My experience hasn't been LLMs automate coding, just speeds it up. It's like I know what I want the solution to be and I'll describe it to the LLM, usually for specific code blocks at a time, and then build it up block-by-block. When I read hacker news people are talking like it's doing much more than that. It doesn't feel like an automation tool to me at all. It just helps me do what I was gonna do anyways, but without having to look up library function calls and language specific syntax

> My experience hasn't been LLMs automate coding, just speeds it up.

This is how basically everyone I know actually uses LLMs.

The whole story about vibecoding and LLMs replacing engineers has become a huge distraction from the really useful discussions to be had. It’s almost impossible to discuss LLMs on HN because everyone is busy attacking the vibecoding strawman all the time.

I'm somewhere in between myself. Before LLMs, I used to block a few sites that distracted me by adding entries in /etc/hosts file to mapping them to 127.0.0.1 on my work machine. I also made the file immutable so that it would take a few steps for me to unblock the sites.

The next step was for me to write a cron job that would reapply the chattr +1 and rewrite the file once in 5 minutes. Sort of an enforcer. I used Claude (web) to write this and cut/pasted it just because I didn't want to bother with bash syntax that I learned and forgot several times.

I then wanted something stronger and looked at publicly available things like pluckeye but they didn't really work the way I wanted. So I tried to write a quick version using Claude (web) and started running it (October 2025). It solved my problem for me.

I wanted a program to use aider on and I started with this. Every time, I needed a feature (e.g. temporary unblocks, prevent tampering and uninstalling, blocking in the browser, violation tracking etc.), I wrote out what I wanted and had the agent do it. OVer the months, it grew to around 4k lines (single file).

Around December, I moved to Claude code from aider and continued doing this. The big task I gave it was to refactor the code into smaller files so that I could manage context better. IT did this well and added tests too. (late December 2025).

I added a helper script to update URLs to block from various sources. Vibe-coded too. Worked fine.

Then, I found it hogging memory because of some crude mistakes I vibe-coded early on fixed that. Cost me around $2 to do so. (Jan 2026).

Then I added support to lock the screen when I crossed a violation threshold. This required some Xlib code to be written. I'm sure I could have written it but it's not really worth it. I know what to do and doing it by hand wouldn't really teach me anything except the innards of a few libraries. I added that.

So, in short, this is something that's 98% AI coded but it genuinely solves a problem for me and has helped me change my behaviour in front of a computer. There are no companies that my research revealed that offer this as a service for Linux. I know what to do but don't have the time write and debug it. With AI, my problem was solved and I have something which is quite valuable to me.

So, while I agree with you that it isn't an "automation tool", the speed and depth which it brings to the environment has opened up possibilities that didn't previously exist. That's the real value and the window through which I'm exploring the whole thing.

You can think of LLMs as a higher level language for whatever programming language you are using, but informal with ambiguous grammar.

i notice a huge difference between working on large systems with lots of microservices and building small apps or tools for myself. The large system work is what you describe, but small apps or tools I resonate with the automate coding crowd.

I've built a few things end to end where I can verify the tool or app does what I want and I haven't seen a single line of the code the LLM wrote. It was a creepy feeling the first time it happened but it's not a workflow I can really use in a lot of my day to day work.

It’s a better Google for me. Instead of searching AWS or StackOverflow it hallucinates a good enough output that I can refactor into an output.

I’m doing both. For production code that I care about, I’m reading every line the LLM writes, correcting it a lot, chatting with an observer LLM who’s checking the work the first LLM and I are writing. It’s speeding stuff up, it also reduces the friction on starting on things. Definitely a time saver.

Then I have some non-trivial side projects where I don’t really care about the code quality, and I’m just letting it run. If I dare look at the code, there’s a bunch of repetition. It rarely gets stuff right the first time, but that’s fine, because it’ll correct it when I tell it it doesn’t work right. Probably full of security holes, code is nasty, but it doesn’t matter for the use-cases I want. I have produced pieces of software here that are actively making my life better, and it’s been mostly unsupervised.