[dead]
Ask HN: I hate coding agents. Is this skill issue?
21–30 of 37 posts
Re: Ask HN: I hate coding agents. Is this skill issue?
#22I had the same issues a year an a half ago. You just have to get over it. It sucks and not much can be done about it.
So do you still use agentic programming? What percentage of code do you write yourself and what percentage do you hand off to AI?
Re: Ask HN: I hate coding agents. Is this skill issue?
#23No, it's not a skill issue. It's a taste issue. You have some. More seriously, you triggered a thought with your point 4. In prose, "editor" is a different skill from "author". It's a different career track. AI is, essentially, taking coders from "author" to "editor". We don't feel nearly as comfortable there. It isn't what we do, or at least what we've been doing for our whole careers.
Very good point!
Re: Ask HN: I hate coding agents. Is this skill issue?
#24AI coding forces people to frontload a lot of the detailed thinking that used to take place over an epic or sprint. It's not a very natural way of working, and in fact is quite contrary to the iterative development style that most devs are already used to.
Re: Ask HN: I hate coding agents. Is this skill issue?
#25[dead]
Re: Ask HN: I hate coding agents. Is this skill issue?
#26My process is becoming as follows:
1) I always start with a clean code base (ie. no uncommitted changes)
2) I have a text file called prompts in which I write my first prompt for my desired change, in the initial prompt I always explicitly ask to NOT generate unit tests.
3) Copy paste the prompt to the cli
4) While the LLM is working on my prompt I go back to my prompts file and start preparing the next prompts that will build on top of the previous one
5) Once the agent is done I review every single line of code and either manually fix what I don’t like or prompt minor changes until I reach my desired result.
6) commit locally the change
7) copy paste the next major prompt from my prompts file
8) Repeat steps 4-8 until I fully implement my major change
9) Once I have my major change I prompt for adding unit tests and related documentation
10) Once my unit tests are all green I execute additional manual tests if required, squash all local commits and push for pear review
Following these steps I can work fully focused and let me emphasise again on the fact that even if the majority of code is written by the LLM I still review and read every single line of code so that when LLM companies decide to fuck us or when shit happens in production I know where to look as if I wrote the code myself like the old days
All of this works for me because I know very well the programming language and the specific domain I am working in thanks to the past experience collected in past years before LLMs.
Re: Ask HN: I hate coding agents. Is this skill issue?
#27My process is becoming as follows: 1) I always start with a clean code base (ie. no uncommitted changes) 2) I have a text file called prompts in which I write my first prompt for my desired change, in the initial prompt I always explicitly ask to NOT generate unit tests. 3) Copy paste the prompt to the cli 4) While the LLM is working on my prompt I go back to my prompts file and start preparing the next prompts that…
Quite similar, but I ask for "/grilling" skill in every prompt so the agent aligns to my decissions before it drifts into own.
And I actually ask to make tests before any implementation and let them all fail.
Re: Ask HN: I hate coding agents. Is this skill issue?
#28My process is becoming as follows: 1) I always start with a clean code base (ie. no uncommitted changes) 2) I have a text file called prompts in which I write my first prompt for my desired change, in the initial prompt I always explicitly ask to NOT generate unit tests. 3) Copy paste the prompt to the cli 4) While the LLM is working on my prompt I go back to my prompts file and start preparing the next prompts that…
Thank you for your suggestion. Going straight to the next prompt while the agent is still working will probably help me stay in flow state longer. However I'll still have to context switch when checking the code. Nonetheless, I'll experiment with this, thanks!
Re: Ask HN: I hate coding agents. Is this skill issue?
#29AI coding forces people to frontload a lot of the detailed thinking that used to take place over an epic or sprint. It's not a very natural way of working, and in fact is quite contrary to the iterative development style that most devs are already used to.
Yep, some time I think we are going back to a waterfall methodology
Re: Ask HN: I hate coding agents. Is this skill issue?
#30I find it painful as well. I actually find agentic coding counterproductive. I typically use LLMs the “old way”: web chat interface, asking questions and searching. I write the code by hand. This makes me 2-3x more productive than before (I guess with agents I could be 5-10x more productive but the price to pay is not worth it)
I was like this too. I found pride for myself on only using the web chat. But being constantly bombarded by titles like "Look what crazy software project this accountant built with X agent!!!!" makes me worry that I'll stay behind if I don't adapt to this new model. I think after all, AI is here to stay, and it's evolving a lot faster than we can keep up