The next two years of software engineering

>I found it especially ironic being on hacker news how few people seemed to have a hacker mindset when it came to LLMs

You keep using the word "LLMs" as if Opus 4.x came out in 2022. The first iterations of transformers were awful. Gpt-2 was more of a toy and Gpt-3 was an eyebrow-raising chatbot. It has taken years of innovations to reach the point of usable stuff without constant hallucinations. So don't fault devs for the flaws of early LLMs

The reason why it is better is that with search you have to narrow your search down to a specific part of what you are trying to do, for example if you need a unique id generating function as part of what you are trying to do you first search for that, then if you need to make sure that whatever gets output is responsive 3 columns then you might search for that, and then do code to glue the things together to what you need, with AI you can ask for all of this together, get something that is about what the searched for results would have been, do your glue code and fixes you would normally have done.

It trims the time requirement of a bit of functionality that you might have searched for 4 examples down by the time requirement of 3 of those searches.

It does however remove the benefit of having done the search which might be that you see the various results, and find that a secondary result is better. You no longer get that benefit. Tradeoffs.

My question: are those people who were building crappy, brittle software, which was full of bugs and and orher suboptimal behavior, that were the main reasons of slowing down the evolution that software, will they now begin writing better software because of AI? Answering yes, implies that the main reason of those problems was that those developers didn't have enough time to spend on analyzing those problems or to build protection harnesses. I would stronly argue that was not the case, as the main reason is of intelectual and personal nature - inability to build abstractions, to follow up the route causes (thus not aquiring necessary knowledge), or to avoid being distracted by some new toy. In 2-5 years I expect the industry going into panic mode, as there will be a shortage of people who could maintain the drivel that is now being created en masse. The future is bright for those with the brains, just need to wait this out

Something very odd about the tone of this article. Is it mostly AI written? There is a lot of references and info. But I am feeling far more disconnected with it.

For the record, I was genuinely trying to read it properly. But it is becoming unbearable by mid article.

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.