zlacker

[parent] [thread] 6 comments
1. fastba+(OP)[view] [source] 2025-06-03 12:25:35
A prompt can be as little as a sentence to write hundreds of lines of code.
replies(1): >>shaky-+YE
2. shaky-+YE[view] [source] 2025-06-03 16:26:06
>>fastba+(OP)
Hundreds of lines that you have to carefully read and understand.
replies(3): >>victor+VK >>ImPost+U61 >>fastba+2Q1
◧◩
3. victor+VK[view] [source] [discussion] 2025-06-03 17:00:10
>>shaky-+YE
Depends on what it is doing. A html template without JS? Enough to just check if it looks right and works.
◧◩
4. ImPost+U61[view] [source] [discussion] 2025-06-03 19:09:11
>>shaky-+YE
You also have to do that with code you write without LLM assistance.
◧◩
5. fastba+2Q1[view] [source] [discussion] 2025-06-04 00:55:33
>>shaky-+YE
Are you not doing that already?

I go line-by-line through the code that I wrote (in my git client) before I stage+commit it.

replies(2): >>shaky-+u56 >>nipah+i2n
◧◩◪
6. shaky-+u56[view] [source] [discussion] 2025-06-05 15:29:14
>>fastba+2Q1
Yes, but you know the kind of code you write. When you re-check it, you are looking for minor typos, no major logic flaws affecting half the committed code.
◧◩◪
7. nipah+i2n[view] [source] [discussion] 2025-06-12 13:47:31
>>fastba+2Q1
You read at the same speed line-by-line your code when you are in your git client?

You are doing something wrong. I go line-by-line through my code like 7x faster than I would do it for someone's else code, because I know what I wrote, my own intentions, my flow of coding and all of those details. I can just look at it en passant, while with AI code I need to carefully review every single detail and the connection between them to approve it.

[go to top]