lies about the cause.

  2. Test-first dispatch for AI coding agents

    The architect writes the tests. The implementer makes them pass. No prose specs, no circular validation.

  3. I made my coding agent dispatch system improve itself

    I dispatched a 952-line monolithic CLI through my own coding-agent dispatch system to be refactored into seven modules. It worked. Notes on what self-bootstrap reveals about agent harness design.

  4. What 16,000 Simon Willison posts reveal about the state of AI coding agents

    I scraped 16,181 of Simon Willison's posts and analysed the 395 from 2026. An inflection in November 2025, GLM-5 closing the gap, and why the harness — not the model — is the competitive moat.

  5. Correctness is model-determined

    I benchmarked four AI coding harnesses on 12 tasks using the same model. The harness barely matters for correctness — it's all about the model.