this post was submitted on 18 Mar 2026
747 points (92.2% liked)
Technology
82798 readers
3191 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
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.
I wasnt building test cases :)
The point was that AI can use playwright and write in C# just fine. Tests was an example of that.
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.
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.