Live data from Hacker News

Prevent cognitive debt by manually retyping LLM-generated code

ankursethi.com

461–470 of 479 posts

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

#461
> Personal projects must be fun above all else. The joy of working on personal projects comes from the process, not from the outcome.

I think that's my fundamental difference with the author. I only write programs I actually need. I enjoy the outcome more than the process.

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

#462
post #458

Earlier quoted context omitted.

Copying is not theft.

Can we get that added to the US Constitution and the UN Declaration of Human Rights?

Does it need to be added? I don't think anything legal considers copying theft. Copyright infringement and theft are literally just different crimes.

I don't think copyright should exist at all, but conflating infringement with theft helps no one. Well, maybe Disney and other copyright empires.

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

#465
post #459
post #355

Earlier quoted context omitted.

If a computer is a bicycle for the mind I think LLMs are a unicycle for the computer.. That’s my own personal take on it anyway.

Intriguing. Like the computer instantiated a wheel and rolls off by itself, no humans needed?

No, in that it's something inherently much more unstable than a bicycle and needs a trained human onboard to have any hope of getting anywhere without falling over spectacularly

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

#466

Earlier quoted context omitted.

I think some sort of visual paradigm is where we will end up. Something like Star Trek, where the system architecture and modules are visually represented in 3D space, and you see how the organization changes with realtime low-latency animation representing the changes as they are made. So you are still in control but just at a higher level. I see some prototypes and weak implementations of this sort of thing but sur…

The problem with all existing GUI coding system is that they make it really hard to make anything other than the types of things they were designed to make. You could do it, but you have to leave the path and get into the weeds of how the system works, which usually has several layers of opinionated code structures on top of the underlying language it's compiling to. An AI visual/GUI coding system might be able to ad…

I'm not suggesting the visual system would driving the coding at all. I'm saying that it would be a visualization of your current code base as built by the LLM.

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

#467
post #439

Earlier quoted context omitted.

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.

No, it's called not throwing more shit at an already shitty wall just to add feature x_2.

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

#468
post #409

Earlier quoted context omitted.

[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.

Sorry, I'm not here to talk about your feelings. I am not "emotionally hurt", nor should you be. This is HackerNews and you're a grown ass adult (I assume). If you disagree with me, then feel free to outline your disagreement, or just ignore and move on.

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

#470
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 some sort of visual paradigm is where we will end up. Something like Star Trek, where the system architecture and modules are visually represented in 3D space, and you see how the organization changes with realtime low-latency animation representing the changes as they are made. So you are still in control but just at a higher level. I see some prototypes and weak implementations of this sort of thing but sur…

I kno you're not suggesting the visual system would drive coding at all or that it'd be a way to visually code (see: scratch). You seem to mean it as a visualization of the current code base. I'm hoping Google's code wiki is the first step in this direction. One thing I always thought was a problem with visual systems like this was understanding the codebase's architectural design at a level yu can't programmatically get out via a syntax tree analysis. Google's code wiki seems to be using an LLM to figure out the high-level structure of the code and then building the flowchart and diagrams from that understanding. Obviously there's gonna be issues and misunderstanding but I think that's the first step in the direction you're talking about. First it's text, mermaid diagrams and 2d. Next it's a 3d visual world of your codebase. AWESOME stuff. Someone @ Google.
Post reply on HN