It will also combine correct things in incorrect ways, so even if everything it is trained on is correct it will still print incorrect things.
We see it in this article, both the statement "Indentation-based scoping, similar to Python" and the code with bracers were probably correct in their original contexts, but combined they are no longer correct. LLMs will make such errors no matter what kind of data you train it on, there is no known way to avoid that class of errors.
Yes, and imagine if StackOverflow questions are part of the training material. The "AI" will be learning from unfinished/unworking code samples.
> Programmers who think ChatGPT is going to replace their job must have a very low opinion of their own skill set.
As a devops guy I live in fear of anything that can copy and paste from stackoverflow faster than I can.
It will also learn all the bugs and reproduce them.
Programmers who think ChatGPT is going to replace their job must have a very low opinion of their own skill set.