Comment

Comment on Sam Altman Thanks Programmers for Their Effort, Says Their Time Is Over

ready_for_qa@programming.dev ⁨2⁩ ⁨days⁩ ago

Then your input is wrong. I mainly work in .net c# and playwright and I have agents building my e2e tests in playwright with just test cases and test steps. These are custom agents I built myself that have the guardrails in place for the agent to stay in bounds.

source

Sort:hotnew top

MangoCats@feddit.it ⁨2⁩ ⁨days⁩ ago
The agents are getting pretty good at reviewing code, too. You don’t have to listen to everything they say, but they do point out a lot of stuff that you pretty much have to admit: yeah, that would be better if I changed it to the suggested revision.

source
Goldholz@lemmy.blahaj.zone ⁨2⁩ ⁨days⁩ ago
I wasnt building test cases :)

source
- ready_for_qa@programming.dev ⁨2⁩ ⁨days⁩ ago
  The point was that AI can use playwright and write in C# just fine. Tests was an example of that.
  
  source
  - MangoCats@feddit.it ⁨2⁩ ⁨days⁩ ago
    Tests are a great use for AI coding, lately. Six months ago Claude Sonnet was writing tests that always passed without testing anything, that has improved dramatically with Opus 4.5/4.6 - it actually hits the functionality now, not just code coverage.
    
    source