Türker Yıldırım

ai-tooling

  • MCP, read as a protocol rather than as a product

    Note2 min read

    A specification for giving a model access to tools and data, read for what it standardises rather than for what it enables. The protocol is small and the…

  • A test written by a tool, and read as review

    Note2 min read

    A generated test for an existing class, which is the case model assistance is genuinely good at, with one caveat. The second test asserts that assignment works, which…

  • What we do not let it near, written down

    Note2 min read

    A scope decision recorded as a rule, because a rule can be reviewed and a feeling cannot. The list is short and it is the shape that matters…

  • Three suggestions that would have been vulnerabilities

    Note1 min read

    Six months of review findings, filtered to the ones with a security consequence. All three are patterns that appear constantly in public code, which is presumably why they…

  • A year of an assistant in the editor, measured

    Deep dive14 min read

    A year of using a model-backed assistant, and an attempt to say something specific about it. Every claim about this is a demonstration or a complaint.

  • Acceptance rate, edit distance, and what neither measures

    Note2 min read

    Two metrics that are available, neither of which answers the question anybody is asking. A high acceptance rate is compatible with a tool that produces plausible code and…

  • A tool that does not know this codebase’s conventions

    Note2 min read

    Suggestions that are idiomatic for the language and wrong for this application, which is the most expensive kind of wrong. Both suggestions are what most PHP looks like,…

  • A team disagreement that data did not resolve

    Note2 min read

    Two people with the same evidence reaching opposite conclusions about a tool, which is a disagreement about values rather than about facts. A disagreement that survives agreement on…