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

411–420 of 479 posts

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

#411

Post by dachris »

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.

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

#412

Post by locknitpicker »

vector_spaces wrote: post #398
locknitpicker wrote: post #389

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 I don't think this personal opinion holds well when contrasted with reality. The truth of the matter is that in moderately large cod…

I will say that yes, sadly, I have browsed through code written by people, and sadly also have browsed through code written by LLMs. Who do you suppose wrote the code the LLM was trained on? Divinity? I'm being tongue and cheek, but as someone who uses these things extensively in work and personal projects, I want to point out that it's new or novel that generating lots of plausible code is now vastly cheaper than it…

> I will say that yes, sadly, I have browsed through code written by people, and sadly also have browsed through code written by LLMs. Who do you suppose wrote the code the LLM was trained on? Divinity?

Training is a red herring. The root cause is constraints, or lack thereof. If you lock a junior dev in a basement and force him to deliver the same features that these LLMs output, you will see exactly the same type of slop. The root cause is that junior devs are inexperienced and oblivious to best practices and guidelines and even the team's internal standards. They output code unconstrained by these guidelines and thus output big balls of mud.

> I'm being tongue and cheek, but as someone who uses these things extensively in work and personal projects, I want to point out that it's new or novel that generating lots of plausible code is now vastly cheaper than it once was, so the scales are quite different.

I agree, but we need to be mindful of what is the actual root cause. I argue it's not AI coding agente but the diverse source of these code changes, which we also see in production settings in projects managed by large teams. In teams manned by junior devs you see very much the same slop building up to a big ball of mud in a few iterations. This is nothing new. What changed is that now ai coding assistants grant everyone access to what amounts to a large team of junior devs.

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

#413

Post by reconnecting »

radcod3 wrote: post #406
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.

> It was only with Claude Code that I realized I never actually enjoyed programming This is so real!

20 or 30 years ago, programming was reserved for people who were truly devoted to it, even when the work was a nightmare of difficulty.

Now, when I talk to programmers in their 20s and 30s and ask which program they first fell in love with, there's usually no answer.

I'm glad they've stopped pretending otherwise.

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

#414

Post by larodi »

Drupon wrote: post #409
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.

[flagged]

yes, it also exposed lots of hidden talent, which is more important. and fakers are nowhere to go, but LLMs are indeed a litmus test for them.

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

#415

Post by embedding-shape »

Drupon wrote: post #409
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.

[flagged]

> 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.

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

#416

Post by mcosta »

Always42 wrote: post #381
jgord wrote: post #364

Earlier quoted context omitted.

I worry about the finger-on-the-scale mean-reversion aspect of this .. the LLM corralling you ever so gently back towards the median. otoh, LLMs really could become the great illustrated primer for educating kids in science / history / languages etc.

Isn't median code often a good thing in terms of ability for others to understand it?

Well, the objetive right now seems to be other LLMs understand it.

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

#417

Post by frumiousirc »

ablob wrote: post #329

So we are reduced to code monkeys mindlessly re-typing what an LLM wrote to increase potential understanding... Whatever this approaches, it is not a state of software engineering I find desirable.

I think this characterization misses the feedback loop that exists.

The OP is not sitting in a one-way flow of info:

    LLM->human->code
but rather a the center of a feedback loop:

    LLMhumancode.
Human-is-the-loop, not human-in-the-loop. Each iteration of that loop is fully driven by the human. Human creativity is involved in both directions.

I'd argue that anytime we drive an LLM through more than one turn (and/or more than one session) we are really doing a human-is-the-loop thing. The OP's extreme case of begin the only thing editing code is on a spectrum with the other extreme being vibe coding (never looking at output code, but still interacting with that output in some way).

Off the spectrum is what I call LLM-vomit. A human one-shots something and puts it out for others to see, suffer and clean up or ignore. This is code that is encountered literally out of context and can only be further improved (if that is even attempted) by approaching it from first principles. Such code is akin to people using LLM to generate an answer delivered to another human. Both flavors (sorry) of LLM-vomit are bad. I can prompt my own LLM to do that, don't do it for me.

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

#418

Post by frumiousirc »

WhyComboNadir wrote: post #191
theappsecguy wrote: post #183

Earlier quoted context omitted.

I feel like you think the car analogy was a clever parallel to draw here but looking at a car centric north american population and the dimensions of a non trivial slice of them that are unable to walk a 5k, id say you made the opposite point.

You have a point based on the way I wrote it. What I was trying to get at: If you're going to walk to the store, don't push you car there! Just walk. So if you want to write code, don't retype what the LLM said, create your code from your own brain.

Of course I push my car to the store! It has the GPS and I've lost the ability to self-navigate. Plus, how else could I carry my groceries.

:)

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

#420

Post by embedding-shape »

tetha wrote: post #394
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…

> People are, in heavy LLM systems, realising that the most valuable commodity is engineers knowing WTF is going on, and that loss of understanding of your codebase is the #1 blocker to actually getting things done. Any senior engineer knows this all too well I've been pushing against this "maximum LLM driven speed" in our infrastructure as well and been working on a middle ground: We can generate a change to Ansible…

Yup, this is how I see teams who care about quality, design and architecture seems to use LLMs, not to "produce more and faster" but to retain same speed but with a lot more confidence and reliability. Hoping this will spread eventually, some companies seem to take a more... hazardous approach to the whole thing.
Post reply on HN