So, I haven’t used Copilot or etc, but I use GPT pretty heavily in coding, and it’s crazy to me that “please autocomplete this thing I typed part of” is the model for AI assistance.
In my experience, GPT functions best when you describe a problem, or a particular refactor (“make log() asynchronous, returning immediately but queueing up the provided string to be written to the log in the background”) (“separate functions A, B, and C into their own separated class”), and then paste the segment of code you want it to operate on, and then paste its reply back into your code. Its generations aren’t perfect, but it can save a ton of time and typing when used in this way; I can’t really imagine that it works well if all the guidance you give it about the code it’s operating on and the task you’re trying to accomplish is what’s currently under the cursor.
I guess most of the issue is that not a lot of the time I spend coding is literally typing code into a blank editor. I would say 90-95% of it is augmenting or fixing existing code with some particular goal in mind. If I were trying to design an effective AI assistant, it would have a sidebar with a class diagram of the currently-relevant classes and their methods, and you could toggle a little eyeball for which ones of them you wanted to “show” to the AI to give it context, and then a box where you could request in a couple sentences the modifications you wanted it to make to that specified code. And, if what you wanted to do was generate some new code, you could do that, but it wasn’t designed around that as the central principle.
IDK, like I say, I haven’t worked with Copilot and friends so I don’t really know, but that’s what I would do.
“Each team is full-stack and full-lifecycle: responsible for front-end, back-end, database, business analysis, feature prioritization, UX, testing, deployment, monitoring”
“But they also shouldn’t be too large, ideally each one is a Two Pizza Team”
Either that’s a team with some hugely diversified skills, or that’s two car-sized pizzas
I agree that this is a challenge. One needs to slice the domain such that it can be covered this way. But this also means more people. In my experience, moving from “activity oriented” teams to “business centric” teams require an increase of the headcount.
Conway’s Law is a category-theoretic statement; it asserts the existence of a homomorphism on graphs, mapping from modules to code authors. Quoting Conway’s original paper:
Speaking as a mathematician might, we would say that there is a homomorphism from the linear graph of a system to the linear graph of its design organization.
The author does not really show an understanding or respect for the underlying maths.
Nothing to do with category theory. A homomorphism of linear graphs is a fairly concrete object, and Conway only uses graph theoretic terminology to clarify his semi-formal exposition. Dunno if I’d say there’s much math not being respected.
I like the concept of reducing cognitive load for the stream-aligned teams. This means all efforts go towards enabling them as much as possible in supporting the business. It also makes it relatively easy to judge if a platform team is doing the right things.
martinfowler.com
Hot