Hacker News Reader

Comment by kossTKR | Hacker News Reader

But if this development continues AI will surely be able to just parse the entire frontend, then look at the repo, then look at the specifications, then when you ask for a specific feature it will instantly implement it gracefully.

I don't see why it wouldn't understand piles of hotfixes on top of each other, or even refactor technical debt in tight coupling with existing or historical specification.

Or is there a reason this is not going to happen in a few years?

View on HN

I very much doubt it. "Revert Norway tax code" or "add content restrictions for Turkey" cannot necessarily be deduced from the codebase. And there are thousands of product requirements like that.

It might become a better code assist tool some 10 years from now, but it won't be able to implement product decisions.

It depends. Did you ever work in Development Support? Understanding requests or bug reports from customers is quite challenging, for trained and experienced developers. In my eyes that would require AGI, which we do not know of, if that can be achieved with the current approach.

I actually did , and yes it's extremely challenging and can be rather rage inducing; "it doesn't work" --> what doesn't work --> "the thing" --> what thing --> ∞ ...

But the thing is conversations like the above ie. both external support and internal feature requests could theoretically be handled by a GPT-like system also ending up in a ai created custom specification that could both be implemented and documented by the ai system instead of humans?

I know we're a few versions out, but still.

If just being persistent and willing to iterate solves the issue, then yes, GPT-like systems could do that. If you have to employ creative thinking to even find out what the customer wants, then check it in the system, debug some processes and derive the desired feature or correction, then we are very far from having such a tool, IMHO.

/s?

Reply on news.ycombinator.com