I was working on a VS code extension that integrated with claude code to show an overlay for the changes instead of the edit tool calls so you could write everything yourself. The idea was that even if you type 100% of the same code instead of making your own changes, it would still mean you go through the code yourself and have a better understanding that you would have on just skimming through the generated code. Maybe I should start working on it again.
Prevent cognitive debt by manually retyping LLM-generated code
421–430 of 479 posts
Re: Prevent cognitive debt by manually retyping LLM-generated code
#422Earlier 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?
Yes, but also not necessarily good code(according to some). A lot of people don't buy into the "code should be optimised for reading" stuff.
Re: Prevent cognitive debt by manually retyping LLM-generated code
#423Today I added a temporary data source to Prometheus to help me monitor a system closely during a tricky ops task. I would not have done that except that the LLM gave me a small script I could quickly check and immediately use. Without it, I'd have roughly spot checked the service via "tail -f".
Our company's policy on LLM use is: use it, disclose it, and take responsibility for the code you commit.
There's no way that typing that tool back in would have done anything useful for me or my organization.
Re: Prevent cognitive debt by manually retyping LLM-generated code
#424As 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]
Are you sure ejaculated is the right word to use for that
Re: Prevent cognitive debt by manually retyping LLM-generated code
#425I was working on a VS code extension that integrated with claude code to show an overlay for the changes instead of the edit tool calls so you could write everything yourself. The idea was that even if you type 100% of the same code instead of making your own changes, it would still mean you go through the code yourself and have a better understanding that you would have on just skimming through the generated code. M…
(posting this here on the off chance someone makes this instead of me so I can just use their version instead)
Re: Prevent cognitive debt by manually retyping LLM-generated code
#426That’s just seems like a worst of both worlds to me.
I can see both logic in doing manual coding (perhaps with AI autocomplete) or a vibe based flow. They’re orthogonal approaches though.
Re: Prevent cognitive debt by manually retyping LLM-generated code
#427[dead]
Re: Prevent cognitive debt by manually retyping LLM-generated code
#428Earlier quoted context omitted.
> you don't learn from it Except that you do. Otherwise you could just sit in school or university and just listen and do nothing, but that way you just learn A LOT less, instead of taking down the lecture/lesson.
Even better would be to rewrite it by hand with a pen.
That's what I was referring to, actually.
Re: Prevent cognitive debt by manually retyping LLM-generated code
#429Earlier quoted context omitted.
I started programming this way as a kid with books and notes that I'd then periodically would be able to enter into a computer to see if it runs.
I programmed this way my first year of community college because I didn't have a computer. I'd retype all of my work in the computer lab.
Me too. And this way you make way fewer bugs, almost none.
Re: Prevent cognitive debt by manually retyping LLM-generated code
#430[dead]