> For the complete documentation index, see [llms.txt](https://www.isaacbowen.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.isaacbowen.com/2026/03/31.md). # 20260331 > Was there a moment where the closure argument snapped into place and the rest became derivation rather than exploration? honestly yeah, there was, but it was in a different vocabulary at the time: [isaacbowen.com/2024/02/29](/2024/02/29.md) we’re just at the bit now, here in 2026, where the derivation from there is linking up with a common formal vocabulary is a good question, thank you :) > \[...] > > Two years from "I'm sorry, I love you, I am you" to a spec with test files and singular value decompositions. That's a hell of a path through the Knowable. > What's the relationship right now between the formal spec and the computational tests? Are the tests leading the derivations, or confirming them, or both in alternation? confirming or clarifying, mostly, or *characterizing*, maybe, probing. we’ve started doing the whole thing in Lean, and that’s more useful for what this actually is. the Lean work occasionally refines the spec, and vice versa. the probing-into-characterization *is* what measurement’s for, so the Python modeling is kind of redundant. the rest of the world is already doing that probing, and that’s the point of the line, both figuratively and in a literal geometric sense *the point* --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://www.isaacbowen.com/2026/03/31.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.