Wow, thanks for your honesty here. I'm commenting primarily to commend your decision-making which I couch in empathetic understanding.
I saw your post and immediately thought, "good, surprised it took {any organization leaving github} this long." I don't hate big M nor the 'github ecosystem' (except maybe github actions, which seems to get 10x the attention it deserves); the challenge is I perceive far better solutions to be chosen which would serve the open source world if we simply deploy a slight increase in cognitive energy.
Can we get one which scans for downvotes on comments which are either positive or in anyway against any dominant narrative in HN?
*If you feel attacked by this comment, you know exactly what to do. Do it. Fulfill your destiny.
My comments have a weird history: either I display technical prowess and flavor my comment negatively (as is statistically more common on HN), or I get downvoted.
My response is to spend less time on HN :D if I want pressure to think a certain way by people with limited skin-in-the-game in my life, i'll just show up to a fundamentalist church ;)
I think so. From my experience Claude/codex tooling really excels at vibe coding the whole thing. You give it a folder and just say: now make it do this. And you don’t really care for the code.
Junie tooling excels when you are more involved. Like, look in these two files, add this specific functionality, in this specific way. Junie is usually a lot faster and to the point. Very simple tooling , it just works for this workflow. But it breaks for the “code the whole thing for me” workflow.
It surprises me how JetBrains managed to lose such a great market opportunity.
I don't think they ever going to be able to re-claim large chunk of developers who are now fine with thin VSCode-like + Terminal for non-JVM languages.
Perfect example of how large corp with research capacity failed to navigate their product changes.
My most enjoyable and productive experiences with AI so far have looked more like pair-programming than agent-based vibe coding. That is to say, I care about the details, and I want to read, understand, edit, and curate the codebase. I find that if I'm not limiting AI to relatively small enhancements per request-review cycle (100 or so LOC), then when things inevitably go off the rails, I'm in a deep hole that takes a long time to climb out of.
I haven't tried out Junie yet, but the concept seems pretty compelling to me. I want a good IDE for the language I'm using, and I'd like an AI that's well integrated and trained on delegating to it for algorithmic/deterministic transforms (e.g. IDE-driven refactorings).
REQUEST: coupon for positive thinking;
STATUS: DENIED, NON-NEW USER NEW BETTER HAHAHA
std::process::exit(sarcasm)
seriously though, this is HN. I'm done complaining about it. I'd like to encourage different behavior, yet my experience has taught me the opposite: Be open to offering feedback in the case feedback is requested or required. In any other case, disengage.
Why would you disagree with the parent post and then fail to provide the title of the book in your own response? Just give the name of the book, please.
