Viewing profile — vidimitrov

"Expertise" is a completely different beast from "knowledge". Expecting to gain it from a model only through prompting is similar to expecting to become capable of something only b…

That’s cool. But how does it work in agentic environment? Do you get any benefit from it? Or it’s intended only for humans to read?

The “deterministic enforcement” is exactly what this enables but its not the responsibility of the spec to say that. Its harnesses or IDEs or you own implementation that will enfor…

Issue trackers are full of intent and decisions, that's true, but that's not the point here... It's about a storage that agents can use natively without the need of callings extern…

This looks very good. Thanks for sharing. I can only imagine how much discipline it takes to write these kinds of commits manually.

The format is optimised for agent querying and human readability in `git log`, not for `git interpret-trailers` compatibility. Those are different use cases.

Trailers were not suitable for the use case. The scope in parentheses is doing real work. `rejected(oauth-library)` lets you do `git log --grep="rejected(auth"` to find every rejec…

The problem is that usually we don't write the WHY in the commits... We tend to always capture the WHAT in the form of prose. And for agents, this is just more noise, since all the…

A few examples are the ability to query historical data and using each action line as a signal for other tooling to build on top but there are many others… you can check what Conve…

That’s exactly the direction I went with. Working on a spec for exactly this - planning to post it here soon: https://github.com/berserkdisruptors/contextual-commits

Nope - though I’ll take it as a compliment either way. It’s a problem I’ve been sitting with for a while, so the answer came out more formed than I expected. You disagree?

He admits the real hole himself: "this doesn't catch spec misunderstandings. If your spec was wrong to begin with, the checks will pass." But there's a second problem underneath th…

Level 4 is where I see the most interesting design decisions get made, and also where most practitioners take a shortcut that compounds badly later. When the author talks about "co…

* * *