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

221–230 of 479 posts

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

#221

Post by almostdeadguy »

dataviz1000 wrote: post #220
almostdeadguy wrote: post #181

Earlier quoted context omitted.

I feel like we're doomed to respond to these lazy analogies ad infinitum. Knowledge abstractions have historically been built by people with a detailed understanding of a problem domain and with a period of vetting the abstraction by many people. That is simply not true with LLM-generated code. We do not really understand what techniques LLMs are using to understand directions, value aesthetic/legibility characterist…

A computer used to be a term for an occupation. [0] > I have concerns that you'll have a job in a year Me too because I might be the best TypeScript coder on Earth and there is no demand for those skills. I'm doing a pivot. [0] https://en.wikipedia.org/wiki/Computer_(occupation)

I don't have any delusions about that, LLMs are impressively good. But they bring with them a host of epistemological problems that I think we ignore at our own peril. A society that blindly trusts the output of LLMs to be good and to make decisions that adhere to our own preferences and acceptance criteria is extremely dangerous! There's a growing call to sort of let LLMs cook and get out of the way, and I think there will be catastrophic problems if we give in to that.

As good as they are, they are still fallible. They still write bugs, they still misunderstand instructions. They even get defensive about bad choices! And even in a world where that appears to no longer be true, we will be making society extremely fragile if we give an alien intelligence total autonomy to do what they think is right.

If you're not going to be writing code, you better be a vigilant babysitter. Otherwise I firmly believe that more than your job is at stake.

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

#223

Post by nullsanity »

jader201 wrote: post #143
npras1 wrote: post #120

Big no for retyping llm generated code by hand. But a big yes for still typing code by hand, and not leaving it to the llm. Except it has to be the code generated by your brain. That is what will create new neurons and new connections, which is what will keep away the cognitive decline. And the constraint of not having to use llms will enhance creativity. Actually, the constraints llms add to your code are more in nu…

> But a big yes for still typing code by hand, and not leaving it to the llm. Except it has to be the code generated by your brain. > That is what will create new neurons and new connections, which is what will keep away the cognitive decline. 100% agree with this. The problem is, your employer doesn’t care whether your brain is creating new neurons and connections. They care about productivity and profit. I feel lik…

[dead]

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

#225

Post by m3kw9 »

npras1 wrote: post #120

Big no for retyping llm generated code by hand. But a big yes for still typing code by hand, and not leaving it to the llm. Except it has to be the code generated by your brain. That is what will create new neurons and new connections, which is what will keep away the cognitive decline. And the constraint of not having to use llms will enhance creativity. Actually, the constraints llms add to your code are more in nu…

so don't use LLMs? You cannot get away from it now, the skill lies in how to generate code small enough for you to digest, as opposed to vibe coder where they generate so much code, there is no way to read it but to accept the run test.

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

#226

Post by dwaltrip »

a2128 wrote: post #60

As someone who, at a point, would copy homework from someone else, copy book reports from online, and use the answer sheets to complete assignments, I can tell you this strategy is long known to accumulate and not prevent cognitive debt

If you do it mindlessly, I'm sure you are right. But one could try to understand and integrate each piece of code as they "copy" it over. May be hard to sustain though.

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

#227

Post by m3kw9 »

Thats nuts. You are fighting a tool that is supposed to offload that. Is like lets not use the power tool, but do it by hand so your muscles won't atrophy, but you should instead use it to free up your muscles for other tasks like better requirements, architecture, tests, UX design.

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

#229

Post by tp3358 »

podgietaru wrote: post #55
frankc wrote: post #10

Earlier quoted context omitted.

It could easily be the other way around - religious addiction for people can't let go of the code.

I don’t think so, because it’s being used as a way to try to remedy one of the new problems brought in by agentic coding - loss of context of what code does.

But if the code base is constructed in a way which results in strong test suites (human driven), quality evals, robust documentation, and modular implementation, will the human really lose that much context?

Given that those things are checked off, I am having a tough time believing a frontier model, in conjunction with a new dev on a project, can't be immediately valuable to determining what is going on in a repo.

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

#230

Post by tumdum_ »

chubot wrote: post #196
iwontberude wrote: post #166

Earlier quoted context omitted.

It's a moot point. In Mag7 companies internal code gets thrown away within 2 years on average because of contract negotiations, new opensource projects that obviate need for the internal codebase, license changes, layoffs, etc, etc. We don't need long term maintainability because its already on its way to the garbage bin. Frankly it's always been this way.

Its' the exact opposite ... Google, nVidia, Amazon, Apple, etc. all have a deep bench of code that is a moat. They have lots of throwaway code too, but those companies are precisely the ones that pay attention to code quality, and comprehensibility by experts A rough proxy for this would be if they say contribute to the C++ standards process, which Google Microsoft nVidia do, and basically zero "normal" companies (sa…

Is google still a big contributor to the c++ standard? I thought they are far less involved than a decade ago.
Post reply on HN