Building an interpreter for my programming language with ChatGPT

Re:Building an interpreter for my programming language with ... by habibur on Sunday December 04, 2022 @07:54AM (#33853263)

Google, Wikipedia, and historically the internet had been unreliable for many of the queries. More so in the beginning. But over time most of the errors are ironed out. ChatGPT is a very promising start I would say.

In the end convenience wins out at cost of correctness. The proportion matters, convenience::correctness.

[ Parent | on HN ]

Re:Building an interpreter for my programming language with ... by jonathanstrange on Sunday December 04, 2022 @09:25AM (#33853944)

How so? Anyone who sincerely asks a question wants the answer to be 100% correct, or the person answering to make it clear that they have a low confidence or don't really know. If the answer is false but stated with certainty, it is not only useless, it can even be worse than useless. There are other quality dimensions for answers, of course, such as the right level of detail and comprehensibility for the person asking, but these are all useless if the answer is false in the first place.

[ Parent | on HN ]

Re:Building an interpreter for my programming language with ... by bastawhiz on Sunday December 04, 2022 @03:50PM (#33857741)

> ChatGPT is a very promising start

It is not the start. It is at least the third iteration (if not more) of this tech.

> In the end convenience wins out at cost of correctness.

There's nothing convenient about a wrong answer. Wrong answers have no value. I could very easily build you a convenient service that is rarely correct but nobody would care.

[ Parent | on HN ]