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

441–450 of 479 posts

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

#441

Post by brabel »

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…

Thank you for writing exactly why people who complain about LLMs making it harder to understand what’s going on are so off. Nothing helps more than asking LLMs to tell you exactly what’s going on! They are insanely good at that. I wrote the plugin system in my product, but many people added to it over a decade and today I have only high level knowledge of it. But if I need to know something about a very specific part of it, I ask Claude and now I know exactly what I needed to know. I could even write the code by hand now, and sometimes I do for the fun of it, but Claude has just explained to me, so it also knows exactly how to do it so why not let it do it?? I can understand as much as I need to by reading the code , asking questions, carefully analyzing the tests, much more than I would if I had needed to focus on every single detail that is irrelevant to the task. Sometimes I even do some minor refactoring just to try and feel like I’m “inside” the code as I used to. But I know I will likely be out of the loop again in 3 or 4 years, as I just can’t remember everything I ever did. But now I have a LLM ready to help me get into it again whenever needed again.

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

#442

Post by inigyou »

brabel wrote: post #439
big_paps wrote: post #396

As someone who’s been programming for 20 years, I have to say that programming itself often causes a kind of brain rot. I’m very glad that I can now focus on other aspects of software development. It was only with Claude Code that I realized I never actually enjoyed programming—I enjoyed building things. You can live a perfectly mentally healthy life without programming.

I would say any programmer has found themselves so deep in the metaphorical woods that they forgot what they were actually trying to achieve in the first place. For example, you start because your boss told you to implement a new feature, but you realized there was no module you could place the feature in, then by looking at the existing module structure you realized it had become completely unsuitable in general, th…

That's called yak shaving.

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

#444

Post by quietbritishjim »

1718627440 wrote: post #431
quietbritishjim wrote: post #85

Earlier quoted context omitted.

Taking down the lesson/lecture does relatively little, you can do it on autopilot. If anything, it distracts from listening to the content. When I took computer science at university (mid naughties) we were given digital lecture notes anyway. (Mathematics lectures did have to be written down but there were no typed notes to start with so it was just out of necessity.) It's the exercises afterwards that are useful for…

> Taking down the lesson/lecture does relatively little Not my experience. > you can do it on autopilot Huh, that sounds magically to me, I certainly can't. Actually taking notes down does the opposite, it forces you to get out of the autopilot, because you must think about the content. Taking notes down, helps you learn better, because you use way more brain areas to process the information. Instead of just hearing,…

Fair enough. We all learn differently. For me, having printed lecture notes meant I could listen (imperfectly!) in lectures rather than focusing on copying. It was a revelation after years of exhausting lectures doing nothing but writing.

I now realise that sounds a bit like a contradiction. I said I could copy on autopilot but also I had to focus on it. I suppose it was more like the second one: I was so focused on copying verbatim (as furiously as I could as there was barely time to do it before it was rubbed out!) that I didn't have a chance to think about the content.

> > Or summarising notes in your words.

> Which is what you do, if you take down notes.

I certainly disagree with this. No one I knew was rephrasing the lecturer's notes in their own terms. There was no time for that. That is something you'd have to do in your own time afterwards, at a much slower pace.

> > but there were no typed notes to start with so it was just out of necessity

> The necessity was created by the teachers in order to get the students to learn.

I assure you, the main reason those maths lecturers didn't spend countless hours typing up their handwritten notes in LaTeX was not the best interests of the students!

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

#445

Post by dev0p »

big_paps wrote: post #396

As someone who’s been programming for 20 years, I have to say that programming itself often causes a kind of brain rot. I’m very glad that I can now focus on other aspects of software development. It was only with Claude Code that I realized I never actually enjoyed programming—I enjoyed building things. You can live a perfectly mentally healthy life without programming.

Programming, as in manually typing the code, is a means to an end.

While I do enjoy coding, building things is what was rewarding, not actually laying down brick after brick after brick after brick.

I've done that for 10+ years. The fact that I don't have to do that anymore is a relief that cannot be overstated. I only have to check on the code that The Ideal Intern produces while I focus on what actually matters, and that is: Building The Thing.

It's all about how you use it and how careful you are with it, and the fact that today there are people IN THE FIELD that still question this baffles me.

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

#446

Post by jaggederest »

richardbarosky wrote: post #408
jaggederest wrote: post #351

Earlier quoted context omitted.

Ben if you're going to blog about things with relative timestamps you need to provide a base timestamp, and I would also appreciate that for when you update the post. "3 months ago" is unhelpful without that context. Well done for registering your beliefs publicly and updating them publicly. So many people out here exist in an epistemology-free zone.

I'm seeing what looks like a date in the top-right corner of the header banner. Not sure if it was added in response to the note, so mentioning just in case!

ah you're right, it was just subtle, mea culpa

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

#447

Post by veber-alex »

20k wrote: post #365
bigbuppo wrote: post #332

Also... if your workflow is "think hard, let LLM write it, read what AI wrote, think hard about what AI wrote, re-type what AI wrote, fix what AI wrote"... Where in the heck are the efficiency gains? Couldn't you just drop the LLM part of it and save the company a trillion dollars in tokens?

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 am at least 3x more productive by letting an LLM write my code and I review and understand every single line it writes.

Also, Fable 5 came up with some amazing solution and designs that I would have never been able to do myself.

I can say with 100% surety that my current project at work is MUCH better with an LLM compared to if I wrote it myself.

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

#449

Post by eythian »

dingocat wrote: post #380
throwaway120381 wrote: post #342

Earlier quoted context omitted.

Don't worry. No one will want human code in just a few years. This bizarre fixation that humans are decent at coding is a myth. Retype what the machine tells you? I would rather garden or move rocks around.

I used to like listening to music and reading books. Now my AI agent does it for me and it's so much faster at it than I used to be.

“The Electric Monk was a labour-saving device, like a dishwasher or a video recorder. Dishwashers washed tedious dishes for you, thus saving you the bother of washing them yourself, video recorders watched tedious television for you, thus saving you the bother of looking at it yourself; Electric Monks believed things for you, thus saving you what was becoming an increasingly onerous task, that of believing all the things the world expected you to believe. Unfortunately”

― Douglas Adams, Dirk Gently's Holistic Detective Agency

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

#450

Post by cousinbryce »

dachris wrote: post #411
big_paps wrote: post #396

As someone who’s been programming for 20 years, I have to say that programming itself often causes a kind of brain rot. I’m very glad that I can now focus on other aspects of software development. It was only with Claude Code that I realized I never actually enjoyed programming—I enjoyed building things. You can live a perfectly mentally healthy life without programming.

Fully agree that programming for me brings along "a kind of brain rot". Hard to describe, but working deep in code just shifts the mind to a state that's ... less open, more focused, more obsessive ... and seeps into daily life. Vernor Vinge's concept of "focus" in "A deepness in the sky" really clicked with me and put into words what I'd always had at the back of my mind. A highly recommended read.

I read it because Elon Musk mentioned it as a favorite. It’s a good book and you can see how the concept of controlling ubiquitous tech is a thing he tries to do
Post reply on HN