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

Ask HN: Cursor is productive for an hour, then burns my application down

news.ycombinator.com

Post reply on HN
Print view View original

1–10 of 15 posts

Re: Ask HN: Cursor is productive for an hour, then burns my application down

#2

Post by Fin_Code »

You are working against LLM attention. A LLM looks at a conversation and focuses on its attention points. Usually the start and end. Your previous work falls into the out of attention space and gets nuked.

If your asking how to have everything attention we currently can't.

Re: Ask HN: Cursor is productive for an hour, then burns my application down

#4

Post by HenryBemis »

My code (that ChatGPT writes for me is from 500 to 1000 lines). Every 5-7 versions, it starts messing things up.

I keep the working versions on a Word file on a Landscape, A3, 3 columns (version number, comment/changelog, the_code)(yes, cheap, scalable, easy).

So, every 5-7 versions, I start a new chat. I ask ChatGPT to read/write a summary/description of the code, and then I proceed to ask it for new changes/enhancements.

Re: Ask HN: Cursor is productive for an hour, then burns my application down

#5

Post by matternous »

HenryBemis wrote: post #4

My code (that ChatGPT writes for me is from 500 to 1000 lines). Every 5-7 versions, it starts messing things up. I keep the working versions on a Word file on a Landscape, A3, 3 columns (version number, comment/changelog, the_code)(yes, cheap, scalable, easy). So, every 5-7 versions, I start a new chat. I ask ChatGPT to read/write a summary/description of the code, and then I proceed to ask it for new changes/enhance…

Wait until you learn about git

Re: Ask HN: Cursor is productive for an hour, then burns my application down

#8

Post by campervans »

gravez wrote: post #3

can you explain a bit more what do you mean by burning down? and what do you use .md files for? Documenting the code?

I use .md files to keep Cursor on track, the flow I use is something like...

Define a feature in detail (using trascription) -> Get o3 or Gemini 2.5 pro to break it down into very small testable tasks. -> review this -> then paste into a tasks.md file -> write and architecture.md file or similar for any additional context needed. -> then prompt Cursor to work through tasks.md step by step.

This keeps it on track, with the whole feature defined from the outset.

But eventually... it will try to ignore the dockerfile and setup up locally, create multiple .env files, write code with placeholders, ignore a files it's just created and written...

It's impossible to get it back on track - it gets into a debug loop of making things worse rather than getting back on track.

Re: Ask HN: Cursor is productive for an hour, then burns my application down

#9

Post by campervans »

matternous wrote: post #5
HenryBemis wrote: post #4

My code (that ChatGPT writes for me is from 500 to 1000 lines). Every 5-7 versions, it starts messing things up. I keep the working versions on a Word file on a Landscape, A3, 3 columns (version number, comment/changelog, the_code)(yes, cheap, scalable, easy). So, every 5-7 versions, I start a new chat. I ask ChatGPT to read/write a summary/description of the code, and then I proceed to ask it for new changes/enhance…

Wait until you learn about git

Yeh, a free GitHub and breaking the code into small functions would 10x your flow here

Re: Ask HN: Cursor is productive for an hour, then burns my application down

#10

Post by campervans »

Fin_Code wrote: post #2

You are working against LLM attention. A LLM looks at a conversation and focuses on its attention points. Usually the start and end. Your previous work falls into the out of attention space and gets nuked. If your asking how to have everything attention we currently can't.

Damn...

So you're saying I need some adderral.ai

Post reply on HN