# 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](https://www.isaacbowen.com/2024/02/29)

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*