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

51–60 of 83 posts

Re: AI coding and the peanut butter and jelly problem

#51

Post by Arn_Thor »

geor9e wrote: post #27
zahlman wrote: post #14

Earlier quoted context omitted.

>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.)

You're seeing this entirely from the perspective of people who do programming as their job. I'm seeing it from the perspective of the other 99% of society. It feels really good that they're no longer gatekept by the rigid and cryptic interfaces that prevented them from really communicating with their computer, just because it couldn't speak their native tongue.

Yep! I’m digitally literate but can’t do anything more advanced than “hello world”. Never had the time or really interest in learning programming.

In the last year I’ve built scripts and even full fledged apps with GUIs to solve a number of problems and automate a bunch of routine tasks at work and in my hobbies. It feels like I woke up with a superpower.

And I’ve learned a ton too, about how the plumbing works, but I still can’t write code on my own. That makes me useful but dependent on the AI.

Re: AI coding and the peanut butter and jelly problem

#52

Post by tharant »

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.

This is one reason I see to be optimistic about some of the hype around LLMs—folks will have to learn how to write high quality specifications and documentation in order to get good results from a language model; society desperately needs better documentation!

Re: AI coding and the peanut butter and jelly problem

#53

Post by barotalomey »

kenjackson wrote: post #18

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.

> If anything, LLMs have surprised at much better they are than humans in understanding instructions for text based activities.

That's demonstrateably false, as proven by both OpenAI's own research [1] and endless independent studies by now.

What is fascinating is how some people cling on false ideas about what LLM is and isnt.

Its a recurring fallacy that's bound to get it's own name any time soon.

1: https://news.ycombinator.com/item?id=43155825

Re: AI coding and the peanut butter and jelly problem

#54

Post by LikesPwsh »

MBCook wrote: post #30
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.

Exactly. This same point was mentioned on Accidental Tech Podcast last week during a section primarily about “vibe coding”. (May have been the paid-only segment) If the LLM gets something wrong, you have to be more exact to get it to make the program do the thing you want. And when that isn’t perfect, you have to tell it exactly what you want to to do in THAT situation. And the next one. And the next one. At that poi…

I realise this is meant to be a jab at high-level programming languages, but SQL really did succeed at that.

Its abstraction may leak sometimes, but most people using it are incredibly productive without needing to learn what a spool operator or bitmap does.

Even though the GUI and natural language aspects of 4GL failed, declarative programming was worth it.

Re: AI coding and the peanut butter and jelly problem

#55

Post by taurath »

derefr wrote: post #41
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.

An LLM is a very effective human-solution-description / pseudocode to "the ten programming languages we use at work, where I'm only really fluent in three of them, and have to use language references for the others each time I code in them" transpiler. It also remembers CLI tool args far better than I do. Before LLMs, I would often have to sit and just read a manpage in its entirety to see if a certain command-line t…

I’ve found that the surfacing of tools and APIs really can help me dive into learning, but ironically usually by AI finding a tool and then me reading its documentation, as I want to understand if it has the capabilities or flexibility I have in mind. I can leave that to LLMs to tell me, but I find it’s too good an opportunity to build my own internal knowledge base to pass up. It’s the back and forth between having an LLM spit out familiar concepts and give new to me solutions. Overall it helps me get through learning quicker I think, because I can often work off of an example to start.

Re: AI coding and the peanut butter and jelly problem

#57

Post by dsjoerg »

derefr wrote: post #38

> Today’s AI Still Has a PB&J Problem If this is how you're modelling the problem, then I don't think you learned the right lesson from the PB&J "parable." Here's a timeless bit of wisdom, several decades old at this point: Managers think that if you can just replace code with something else that isn't text with formal syntax , then all the sudden "regular people" (like them, maybe?) will be able to "program" a syste…

You're right about everything except you underestimate the current generation of LLMs. With the right prompting and guidance, they _already_ can give pushback and ask questions until satisfied.

Re: AI coding and the peanut butter and jelly problem

#58

Post by otabdeveloper4 »

barotalomey wrote: post #53
kenjackson wrote: post #18

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.

> If anything, LLMs have surprised at much better they are than humans in understanding instructions for text based activities. That's demonstrateably false, as proven by both OpenAI's own research [1] and endless independent studies by now. What is fascinating is how some people cling on false ideas about what LLM is and isnt. Its a recurring fallacy that's bound to get it's own name any time soon. 1: https://news.y…

People think coding is the difficult part of programming.

Which it isn't, just like pressing keys isn't the difficult part of being a pianist.

If they invented a machine to press piano keys with superhuman speed and precision that wouldn't make you a musician.

Re: AI coding and the peanut butter and jelly problem

#60

Post by otabdeveloper4 »

geor9e wrote: post #34
wrs wrote: post #32

Earlier quoted context omitted.

The point of the PB&J thing is exactly to demonstrate that your native tongue isn’t precise enough to program a computer with. There’s a reason those interfaces are rigid, and it’s not “gatekeeping”. (The cryptic part is just to increase information density — see COBOL for an alternative.)

I think https://docs.cursor.com/chat/agent has shown plain English is precise enough to program a computer with, and some well respected programmers have become fans of it https://x.com/karpathy/status/1886192184808149383 I only took exception to the original statement - that coding is trivial, and the questioning if AI is even useful. So many people are finally able to create things they were never able to. That's s…

> plain English is precise enough to program a computer with

Only if your problem is already uploaded on Github.

Post reply on HN