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

Prevent cognitive debt by manually retyping LLM-generated code

ankursethi.com

Post reply on HN
Print view View original

471–479 of 479 posts

Re: Prevent cognitive debt by manually retyping LLM-generated code

#471

Post by embedding-shape »

Drupon wrote: post #468
embedding-shape wrote: post #415

Earlier quoted context omitted.

> Poor coders have always existed. You're not the first and won't be the last. Did you get so emotionally hurt by another person saying they didn't want to actually type code anymore, that you felt the need to tell them they're likely a "poor coder"? You can still continue to type code if you'd like, no need to put others down because you prefer a different way of working.

Sorry, I'm not here to talk about your feelings. I am not "emotionally hurt", nor should you be. This is HackerNews and you're a grown ass adult (I assume). If you disagree with me, then feel free to outline your disagreement, or just ignore and move on.

> then feel free to outline your disagreement

My disagreement comes from feeling the need to put others down because they said something you didn't like. Nothing in their comments talks about if they're a good/bad programmer, clearly your putdown comes from a place of hurt. But no worries, lets ignore it from now on out, hope it gets better for you mate!

Re: Prevent cognitive debt by manually retyping LLM-generated code

#472

Post by nullbio »

elzbardico wrote: post #345
nullbio wrote: post #340

A better interface for code review would be a pseudocode layer that sits on top of all of your code, at the editor level. Basically it would convert all of the chunks of your code using an LLM to simple pseudocode with clickable symbols so you can follow function calls, definitions, then you could expand/collapse it to see the real underlying code.

I know how to program, why do I need things to be converted to pseudo code?

It's easier to skim pseudocode than it is to reason about complex logic. When I say pseudocode I'm talking very high level but structured explanations, and less the sort of traditional pseudocode you'd imagine which is basically just a generalization over syntax.

Re: Prevent cognitive debt by manually retyping LLM-generated code

#473

Post by dns_snek »

gw32 wrote: post #305
dns_snek wrote: post #131

Earlier quoted context omitted.

Of course you learn more if you retype material than if you do nothing, but it's still a waste of time, comparatively speaking, because there are much better ways of engaging with the material like solving practice problems. Having to spend 95% of the time taking notes of things that could be distributed in a PDF has only ever hindered me academically. It's mechanical and boring, my mind tunes out and I get nothing o…

Am I the only one who enjoys taking notes? But more in the sense of recording knowledge so that I have it in perpetuity. For instance, I have almost completely forgotten how to solve ODEs, even though I had a good command of it when I learned it (by solving practice problems). In that sense, I wish that my prior self had taken good notes, so that I wouldn't have to dig up source material if I wanted to relearn it aga…

It's not that I don't enjoy taking notes - I liked to take notes, distill knowledge, make "cheatsheets" outside of class.

To this day I still take countless notes when I learn new things, I just find it incredibly distracting to have to take notes during a lecture/class because it doesn't allow me to process the material properly.

Re: Prevent cognitive debt by manually retyping LLM-generated code

#474

Post by shadim80 »

locknitpicker wrote: post #389
20k wrote: post #365

Earlier quoted context omitted.

LLM speedups have always been predicated on not understanding the code they produce as well as if you wrote it yourself. Reviewing even well written code to understand it in depth, has always taken longer than simply writing it yourself - let alone sloppy LLM code that you have to fix People are, in heavy LLM systems, realising that the most valuable commodity is engineers knowing WTF is going on, and that loss of un…

> LLM speedups have always been predicated on not understanding the code they produce as well as if you wrote it yourself. Reviewing even well written code to understand it in depth, has always taken longer than simply writing it yourself - let alone sloppy LLM code that you have to fix I don't think this personal opinion holds well when contrasted with reality. The truth of the matter is that in moderately large cod…

[flagged]

Re: Prevent cognitive debt by manually retyping LLM-generated code

#475

Post by Drupon »

embedding-shape wrote: post #471
Drupon wrote: post #468

Earlier quoted context omitted.

Sorry, I'm not here to talk about your feelings. I am not "emotionally hurt", nor should you be. This is HackerNews and you're a grown ass adult (I assume). If you disagree with me, then feel free to outline your disagreement, or just ignore and move on.

> then feel free to outline your disagreement My disagreement comes from feeling the need to put others down because they said something you didn't like. Nothing in their comments talks about if they're a good/bad programmer, clearly your putdown comes from a place of hurt. But no worries, lets ignore it from now on out, hope it gets better for you mate!

I'm doing just fine; no need for the passive aggressive bitchiness. Just say what you mean.

Re: Prevent cognitive debt by manually retyping LLM-generated code

#476

Post by cylee3 »

wahern wrote: post #13

Good advice yesterday, good advice today, and good advice tomorrow. I don't remember if I read this advice or just intuited it myself (perhaps after some hard lessons), but it's a programming habit I've kept for as long as I can remember (I started coding in the 90s). If I feel rushed, e.g. someone looking over my shoulder, and I copy+paste something, it always leaves me with a sense of unease. It creates a memory &…

[flagged]

Re: Prevent cognitive debt by manually retyping LLM-generated code

#477

Post by aucisson_masque »

Anamon wrote: post #391
aucisson_masque wrote: post #374

> might not be the most efficient way to work with an LLM, but I value comprehension over productivity. LLM are becoming so good that they are better than us at understanding code. And it's only going to get worst every year. I think that the job of 'coding' is done, it's dying and will be effectively dead in a decade. You better find ways to make yourself usable around LLM work but not by doing what LLM already do.

LLMs don't understand a damn thing. They can't. They're not built to. An LLM doesn't "understand" its own slop. It can use that slop as further input for generating more slop on top of it, but at no point of the process does anything like a concept or understanding come in.

I know it's not supposed to understand but it's just so good at faking it, and being right, that at some point we can claim it's 'underdtanding' it.

Or you'd have to invent a new word.

Re: Prevent cognitive debt by manually retyping LLM-generated code

#479

Post by embedding-shape »

Drupon wrote: post #475
embedding-shape wrote: post #471

Earlier quoted context omitted.

> then feel free to outline your disagreement My disagreement comes from feeling the need to put others down because they said something you didn't like. Nothing in their comments talks about if they're a good/bad programmer, clearly your putdown comes from a place of hurt. But no worries, lets ignore it from now on out, hope it gets better for you mate!

I'm doing just fine; no need for the passive aggressive bitchiness. Just say what you mean.

How am I not already saying what I mean? What exactly is unclear here? This was what you initially said:

> Poor coders have always existed. You're not the first and won't be the last.

And somehow I'm the one with the passive aggressive bitchiness? :P Enjoy your Saturday mate.

Post reply on HN