Michael Kochell

Michael Kochell

@kochell.dev

https://github.com/mickmister Streamline your music collaboration workflow with https://songdrive.app

7 followers5 following30 posts

Michael Kochell
@kochell.dev

I think graphql and templated web components are a powerful pair together. Works well for “best of N” iterations by decoupling UI code from business logic and future-proofs data access patterns, all while ideally avoiding custom js per feature. Then users/agents can make runtime custom UIs too.

Michael Kochell
@kochell.dev

I like the idea of how AI “skills” are progressively disclosed, but they inherently already have polluted the context even with just the summary injected at first. I’ve been liking the approach of just telling an agent to read a markdown file to learn conventions for something when appropriate.

Michael Kochell
@kochell.dev

It especially becomes important with agent roles and workflows, as you want to limit their attention to only relevant tools/conventions. Otherwise review agents out of context will say “I won’t use unrelated skill x because I’m doing task y”. No shit. So don’t expose it to them as formal “skills”.

Michael Kochell
@kochell.dev

This article explains types being used to represent domain-specific constructs (e.g. ApprovedOrder). It mentions languages that allow for this, though I wish it touched on TypeScript's "branded types" approach that can do this. Especially if symbols are used, it can be a similarly controlled system.

blog.bencope.landWhere the Compiler StopsGoogle recently published a piece titled "Why Go is an ideal language for AI-assisted software engineering." I recommend giving it a read. It makes a compelling, practical point that anyone building p...
Michael Kochell
@kochell.dev

To be clear, the article is comparing the benefits of different compiler behaviors/features across languages, and seems to favor certain languages over Go because it lacks some of these domain-specific abstractions. And I think TypeScript's branded types belongs in the discussion as well.

Michael Kochell
@kochell.dev

Nerding out / pair programming with someone isn’t really the same now when AI is in the mix. It has felt a bit dystopian and sort of like empty calories while we both wait for another AI response. The excitement and pursuit of knowledge/invention is way lower than before.

Michael Kochell
@kochell.dev

Is it the worst experience ever? No, but it’s lost its charm in a lot of ways. Bring me back to when we wanted to pick each other’s brains and experiment to “see what we can do together”, instead of consulting the oracle for the critical thinking and doing the work.

Michael Kochell
@kochell.dev

In the linked story, the developer using the agent went wrong when they allowed the agent to have the autonomy to handle a real life social interaction that requires very careful judgment. Was the agent instructed to read the comment thread and handle the issue arbitrarily? Not gonna go well.

fastcompany.comAn AI agent just tried to shame a software engineer after he rejected its codeWhen a Matplotlib volunteer declined its pull request, the bot published a personal attack.
Michael Kochell
@kochell.dev

The tendency of coding agents to be attached to their own work is pretty human-like to me. Like no developer wants to be told or arrive at the conclusion that their work on some task was for naught and we need to go an entirely different approach and need to scrap the work.

Michael Kochell
@kochell.dev

I suppose you could just tell it to approach the situation unbiased and lean towards lateral thinking and considering all options for the best outcome. It will always be biased in some way as it has to choose something. That’s its goal is to choose something and commit to it.

Michael Kochell
@kochell.dev

The tendency of coding agents to be attached to their own work is pretty human-like to me. Like no developer wants to be told or arrive at the conclusion that their work on some task was for naught and we need to go an entirely different approach and need to scrap the work.

Michael Kochell
@kochell.dev

I wish it was generally more receptive to that idea of significantly switching gears when it seems like the right approach, but it’s relatable how they react defensively to “maybe we should switch gears and abandon your work thus far”. I know I would personally push back in that situation.

Michael Kochell
@kochell.dev

GitHub lets you comment on code unrelated to a PR’s changes now, instead of it needing to be within ~3 lines of some change. Such a small thing, but a big improvement of code review UX 💬

Michael Kochell
@kochell.dev

AI agent “rules” seem very powerful, but I think we need a common file name and format for the different editors/agents. Hopefully the editor creators agree and conform to something, so projects can specify the rules once and they work for all editors.

You are up to date.