skip to content
Topic

coding-agents

7 essays on this topic.

Papers
  1. What A Prompt Trim Cannot See

    Deleting your agent's accumulated instructions is safest for the people who never tested them, and most dangerous for the people who did.

  2. Where the Harness Starts to Matter

    In April my benchmark said coding correctness is model-determined and the harness is a thin proxy. Two newer results show exactly where that claim breaks: the harness matters at the edge of what the model can do.

  3. 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.

  4. Test-first dispatch for AI coding agents

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

  5. 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.

  6. 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.

  7. 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.