Hacker News Reader

Comment by jbellis | Hacker News Reader

(creator here)

idk, everyone else seems to want to take the 40 year old IDE paradigm we're all used to (really! that's how old Turbo Pascal 3 is!) and graft AI onto it. I think we need a fundamentally different design to truly take advantage of the change from "I'm mostly reading and writing code at human speeds" to "I'm mostly supervising the AI which is better at generating syntax than I am."

of course the downside to going against the crowd is that the crowd is usually right, we'll see how it goes!

View on HN

I'd love to see things like Brokk experiment a bit more with what other information to include in our git repositories, besides the code, that helps improve AI-based code generation. For example, perhaps the repo should include more design information about the look-and-feel, as visual information or Figma files, rather than just, say the CSS and HTML. Or it might help if the repository included more business requirements so that the AI has better information to guide prioritization of changes. Obviously other bits, like coding standards, should be included as well, though perhaps using a larger context might mitigate the need for coding standards if the generated code followed the existing code (which often doesn't happen).

I think that's what's going to happen over time. We're going to be writing more and more code, but supervising an AI mostly.

The big problem is that we're treating the AI as an all knowing oracle. And probably what we should be doing is treating the AI as a colleague -- allowing it to ask questions about the code base to develop the subtle clues.

Often what happens is that subtlety is lost on the code base, and sometimes, AI will think it's an outright error, when in fact it's completely on purpose.

Comments go a long way towards this end, but in large legacy codebases, comments may not exist, and the coders expected people to understand at first glance the code was correct.

Test driving Junie, I've had it remove a feature it thought was broken code, and then it fixes the unit tests, instead of trying to understand if the unit test was actually broken or the feature was broken.

I am a huge supporter of completely re-working the IDE UI as well. I'm not arguing for keeping the existing IDE interfaces. I like that folks are experimenting with entirely new interfaces. In fact, I'd go further and suggest that all of the overly complex interfaces used on any sort of content-creation app, like Unity, Unreal, Photoshop, as well as code IDEs, will eventually be completely refactored to remove all the old complexity in favor of either chat-based or other AI-driven interfaces. My point is simply that there are too many new AI-driven IDEs for folks to try out, even the developers of those IDEs. Many of the features in Brokk that were seemingly described in the Brokk 101 blog video as "differentiators" are existing Copilot features. Has the author ever used Copilot? Or just Cursor? Or another AI variant?

Reply on news.ycombinator.com