And the painting in full glory, at 15000 x 12415.

https://api-www.louvre.fr/sites/default/files/2026-05/prise-...

> but I do see I'm a lot "lazier", even stuff that used to be routine when I started coding now feel heavy.

Not getting that quick dopamine hit the LLMs give you..

Some say you can re-train your system to get back the dopamine hits you used to get from other things, like the enjoyment of the "old fashioned" manual coding and math. Getting there is hard work. And YMMV.

I just do things manually and ask LLMs to check my work. That seems to be working great for me.

I had the most Russian of Russian bosses when I was in college. My first day on the job he so eloquently stated, "I am not your mother. Do not come to me with problems. Come to me with solutions. I want to know what you tried and what did not work."

His advice has served me well in many areas of life too. I try my best to treat LLMs no differently for domains I care about (not one-off little questions here and there).

What I would like to do is double model post-check, with a form of "debate", to better catch edge cases.

Unfortunately, I haven't found a way to set that up as I envisioned it, for the time being.

> I am running Claude in its own QEMU VM

How much system resources does it need to work smoothly? I was also thinking about doing something similar.

I dont think Claude itself needs much, its more like what you do with it. In my case it is doing some gradle builds and java tests with some postgres docker containers inside the vm so I gave it max 8G RAM with 4 cores and have no issues. I share my workspace folder (with virtiofs and also the user home so I can rebuild the vm from scratch and keep settings) because I like my tools on the host and my full creds are outside and I didnt want to keep syncing branches. I access it with ssh (with passt). So far no real issues.

Late edit, I wanted to clarify I do not share my user home, but the VM user home for backups, thats separate user that does not have my own users credentials etc

Thanks!

Go full circle, and use the amazing tech to make a summary of the amazing tech's website written by the amazing tech to praise the amazing tech.

> I follow a similar approach and use multiple LLMs per task.

Pardon my ignorance, but how would go about doing that on, say, a standard c++ project?

I get the part where one can use codex/claude with an ide and/or extension. But how does one connect two LLMs together in such a setup?

> Why go to the expense of training your own model, especially when it will be inferior to state of the art models.

Uuh.. No? Especially of the training data, as in this case, is of better quality.

You mean the trick some environmental/health agencies like to pull when dangerous pollutants are above the set maximum limit? :-)

That's not a bug. It's a (safety) feature.

? Curious. In this case, how is sleep 10s a safety feature?

The screensaver should never see keyboard input. And it shouldn't take 10s for the visual changeover - even for Windows.

Happy to read if you've got a pointer for me.

Sorry, misread.

I read it as: made an error while typing my password in screensaver mode, needed to wait 10s for the next try.

Waiting 10 s to be able to input your initial password is, I fully agree, not acceptable.. (And even not on Windows, which I try to avoid as much as possible, among other things, for those reasons. :-))

Say what now? TIL..

Ferrari Deuce? :-|