Hacker News new | ask | show | jobs
by mostertoaster 262 days ago
> And sure, if you can express your intent clearly in English

I think it is underestimated how difficult this truly is.

And this will always remain uniquely human because only The human truly knows their intent (sometimes).

I’ve had the AIs (ala the google) after I say “make me a script that does XYZ”, say here you go, and if I asked does it work and it tests it out will say yep it does, but only I will know if it is actually doing what I intended. I often will have to clarify my intent because I didn’t communicate well the first time. As we’ve all seen even amongst humans to each other, intent is not always well expressed.

There will always be a judgement made by a human with yes that is my intent or no it is not.

But even in old days of writing the “code” itself, most bugs were you not precisely saying what you wanted the program to do.

I think it’s correct to think of LLMs as compiling English to code, like c++ getting compiled to assembly.

3 comments

The irony is that over the last decades we have come up with languages that try to remove the ambiguity. Some close to English, some not. The very specific "this is what I want you to do" languages. Almost like they are...describing the program you want to create. Might even wanna call them a programming language :D
Go has 25 keywords. C has 32. Famously verbose Visual Basic has over 200.

English has 1-2 million.

I’d only count closed-class words as keywords. Open-class words, which comprise the vast majority of the dictionary, are more like a standard library.
You can't communicate at all with only closed class words. You can write fully capable programs with only built-in keywords though, so I wouldn't make that comparison.
Not sure a keyword only C program can communicate, either. printf isn't a keyword...
It won’t be portable or a good idea but you can use os/hardware specific directives.

But this is drifting. The point of it all is that the ambiguity of programming languages are already high despite all our best efforts.

The ambiguity of natural language is many orders of magnitude worse.

Which is great for poetry but we’re not writing poetry.

Anybody who has worked in requirements management in any meaningful capacity understands this…