Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI coding and the peanut butter and jelly problem

iamcharliegraham.substack.com

Post reply on HN
Print view View original

11–20 of 83 posts

Re: AI coding and the peanut butter and jelly problem

#11

Post by geor9e »

zahlman wrote: post #6

Okay, but like. If you do have that skill to communicate clearly and describe the requirements of a novel problem, why is the AI still useful? Actually writing the code should be relatively trivial from there. If it isn't, that points to a problem with your tools/architecture/etc. Programmers IMX are, on average, far too tolerant of boilerplate.

>Actually writing the code should be relatively trivial

For you, maybe. This statement assumes years of grueling training to become bilingual in a foreign programming language. And I can't type at 1000 tokens/s personally - sometimes I just want to press the voice dictate key and blab for five seconds and move on to something actually interesting.

Re: AI coding and the peanut butter and jelly problem

#13

Post by zahlman »

simonw wrote: post #8
zahlman wrote: post #6

Okay, but like. If you do have that skill to communicate clearly and describe the requirements of a novel problem, why is the AI still useful? Actually writing the code should be relatively trivial from there. If it isn't, that points to a problem with your tools/architecture/etc. Programmers IMX are, on average, far too tolerant of boilerplate.

Once you've got to a detailed specification, LLMs are a lot faster at correctly typing code than you are.

In your analysis, do you account for the time taken to type a detailed specification with which to prompt the LLM?

Or the time to review the code - whether by manual fixes, or iterating with the prompt, or both?

Re: AI coding and the peanut butter and jelly problem

#14

Post by zahlman »

geor9e wrote: post #11
zahlman wrote: post #6

Okay, but like. If you do have that skill to communicate clearly and describe the requirements of a novel problem, why is the AI still useful? Actually writing the code should be relatively trivial from there. If it isn't, that points to a problem with your tools/architecture/etc. Programmers IMX are, on average, far too tolerant of boilerplate.

>Actually writing the code should be relatively trivial For you, maybe. This statement assumes years of grueling training to become bilingual in a foreign programming language. And I can't type at 1000 tokens/s personally - sometimes I just want to press the voice dictate key and blab for five seconds and move on to something actually interesting.

>This statement assumes years of grueling training to become bilingual in a foreign programming language

...So, less experienced programmers are supposed to be happy that they can save time with the same technology that will convince their employers that a human isn't necessary for the position?

(And, frankly, I've overall quite enjoyed the many years I've put into the craft.)

Re: AI coding and the peanut butter and jelly problem

#15

Post by grahac »

csours wrote: post #3
grahac wrote: post #2

Anyone here see the CS50 peanut butter and jelly problem in person?

Not in that course, but I've done it at a "STEM" day; it's just about the most fun I've ever had teaching.

That's awesome.

I got the sense the professor liked it a ton too. In the videos of this on YouTube you can see the professor really enjoying watching it all go down.

It still is so memorable.

Re: AI coding and the peanut butter and jelly problem

#17

Post by simonw »

zahlman wrote: post #13
simonw wrote: post #8

Earlier quoted context omitted.

Once you've got to a detailed specification, LLMs are a lot faster at correctly typing code than you are.

In your analysis, do you account for the time taken to type a detailed specification with which to prompt the LLM? Or the time to review the code - whether by manual fixes, or iterating with the prompt, or both?

No, just the time spent typing the code.

Re: AI coding and the peanut butter and jelly problem

#18

Post by kenjackson »

This is actually no different than for humans once you get past the familiar. It's like the famous project management tree story: https://pmac-agpc.ca/project-management-tree-swing-story

If anything, LLMs have surprised at much better they are than humans in understanding instructions for text based activities. But they are MUCH worse than humans when it comes to creating images/videos.

Re: AI coding and the peanut butter and jelly problem

#19

Post by recursivegirth »

simonw wrote: post #17
zahlman wrote: post #13

Earlier quoted context omitted.

In your analysis, do you account for the time taken to type a detailed specification with which to prompt the LLM? Or the time to review the code - whether by manual fixes, or iterating with the prompt, or both?

No, just the time spent typing the code.

Time to first iteration is a huge metric that no one is tracking.

Re: AI coding and the peanut butter and jelly problem

#20

Post by layer8 »

simonw wrote: post #8
zahlman wrote: post #6

Okay, but like. If you do have that skill to communicate clearly and describe the requirements of a novel problem, why is the AI still useful? Actually writing the code should be relatively trivial from there. If it isn't, that points to a problem with your tools/architecture/etc. Programmers IMX are, on average, far too tolerant of boilerplate.

Once you've got to a detailed specification, LLMs are a lot faster at correctly typing code than you are.

As a developer, typing speed is rarely the bottleneck.
Post reply on HN