Hacker News Reader

Comment by powerset | Hacker News Reader

I've had a similar experience, shipping new features at incredible speed, then waste a ton of time going down the wrong track trying to debug something because the LLM gave me a confidently wrong solution.

View on HN

Well that's kind of on you for not noticing that it was the wrong solution, isn't it?

I think the parents post happened to everybody, and if it hasn’t it will.

The edge between being actually more productive or just “pretend productive” using large language models is something that we all haven’t completely figured out yet.

Sometimes the solution is 99% correct but the other 1% is so subtly wrong that it both doesn't work and is a debugging hell.

Welcome to programming.

Ya but you kind of get painted in corner sometimes. And sunken cost fallacy kicks in.

often it's something you casually overlook, some minor implementation detail that you didn't give much thought to that ends up being a huge mess later on, IME

It's on you however for not understanding the greater point?

Seems like LLMs would be well suited for test driven development. A human writes tests and the LLM can generate code passing all tests; ending with a solution that meets the humans expectations.

I disagree because you're only considering the "get code to make the test pass". Refactoring, refining, and simplifying is critical and I've yet to see this applied well. (I've also yet to see the former applied usably well either despite "write tests generate code" being an early direction.)

This is more or less how I use LLMs right now. They’re fantastic at the plumbing, so that I can focus on the important part - the business and domain logic.

Reply on news.ycombinator.com