nurettin

In my experience, LLMs instantly find the reason for the crash and fix. They don't even need to go through the debugging phase anymore. It doesn't matter if you're generating c++ lisp or cobol.

It was the best part of turbo pascal as well. Before IDEs decided to hide information.

With these numbers, I'm holding my breath for the pelicanbench.

LXC is a jail and qemu is an extra layer of emulation. Why pay that extra cost? Just because it serves a wsl image isn't really an answer. How is that worth the extra layer?

We still have developers because we can't outsource responsibility to AI. If shit breaks, we still need someone to fix it. Maybe you think that can also be automated. I have a counter-example. AI will rarely use the existing state when solving a bug. It will tack on it's own event queue, it will make up it's own messaging system, it is a cancerous growth. And this observation is based on both opus5.5 and gpt5.6-astra. The results are way past magical at this point, but you still have to weigh in pretty heavily for orderly code growth where solutions are succint, focused and preserve the existing structure. They are still noobs at fixing/adding stuff.

Same here

That very similar history is shared by us dinosaurs. I especially remember tuning the 1530 datasette to play differently recorded tapes, then moving to DOS and discovering how much faster it was to run something compiled by turbo pascal. Then discovering "infinite memory" since you could create a pointer pointing at a place in memory which had... another pointer!!! (I was a very happy kid after discovering that)

I don't have a voice or likeness in my code. Sure, I have a very specific style in all the code I wrote for the past couple of decades, but you can achieve the same outputs with completely orthogonal styles as well. (like AoS vs SoA) so what would I even negotiate for when everything I ever thought of got distilled into neural network weights to be high-pressure sprayed to the masses?

Used claude since 7/2025. Switched to codex after fable got blocked. It was still 5.5 but I knew they had to come up with something. As soon as I switched, wow. It wasn't super intelligent, but it was stable. Every day it was the same performance. This consistency is definitely worth paying for.

Oooh real 64bit ide instead of the crippled 32bit junk they gave as a demo for the past 10 years. Good improvement.

I used to get wrist pain from using mouse and keyboard back 20 years ago. I did no exercises. No stretching, no rock climbing, no triathlons, it just slowly subsided and went away. Maybe I just became aware of positioning and strain to such an expert degree that I just instinctively do the correct moves.

At that revenue, why not make your own filesystem, database and index structure? There is no way mysql is the best possible software for this use case. Why stop innovation and hand everything over to ops?

I mean, yeah, we are pretty trash without years of domain knowledge. But programmers do have a large domain. Some are experts at a/v, some security/networking, some like to make games/demos. These domains were highly accessible to us and still are. It's not like we solved coding exercises all day when we weren't leasing our souls to companies.

It is heartwarming to see how sarcasm turns into a celebration of mediocrity.

> Things not working the way I expect means I have to do more work to figure something out.

You must love SELinux

I don't think it was AI, I seem to remember that google broke search or SO SEO broke to the point where it wouldn't even point at the right SO article. There used to be a lot of commotion on the forums about how broken google search became for them.

This is why I always fail loud rather than pick a stupid default.

Are you really diving into technicals just by asking "sooo what did you do?" to your AI? Without document crawling, debugging and pulling your hair out, how much of it is really a deep dive? I feel like all that effort that goes into generating a mental image from bits and pieces is gone. I'm just grudgingly happy I went through all that before humanity retired.

Anthropic should make their own language, and openai should follow suit.

Maybe it is because anthropic prefers a larger system prompt?

https://github.com/asgeirtj/system_prompts_leaks/blob/main/A...

I agree with all of this, and gource is an excellent example, but this is still "what" and builds no case for a "why". Not even an anecdote like "I told the agent this and it completely misunderstood and did the other thing so I built this which you can use to undo the work after the fact."

I tell it to avoid belts and suspenders, don't leave dysfunctional code in, and fail loud. Seems to change that behavior.

I just tell it "you have until morning to work on this, be careful not to use too much ram and don't burn the cpu"

and then it goes off to do its thing and hopefully rngesus is with us.

I've been using both codex and claude for the past month and if anthropic acted up like that I'd switch fully to codex in a heartbeat.

Looking back, I wonder what really changed over 25 years for the linux ecosystem. We had lots of distros, there were games built for linux (I remember playing the entire Neverwinter nights on debian) there was wine for StarCraft broodwars, x11+compiz for cool accelerated desktop graphics, proprietary Nvidia drivers were always there. Sure, everything was 32bit but it was good enough for desktop, and amd64 was about to pop.

The other day I tried to install fedora 44 on a friend's computer. He wanted kde so we set that up and whoops, no way to start programs on the discrete video card. I hacked around it by starting xorg, setting an alias and environment variables, but it was a bit embarrassing to see that things have regressed.

I'm not going to downplay it. I've been coding since the 80s and using these models since 2023. 10 minutes after using fable I told my colleague this is a new era. It is the difference between sonnet and opus. I didn't think this was possible.

It was over before this announcement. After a couple of days, even though the model was set to fable, it felt like opus. We are back to sticks and stones.

Sometimes it is ok to sit there in confusion and ask the user to clarify rather than go on an adhd fueled rampage to figure it out without asking.

What do you mean by water fasting? Do you avoid drinking water directly, or do you avoid all food? For example salads are basically sacks of water.

I also run a Qwen 3.6 moe A4B on old hardware. I set it up with

numactl --membind=1

so it is constrained to one of the memory sticks which speeds up token generation a little.

Learning some schmuck's framework, IDE, language or OS never felt rewarding to me. It was always like playing with broken toys. Hear me out.

There was always some subtle quirk, a bug that irks me once every so often, something I'd never want to unleash upon masses and although these people made their work available through various channels, paid or unpaid, for some reason I felt more of a grudge than gratitude.

And I tried to fix things I did. It was a breathless, thankless exercise of working through someone else's code line by line for decades while hardly being able to lift my head because of actual work I had to do to support my life. And thus a villain was born.

I am so glad it is over. It is all ingested into neural network weights and high-pressure sprayed to the masses through RNG. I am finally free. I don't have to learn your stupid aws commands, your helm configs, your systemd antics, your http api. I don't have to care about your life times, your gc params. I tell the computer and it clinks and clanks and eventually gets the job done like gene rodenberry intended.