Why is LLM reasoning in English? Seems a waste to “think” in full sentences with articles and other “unnecessary” words?

why waste time say lot word, when few word do trick.

I recently found Opus is pretty good at consolidating very-similar-but-different codebases.

Sure, I had to tell it to so, but it trudged through and did it fairly independently… Was especially nice as refactoring test infrastructure code isn’t always very exciting…

I can’t help but think that Anthropic somehow trained on proprietary data too.

Twice, I’ve asked it about a niche almost undocumented hardware register and it told me about fields that aren’t published anywhere…

Your first response is probably that the LLM inferred from public header files or sample code — except this is a really niche thing, there is only one reference implementation published by the manufacturer, only one specification document, and neither ever mentioned these undocumented fields… And if I ask it about the source, it will claim it was an error and these things don’t exist…

A natural assumption would be that it was hallucinated — but sure doesn’t seem like it.

At this point, I wonder if that is the real game and providing AI services is only the side business…

Imagine how much deeply private corporate data is being feed to 3rd-party hosted AI models.

They get to see what even Google doesn’t get to see.

Let that sink in…

And, yeah, they have an AI that can comb through it faster than any human and better than any dumb algorithm.

But yeah, the convenience is so tempting, how many can say no? The Devil was never this clever…

It all went downhill after USTAR format. Of course, BCD encoding of sizes was a choice.

I’m damn convinced cpio never took off because the CLI tool’s syntax is a horrible abomination… Picking “-i” to EXTRACT is wild. Not being able to archive a directory tree without 3rd party assistance seems a bit much, even for the UNIX philosophy…

Gee, Synaptics seems a bit touchy about this…

That's okay, we'll still have the alps.

Couldn’t let Notepad keep the its title uncontested, right?

Even Yahoo has an AI and better search results than they did in the past…

I think Intel figured out way to be even worse…

Are the Qwen models actually close to Claude?

I tried running one of the Qwen 3.8 models locally. Asked it to code a simple thing. It pontificated on its place in the universe and then asked me what I want it to actually do!

Claude would have written, documented, and unit tested the thing on the first shot…

I want to run local models, but if this is the current state, it’s hard to mentally justify the hardware expense to only get this…

The “universal radio hacker” software makes it really easy to decode OOK remotes using an SDR. It figures out the parameters too.

https://github.com/jopohl/urh

I used this to decode my fan remote signals and wrote a simple python script for doing OOK transmissions with a HackRF. (I felt like doing my own).