HACKER Q&A
📣 ohjeez

Biggest misconceptions about using generative AI in programming?


You can’t throw a broken slipstick without reading another article about the ways software engineers use (or should use) generative AI to write their applications. Most of them promise better developer productivity. And plenty of people are adopting it: according to a StackOverflow 2023 developer survey, 70% of developers are using or are planning to use AI tools in their development process.

But “Yeah, let’s jump on board!” doesn’t mean that every developer should dive right in, or do it in the same way. Despite its value, generative AI isn’t ideal in all situations – particularly when programmers make wrong assumptions about its use. So I’m writing a blog post that aims to debunk the mistaken beliefs so that you can use generative AI the right way.

So:

* What is the biggest misconception you have encountered regarding using generative AI to improve programming productivity?

* What's the issue with it? Why is it a problem, and (if appropriate) what should the right path be?

  👤 Doctor-R Accepted Answer ✓
Is the generated code correct? Was the training input code correct? Did the AI understand what you were asking? Did you specify the problem correctly, with all of the boundary conditions?

If AI programming is so good, why are there so many zero-day bugs in Windows?

👤 blackbear_
> What is the biggest misconception you have encountered regarding using generative AI to improve programming productivity?

That typing is the bottleneck and that all we need is a way to type faster.