☆ Yσɠƚԋσʂ ☆

  • 565 Posts
  • 580 Comments
Joined 6 years ago
cake
Cake day: January 18th, 2020

help-circle













  • I can only go by what you say here which is frankly nonsense. I’ve explained to you that any serious software project relies on practices like tests and code reviews to ensure quality of the code being produced. Whether the code is written by a tool or a human is entirely beside the point. It should be treated the same way. Anybody who’s actually written code knows that humans are fallible and make plenty of mistakes, so your argument about hallucinations applies to human written code exactly the same way. The way to deal with it in both cases is by having contracts that the code fulfills. My intention is to correct misinformation that people such as yourself are spreading.



  • I gave you the benefit of the doubt initially assuming you simply haven’t used these tools. Now, you’ve come back and emphatically stated that you have. Given that what you describe is not how these tools work, it’s very clear that you are being dishonest by your own admission. Now you’re just using sophistry to paper over that.






  • Again, you’re discussing tools you haven’t actually used and you clearly have no clue how they work. If you had, then you would realize that agents can work against tests, which act as a contract they fill. I use these tools on daily basis and I have no idea what these surprises you’re talking about are. As a practitioner, I find these things plenty practical.