zlacker

[return to "My AI skeptic friends are all nuts"]
1. puttyc+Zb[view] [source] 2025-06-02 22:22:42
>>tablet+(OP)
> An LLM can be instructed to just figure all that shit out. Often, it will drop you precisely at that golden moment where shit almost works, and development means tweaking code and immediately seeing things work better.

Well, except that in order to fix that 1% you'd need to read and understand whatever the LLM did and then look for that 1%. I get the shills just thinking about this, whether the original programmer was human or not. I'd rather just write everything myself to begin with.

◧◩
2. nojito+wo[view] [source] 2025-06-02 23:42:23
>>puttyc+Zb
Reading code is vastly quicker than writing it from scratch.
◧◩◪
3. abenga+ny[view] [source] 2025-06-03 01:09:38
>>nojito+wo
This is a lie, unless you are just speaking of the mechanics of cursorily skimming it. Reading code to understand it enough to commit it in my name is harder and slower than writing it myself.
◧◩◪◨
4. nojito+E01[view] [source] 2025-06-03 06:22:07
>>abenga+ny
So you don’t use any libraries in your code?

How about reading documentation?

Or reviewing PRs?

Or go through source code to build out new features?

◧◩◪◨⬒
5. abenga+O81[view] [source] 2025-06-03 07:41:58
>>nojito+E01
I don't commit entire libraries as written by me. Documentation is also far easier to read. Reviewing PRs is quite involving, since I want to do it well. Easier than typing code for sure.
[go to top]