Live data from Hacker News

Agentic coding is burning me out

0xsid.com

11–19 of 19 posts

Re: Agentic coding is burning me out

#11
Easiest way to keep yourself from overload is get yourself a local model. At 128GB in Mac Studio or AMD395+ and it's large enough to get the sweet context window, but slow enough that you can either process what it's doing or focus on something requiring more careful work.

It's still hard to stop yourself from constant bikesheding, reorganizing, etc, but yeah, mentally it's a different bag of tricks you need to learn.

Re: Agentic coding is burning me out

#12

Agent coding hype is marketing to push FOMO on devs in order to trick them into turning off their brain in exchange for money. They get hooked at work where they are likely more than happy to let a machine barf out boring code they likely didn't want to write in the first place. Then they bring that practice home. It's digital crack for devs.

I find it difficult to distinguish agent coding from just a code harness. They refer to different things, but those agents dont exist without a harness that manages them.

The harness though is real; the LLM does not do anything interesting without a set of tools, specific prompts to use them, and taking a lot of forced context planning out of the dev's hands.

But yeah, usually when you mix business interests without customer concerns, those business interests develop dark patterns so they can invent concerns and then solve them.

Re: Agentic coding is burning me out

#13
post #9

Earlier quoted context omitted.

Which part of the post feels LLM written to you? Not snark, I’m genuinely curious. I’ve recently started writing again, after well over a decade, so I’m not very up to date on how things are done and perceived. FWIW, I write these on Google Docs and then port them over to my site. Earlier posts had an AI disclaimer saying I used Google Docs which presumably uses AI for spellchecking and obvious grammar issues but it…

I should say that the OP didn't actually scream LLM to me. I was just making a general reply to the parent comment's statement about LLM writing. I should have made that clear. I, too, would be curious what they found so obviously sloppy about this post. It seems to me like it had a human voice.

No worries, it just grated a bit to be called AI slop by the person you were responding to and I assumed you agreed with them too.

Re: Agentic coding is burning me out

#15
post #5

Earlier quoted context omitted.

Being able to write well is arguably one of the most important things any person can ever learn, as you can't write well without thinking well. So, I immediately write-off anyone who produces their writing with LLMs, as it is quite apparent that they are not a serious, thoughtful person and are instead just cosplaying as one via LLM. The fact that they can't see this (or, worse, think the slop actually makes them loo…

Which part of the post feels LLM written to you? Not snark, I’m genuinely curious. I’ve recently started writing again, after well over a decade, so I’m not very up to date on how things are done and perceived. FWIW, I write these on Google Docs and then port them over to my site. Earlier posts had an AI disclaimer saying I used Google Docs which presumably uses AI for spellchecking and obvious grammar issues but it…

doesn't come off as llm to me. Funny, comments like this exist on every blog post shared here. Don't think there's a way to escape it unless you video yourself typing or something..

Re: Agentic coding is burning me out

#16
post #4

They were so burned out that they decided to use an LLM to write this blog post. It should be embarrassing to people that they can’t even write a whole argument out by hand. It’s not that hard. All you have to do is believe in it. This blog post is just selling the idea of engineering as craft. It exists to make us feel good about having skills and to get us to regurgitate our priors in the comments. We should at lea…

Doesn't read like LLM writing to me and my detector usually fires very quickly. Don't see any obvious signs - want to share what made you think of LLM writing?

Re: Agentic coding is burning me out

#18
I can relate to that. If I'm not careful catching up my internal model and understand of the problem space and the specification of my project while the agent keeps spitting out code I feel very uncomfortable. Perhaps I have very high standards for my code quality for various reasons? But its extremely frustrating and tiring to me to check all the implicit assumptions the agent so boldly makes at high speed.

Usually, I start with a solid idea that needs hands on experience to fully developin, so I need to stay in the loop. Than I have to force myself to carefully review the code and point out architectural issues (usually there sneak in a lot of them). If I don't force myself, I end up in a limbo where the agent produces code faster than my mental model following.

Even if I have a well developed domain knowledge and a good idea what I want, I then definitely feel some kind of, what I guess compares to, slot machine effect. "Maybe now I get what I want. Argh, not quite. Okay, feels nearly there. Perhaps only this prompt. Ah, there is something missing...".

I'm really curious how you handle and approach this.

Post reply on HN