Morning Bathrobe Rant. Quicksilver.
@unclebobmartin290 тыс. подписчиков
35 074 просмотра
41 комментарий
Комментарии из оригинального поста в X (Twitter)

@CurtisForrester
I'm convinced you're certifiably insane. Don't change one bit! Totally agree on your perspective. I'm just now telling my agent it screwed up on the last round of refactoring - because I saw the error in PyCharm. Build moar tests.
6 отметок «Нравится»

@unclebobmartin
It's OK to be a little crazy.
12 отметок «Нравится»

@weslong
These "Bathrobe Rants" are so amazing and so accurate!
5 отметок «Нравится»

@ivatokar
What we need is more like VDD, Verification Driven Development.
3 отметки «Нравится»

@DimitriGilbert
i've hated TDD for so long i don't remember when it started... I've tried using that for some test project and now i can't imagine doing anything of a decent size with AI without that...
3 отметки «Нравится»

@LGrapenthin
Didn't you try this approach with your space game and eventually it started cheating, even with mutation tests and CRAP threshold?
2 отметки «Нравится»

@unclebobmartin
Yes, so I had to tighten up all the constraints. Now it behaves quite well.
7 отметок «Нравится»

@glvnme
@swyx here is your headliner for next aieng nyc event go in debt if needed unc is so ahead
2 отметки «Нравится»

@victor36max_
Good vibe coding is good software engineering. We have had these practices for decades.
2 отметки «Нравится»

@worldcr48747071
This is where AI excels in the hands of tenured artisans. Thank you for sharing.
1 отметка «Нравится»

@realhenry
Just found your account and really appreciate these rants. Thank you. Followed
1 отметка «Нравится»

@steveMmattison
Loving these morning bathrobe rants, keep them coming, helpful, t.y.
1 отметка «Нравится»

@dnltjkr
you sure you can't just make a podcast? Cause I sure would listen to hours of that
1 отметка «Нравится»

@_centoundici
I love the voice, It reminds me Mark Hamill’s interpretation of the joker
1 отметка «Нравится»

@Red_256
POV all your real features will break. It will just generate more and more tests and once you take a look everything is broken. It is an absolute necessity to have clear defined e2e tests. These tests must be maintained by another orchestrator or made to be hardly editable or else your agent will just change the tests to make it work.
1 отметка «Нравится»

@patrick_kuhnke_
A rant a day keeps the doctor away.
1 отметка «Нравится»

@noozie
Yeah, that works, and is better suited for some environments. But let me also add to the discussion, property testing. Identify the property of your feature, and write a test that validates that property, then throw a random generator on your inputs, and run it N times. See what breaks...hopefully nothing. Then you're one step away from deterministic simulation testing, where you take those property tests, and you add some hooks in important places to introduce faults, like network connectivity issues (30% packet loss, for instance, hard disk latent sector, etc) and you see if your property still holds. Not a replacement for acceptance testing, but does allow you to keep acceptance tests more towards the frontend, and use a more effective tool on the backend.
1 отметка «Нравится»

@kubasienki
Classic tools remain highly relevant. Since LLMs mimic human logic, the tools designed for human developers continue to provide immense value. Let's be real - LLMs are remarkable machines, but not everything is now automatable. Maybe because of the llms maturity, or maybe because of the inherent nature of creating software.
1 отметка «Нравится»

@Jessejrlim
I've not had this problem good architecture helps
1 отметка «Нравится»

@unclebobmartin
Good architecture helps indeed. A good suite of unit tests helps too. And if you have a good suite of integration tests then those could be your acceptance tests. If you don't have those tests, expect the quicksilver.
6 отметок «Нравится»
















