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

351–360 of 479 posts

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

#351

Post by jaggederest »

kamens wrote: post #339

I used to do this and called it "Coding with AI the Hard Way" in a nod to Zed Shaw: https://kamens.com/blog/code-with-ai-the-hard-way I no longer do and blogged my updates for fear of being seen as a luddite: https://kamens.com/blog/code-with-ai-the-hard-way-update https://kamens.com/blog/code-with-ai-the-hard-way-update-ii

Ben if you're going to blog about things with relative timestamps you need to provide a base timestamp, and I would also appreciate that for when you update the post. "3 months ago" is unhelpful without that context.

Well done for registering your beliefs publicly and updating them publicly. So many people out here exist in an epistemology-free zone.

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

#352

Post by skydhash »

ErroneousBosh wrote: post #290
swat535 wrote: post #201

Earlier quoted context omitted.

> It cannot do the job I want it to. I mean in your case, you are not able to use LLMs effectively to build features, so you should type the code by hand. However, upper management is excited about AI because it can push features quickly to production. Granted, they will be giant balls of slop but they don't care. As long as it works in the UI, they are happy. If no one could get anything done with AI, there wouldn't…

> I mean in your case, you are not able to use LLMs effectively to build features, so you should type the code by hand. I never write code sitting at a computer. Mostly I write it in the car, when I have no distractions. I just type it in when I'm sitting at the computer. I've been using Claude as an experiment for some "fun" projects that I'm unlikely to release, just to see how it is. The thing is, at least for the…

I mostly do reading in front of the computer (not code, docs), but that's before I'm used to the project. Usually I spend more time on the couch than in front of the computer. Because that's where I think best. If I'm writing code, I already have the solution.

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

#353

Post by baliex »

ncallaway wrote: post #344
bigbuppo wrote: post #332

Also... if your workflow is "think hard, let LLM write it, read what AI wrote, think hard about what AI wrote, re-type what AI wrote, fix what AI wrote"... Where in the heck are the efficiency gains? Couldn't you just drop the LLM part of it and save the company a trillion dollars in tokens?

I've found I can get quite a bit of use out of it as a basically ever-present rubber duck. Using a cheap model, I usually spend - here's the problem I'm trying to solve: - here's my initial plan for the design: - is there anything I'm not thinking about or my plan is missing? It'll occasionally pop out a suggestion that I like more than my original plan, or it'll give me some new angles to think through the original…

I’m guilty of using this approach too and noticed that an (obvious?) side-effect is that I get fewer wonderful, human, “aha” moments with my colleagues.

I mentioned this at a stand-up and only then did others think about it and notice the same of themselves.

This, to me, is one of the major downsides of all this: less collaboration, more individualism

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

#354

Post by cavoirom »

bigbuppo wrote: post #332

Also... if your workflow is "think hard, let LLM write it, read what AI wrote, think hard about what AI wrote, re-type what AI wrote, fix what AI wrote"... Where in the heck are the efficiency gains? Couldn't you just drop the LLM part of it and save the company a trillion dollars in tokens?

knowledge, by doing that I retrieve the knowledge from LLM, I learn faster, write code faster, do things more careful... The efficiency is the better design, better code quality, higher test coverage, less bugs. Because LLM let me gain knowledge faster than previous tools.

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

#355

Post by baliex »

kfarr wrote: post #322
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.

If a computer is a bicycle for the mind, perhaps LLMs are the cars for the mind…

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.

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

#356

Post by cavoirom »

tmnvix wrote: post #324
WhyComboNadir wrote: post #191

Earlier quoted context omitted.

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.

Haha, your analogy reminds me of one I often make to highlight just how much we undervalue fossil fuels. Imagine filling your car with $1 worth of fuel and then driving it on flat terrain as far as it will take you. Now get out and push your car back. Friction and momentum aside, that's the astounding amount of energy/work we get from a dollar's worth of fuel. Now imagine your car is actually an LLM model. It gets yo…

I agree with your point, I found it makes more sense with the company when they have a problematic product no one can fix.

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

#357

Post by danielvaughn »

rzzzt wrote: post #298
danielvaughn wrote: post #189

Earlier quoted context omitted.

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?

No, but I consciously chose not to do that, because I wanted to gain muscle memory by typing the code by hand.

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

#358

Post by crossroadsguy »

bigbuppo wrote: post #332

Also... if your workflow is "think hard, let LLM write it, read what AI wrote, think hard about what AI wrote, re-type what AI wrote, fix what AI wrote"... Where in the heck are the efficiency gains? Couldn't you just drop the LLM part of it and save the company a trillion dollars in tokens?

Besides, many companies proactively punish doing anything not by LLM.

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

#359

Post by system2 »

bendmorris wrote: post #347
system2 wrote: post #334

While your competitors ship out million-line software, you are going to write down the LLM code. This approach will make a software engineer homeless in a very short time.

LOC is not a good indicator of productivity or quality - or it anything these days it's a negative one. "Million-line software" is meaningless.

From a marketing perspective, I do not agree. The competitors can claim 100 more features than your "lean" code. That by itself makes you lose customers.

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

#360

Post by nharada »

colordrops wrote: post #336
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 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…

Agreed I want an IDE but only architecture. I suspect it’ll get superseded though eventually too.
Post reply on HN