Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cognitive Debt: When Velocity Exceeds Comprehension

rockoder.com

Post reply on HN
Print view View original

161–170 of 234 posts

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#161

Post by mort96 »

allan_s wrote: post #145
juanre wrote: post #136

"The system they built feels slightly foreign even as it functions correctly." This is exactly the same issue that engineers who become managers have. You are further away from the code; your understanding is less grounded, it feels disconnected. When software engineers become agent herders their day-to-day starts to resemble more that of a manager than that of an engineer.

exactly, as a manager and a sometimes a developer, "vibe-coding" has been looking more and more as my day job (in a good way, it's good to not have to do all the dirty work for your pet projects) and it's all about having the same discipline in term of: * thinking about the big picture * knowing how you can verify that the code match the big picture. In both case, somtimes you are happily surprised, sometimes you dis…

Do you view it as an issue at all that when everyone takes on a more manager-like role, no human remains who has the hands-on experience and understanding of the system?

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#162

Post by vaylian »

andai wrote: post #8

Skill is stored in the fingers!

This. I think differently about code that I write compared to code that I only read. Every character, every symbol, every expression that I write is guaranteed to have my full attention for at least a short moment and I know why it is supposed to be there. There is meaning to everything that I write. A LLM just tries to come up with a plausibly-looking piece of code. There is no meaning in that.

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#163

Post by RealityVoid »

matsemann wrote: post #123
Klaster_1 wrote: post #84

The article very much resonates with my experience past several months. The project I work on has been steadily growing for years, but the amount of engineers taking care of it stayed same or even declined a bit. Most of features are isolated and left untouched for months unless something comes up. So far, I managed growing scope by relying on tests more and more. Then I switched to exclusively developing against a s…

Learning has always been to write things down. Just reading it seldom sticks.

Absolutely not. Learning has been to experiment with the things until you form a effective mental model of the thing. Writing things does ab-so-luetely nothing except make you feel good in the moment. Just like listening to a lecture without engaging with the subject matter deeper.

Writing things down is important for organisational persistence of information but that is something else.

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#164

Post by Belphemur »

atmosx wrote: post #148
slashdev wrote: post #104

Earlier quoted context omitted.

I have this at the bottom of my AGENTS.md: You will also add a markdown file to the changelog directory named with the current date and time `date -u +"%Y-%m-%dT%H-%M-%SZ"`, record the prompt, and a brief summary of what changes you made, this should be the same summary you gave the developer in the chat. From that I get the prompt and the summary for each change. It's not perfect but it at least adds some context ar…

Isn’t the commit message a better place to add what and why? You might need to feed some info that the agent doesn’t have access to “we are developing feature X this change will such and such to blah blah”. The agent will write a pretty good commit message most of the times. Why do you need a markdown file? Are releasing new versions of the software for third parties?

Cheaper and faster retrieval to be added to the context and discoverable by the agent.

You need more git commands to find the right commit that contains the context you want (either you the human or the LLM burning too many token and time) than just include the right MD file or use grep with proper keywords.

Moreover you could need multiple commits to get the full context, while if you ask the LLM to keep the MD file up to date, you have everything together.

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#166

Post by epolanski »

One thing that I do that increases both my productivity and the output quality is to have few hours of planning, first business logic, then a separate one session for implementation and then have AI tell me what code I need to write.

I don't let it edit code, but I do have it guide me. Writing the code myself forces me to think about it, question it in isolation and tie it to the overall design.

I don't always do so, sometimes I do let it do the edits for simpler smaller changes, but I do at any new feature.

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#168

Post by direwolf20 »

RealityVoid wrote: post #163
matsemann wrote: post #123

Earlier quoted context omitted.

Learning has always been to write things down. Just reading it seldom sticks.

Absolutely not. Learning has been to experiment with the things until you form a effective mental model of the thing. Writing things does ab-so-luetely nothing except make you feel good in the moment. Just like listening to a lecture without engaging with the subject matter deeper. Writing things down is important for organisational persistence of information but that is something else.

Writing is better than reading, but doing is better than writing.

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#169

Post by bendmorris »

crazygringo wrote: post #153

> Six months later, an architectural change required modifying those features. No one on the team could explain why certain components existed or how they interacted. The engineer who built them stared at her own code like a stranger’s. Genuine question: so what? First of all, team members leave all the time , and you're stuck staring at code nobody instantly understands. Second of all, LLM's are a godsend in help yo…

>Heck, I often don't remember anything about code I wrote six months ago. It might as well have been written by someone else.

This just isn't true at all in my experience. Do I remember every detail of code I haven't looked at for six months? No, but I can go back and recall pretty quickly how it's structured and find my way around. I'm much more able to do that with code I wrote and thought deeply about. It's like riding a bicycle - if you invested in building up your knowledge once, you can bring it back more easily.

LLMs can sometimes help you to understand someone else's code but they can also hallucinate and I think people gloss over how frequently this happens. If no one actually understands or can verify what it's saying, all I can say is good luck.

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#170

Post by shimman »

direwolf20 wrote: post #168
RealityVoid wrote: post #163

Earlier quoted context omitted.

Absolutely not. Learning has been to experiment with the things until you form a effective mental model of the thing. Writing things does ab-so-luetely nothing except make you feel good in the moment. Just like listening to a lecture without engaging with the subject matter deeper. Writing things down is important for organisational persistence of information but that is something else.

Writing is better than reading, but doing is better than writing.

How does this apply to coding when the act of writing IS doing? Or do you mean like coding "on your own" versus following a tutorial for example?
Post reply on HN