Live data from Hacker News

Prevent cognitive debt by manually retyping LLM-generated code

ankursethi.com

291–300 of 479 posts

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

#292

Earlier quoted context omitted.

> Well there’s a lot of middle ground between “don’t use AI” and “generate everything.” Sure, but again, this assumes both that handwriting code sometimes outperforms LLMs, and also that your employer agrees with this. I think it’s only a matter of time (again, if we’re not already there) before LLMs outperform handwritten code nearly all of the time. And, even if that’s not the case, I’m pretty convinced nearly all…

this pure speculation. maybe you're right that it's a matter of time but /maybe you're wrong/. neither of us can actually know, because you're making predictions about the future rather than claims about what is true today

I'm REALLY REALLY not enjoying this current middle ground where we may be on the cusp of LLMs writing all code better than I could OR we may be on the cusp of realising that this is a chimera.

Mostly I just want to skip forward to the point where we find out which track we're on, because until we know, I feel constantly tense.

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

#294

Lots of reactions here, but if it works for you then that's great. For me I feel that LLMs have exploded (in a good way) my cognitive capabilities. I'm now the general of an army, rather than playing the role of a soldier. Of course that means that I lose the experience of being the lonely soldier, but it is a no-brainer tradeoff for me. Anyway, I have to go now so I can push my car to the grocery store (so I don't f…

Don’t good generals know how everyone else in their army does their jobs? At the very least to the extent they can see through the bullshit. For example, I don’t handwrite the code that the compiler produces, but I know how to troubleshoot the IR/assembly and fix optimization issues that arise occasionally. That makes me better at my job of directing the compiler.

> Don’t good generals know how everyone else in their army does their jobs?

They most certainly do, but on a mid-higher level. They don't probably know every single motion and definitely lack hands-on experience. But they know enough to be able to manage them efficiently.

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

#295
In the life of the LLM, we're still in the phase where we're all on the floor playing with these toys. It's strange to assume cognitive debt is an absolute outcome in this new paradigm of engineering when nobody really knows what the future holds. Personally, I feel like I have more time to think, not less, but that's also just my experience. Part of the fun of this is that we're all science experiments right now.

I'm just kind of enjoying the feeling of riding on the swell of a gigantic wave for once instead of feeling like I'm starting from behind it.

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

#297
post #202

In my love(?)-hate relationship with "vibecoding", even I tried this approach. For a while it worked, though that "while" didn't last as long as the months OOP has been riding this wave. Though, the vibes have usually been off, so I wish I could keep both thinking of and writing that code which adds negligibly to shareholder value. I say "wish" because a part of me has definitely been hijacked, in much the same way a…

LLMs are addictive, no doubt about it. We've found the cigarette of our time.

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

#298
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…

I disagree. Before coding agents really took off, back in like 2022, I was trying to learn how to create grammars in Treesitter. One evening I sat down with ChatGPT and had it generate a grammar for me. But because it was on ChatGPT, I had to manually write everything it spit out. What ended up happening is that I was typing, I'd notice little weird bits here and there, and I'd ask questions about it, explore alterna…

Was copying to the clipboard disallowed back then?

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

#299

Earlier quoted context omitted.

> 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…

Not shocked to see here that people believe "manually writing code" is the way to build brain power. How about moving up the stack?

This is what I've been focusing on. Writing good user stories, defining the definition of "done", acceptance testing. Thinking about the high level design decisions. Never thinking about how I'm going to implement feature X is honestly a breath of fresh air.

I've been writing code for nearly 30 years, and I'm done.

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

#300
There's value to hand-copying something. Hunter S. Thompson transcribed Hemingway to internalize the cadence of his writing.

However, if you're serious about it, then why not hand-write your LLM-generated code? You'll get much better retention and comprehension than typing.

Post reply on HN