logoalt Hacker News

jdw64 • today at 8:04 PM • 0 replies • view on HN

I’ve used it a bit, and I think the GPT model writes code well, but it’s always overly defensive code—though that’s ultimately a matter of personal preference—and it tends to write too many tests. I can understand the defensive code, but it feels like if you give it a task of size 1, it writes tests of size 3.