Plain copy paste without a critical view is not recommended, but it surely provides good pieces of code from time to time. Especially in obscure frameworks/languages, compared to what can be googled.
ChatGPT 4 is a really big difference with 3.5 though. What took me hours together with the 3.5, was fixed in a few minutes with 4.
deleted by creator
This. I always use that example, ChatGPT is stack overflow or a very eager intern. Review and make test cases
Man, it’s great until it contently feeds you incorrect information. I’ve been burned far too many times at this point…
deleted by creator
I only verify information I get on the Internet if I don’t agree with it or need to use it in an argument, and I’m not about to change
Oof, glad I’m not alone
Wait…
TBH, if you can’t almost instantly figure out why and how ChatGPT suggested bad code, you shouldn’t be using it at all - you’re out of depth.
It’s why I’ll gladly use it to suggest markdown or C code, but never for a complex Python library.
Blaming the AI for misinformation is like blaming Google for giving you bad search results.
Learn how to parse the data and fact check it. Usually you can get a hyperlink to the source to see if it’s even reasonably trustworthy.
Plain copy paste without a critical view is not recommended, but it surely provides good pieces of code from time to time. Especially in obscure frameworks/languages, compared to what can be googled.
ChatGPT 4 is a really big difference with 3.5 though. What took me hours together with the 3.5, was fixed in a few minutes with 4.