In 20+ years in the industry, I've never seen software development change as fast as it's changing today. Lovable is a cool place that lets you work at the cutting edge and find out what the future of software development looks like [1/2]
@ByrneHobart Reading code stochastically, but not every line. Trying to make sure every important line is read though.
A lot of learning from LLMs. "This looks off, is there a better way?" is something I use almost daily. LLMs are great at helping you learn when you want to.
Friends who used to hand-write code and who now vibecode, I'm curious about how much time you spend reading source code, and especially curious if you learned any new programming idioms from LLM outputs.
@GergelyOrosz The quality of test code I get from LLMs is consistently worse than quality of production code. I guess test code in the training set was quite dull and the style transferred. Still great use for them, I now get higher test coverage just because adding adequate tests is so easy
When I say "because I had to" I mean because I knew that they are SO important both for the present and the future.
But they never gave me much intellectual satisfaction - in ways that writing my code had done (and still does!)
One really, really, really good use case for AI and coding:
Writing unit integration tests.
I always hated doing these, because most of the effort was about the setup (remembering how to use the test framework, how to create a fake, a mock, the syntax)
Love handing it off!!
On code review: It's the new bottleneck. Every agent gives you a week's worth of not-great code in hours. You have to review it all. Your team has to review it all. Stacked PRs, better PR hygiene, AI self-review all help. 3/x
AI writes 90% of my production code now. Speedup: 3-4x for prototypes, but only 1.5x for prod. The bottleneck moved from writing code to reviewing it. You still have to read every line. Field notes from 6+ months of coding with agents: 1/x
@GergelyOrosz Very true! Removing code review makes sense when no human is ever expected to look at the code or modify it. In more traditional code bases teams would probably fight slop, with mixed success. Strong engineering teams would mostly win and weak one would mostly give up
It’s just amusing that with these AI tools and agents we seem to be getting back to this truth:
A team of strong software engineers who care about the quality + maintainability of the codebase >> A team of devs using powerful AI coding agents rather mindlessly
Unpopular opinion:
Current code review tools just don’t make much sense for AI-generated code
When reviewing code I really want to know:
- The prompt made by the dev
- What corrections the other dev made to the code
- Clear marking of code AI-generated not changed by a human
@igrekde Если ли пакетные менеджеры, где обратная совместимость и несовместимость представлены нормально? В npm всё ужасно, в java-мире ужасно.
Вроде, были интересные идеи в Golang и в Rust?
На этой неделе пишем невероятный выпуск про то, как дизайнить API библиотек и поддерживать его, не ломая проекты и жизни разработчикам, его использующим. Накидайте ваших вопросов!