Hacker News Reader

Comment by HaphazardGuess | Hacker News Reader

A.I suffers from the last-mile problem. It can do 90% of the work in 20 minutes but then the remaining 10% ends up taking 20 million hours to actually finish. It frustrating to the point that I sometimes want to throw the whole thing out and start from scratch.

View on HN

Some people would argue that this is the best way to use AI as it exists today. Generate a POC and then if that POC makes sense, then rebuild it from scratch by hand. Maybe you can still use AI for a bit of boilerplate generation, but you should write all of the business logic and verify it by hand.

Personally, I'm starting to lean more and more towards this approach.

Though, I have to admit, for a well defined bug ticket, AI can be super useful to knock those out.

I find AI useful for boilerplate stuff, very generic code like mappers etc.

For more complex stuff, I find that the best workflow is usually treating AI like a kind of stupid, but very motivated intern you're pair programming with. Nothing unsupervised and you might have to touch up/do manually the really critical parts, but it can help with a lot of the bitchwork.

> Some people would argue

Who are these people? Where did they argue that?

That has been my experience at the beginning, but not anymore.

I have developed some intuition of how large tasks I can give it so that it will complete them well, probably erring on the conservative side.

I am using it daily for all my code writing and honestly don't remember the last time I had the feeling that I had to spend a lot of work to get the last few % done.

Reply on news.ycombinator.com