nhod

At this exact moment there is another post [1] on HN from Derek Thompson talking about the >70% drop over the past few decades in having other people over to socialize for dinner. Correlation is not causation, and...

[1] https://news.ycombinator.com/item?id=49891295

I've been using a project called SX https://github.com/sleuth-io/sx to manage them. It has its quirks, but overall I find it to be very useful.

One thing I've had to write as a layer on top of it is a way to assemble agent-specific CLAUDE.md / AGENTS.md from fragments.

For example, I have a little fragment that has all agents respond to me in ordered list format. (Since they often ask a bunch of question all jumbled throughout a response, the ordered list format allows me to respond to those specific questions.) And I also have a growing anti-Claudeism fragment as well.

Then I combine this with project-specific fragments and have it assembled into into a single CLAUDE.md / AGENTS.md. The layer also does a little reporting on the length of the resulting files and notifies me if it ever grows beyond a certain size.

"If you have a problem, that means it can be solved. If it cannot be solved, then it is not a problem. It is a reality to be accepted.” — Gus Fring, Breaking Bad

I don’t mean this callously. People confuse not having a choice with not liking the consequences of their choices.

You always have a choice. At minimum you can always choose to accept your circumstances. If you choose to not accept them, then your options are to choose to change them and accept the consequences of that choice, or to not change them and in the process choose to be a victim of circumstance and live in a state of complaint or dis-ease or anger or whatever other ill you create for yourself.

Those are literally your only options. The circumstances are seemingly not going to change. That means you have to. Whatever choice you are making now is seemingly not serving you, ergo a post on HN. What new choices can you make that will lead to a different result?

Agreed, and then the actual text of the post gets worse. It’s actually unreadable; I literally could not follow what the article was about (without putting in the effort to unravel the Claudisms, a little like unraveling Shakespeare or Finnegan’s Wake) and gave up.

It seems we are all (on HN) thoroughly convinced that the models have all gotten worse at writing as the version numbers have gone up and they are supposedly more powerful models. Sol 5.6 is nowhere near as bad as Opus 5 or even the 4 series but not great.

But looking back there was a time we were enamored with how they wrote. Perhaps it’s related to the newfound prohibitions on “write in this writer’s style”? I wonder if training the models to not be able to do that anymore has steered them towards not being able to write, at all, in any existing human good writing style and they are navigating the small pathway through all existing good human writing to whatever you want to call what they are doing now?

“Every tool is scar tissue over a real wound. Follow the wounds, and the map draws itself. THE ONE IDEA THAT UNLOCKS EVERYTHING” uh-huh

I have noticed myself having a visceral reaction to the AI tells now, somewhere between disgust and anger. And I am not an angry man and I like AI! There is just something about the voice that is incredibly off-putting, like a know-it-all friend who just ripped a giant fart. It is annoyingly correct and also smells really bad.

“the matchup feels earned” is a current AI-written tell. To whom does it feel earned? To the AI that wrote this article?

I don’t know what it is specifically, but my weak human pattern-matching skills find this kind of language increasingly revolting. I don’t know why it is revolting, per se. It’s just the feeling I get.

Of course, me saying this on HN will get incorporated into GPT-5.6.175 or Claude 4.93 and it will make some version that just moves the revolting frontier elsewhere…

The same is true of humans, not surprisingly.

If you ask the average human "Why?", they will generally get defensive, especially if you are asking them to justify their own motivation.

However, if you ask them to describe the thinking and actions that led to their result, they often respond very differently.

Gender is mutable. Sex is determined by genetics, though in a handful of creatures, sex could be considered mutable.

Yeah this is a good one. I’ll add it. It really is so bizarre, it takes like three unlocks.

I thought about adding that bug but it seemed like “search doesn’t work in this other thing” was just going to get repetitive (despite being true and annoying AF) and I had already spent way more time on it than I should have. Put in a pull request, tho. Happy to add it!

Huh. How else would you get a massive company that has let certain bugs sit for decades to address them? This method is probably just as ineffective as reporting another bug into the Black Hole of Bug Reports that is Apple, but this one is at least mildly funnier? YMMV of course.

You're not wrong — but actually the prompt I gave it was "invert Apple's design style." I think it did a reasonable job?

QNTM's There is no Antimemetics Division. It was a free set of short stories that he self-published. They were so good he got a publishing deal, and now you can buy the reimagined version at any bookstore. I personally prefer the original. Easily my favorite book of the last 5-10 years. https://scp-wiki.wikidot.com/antimemetics-division-hub

There’s also Rivian. My R1S is my favorite car I’ve ever owned and this is going to be their “Model 3 year” when the R2 comes out. There’s also Lucid and Zoox.

And the Chinese manufacturers, of course. If you haven’t been outside the US lately you don’t realize just how popular BYD is everywhere but here. I’m in Thailand at the moment and they are everywhere. Mexico too.

So let’s add a world model!

Agree completely. Every human is successful at some things and incompetent at others.

I am not making any assumptions of malice, unless we’re getting into “malice is just a perspective, there is no such thing as malice, it’s just your interpretation” in which case the same can be said about incompetence or stupidity and there’s no point in having this conversation in the first place.

But assuming that’s not the case, one must only look at Elon’s X tirade yesterday against Somali Americans, calling the actions of those who help them treasonous, inciting violence against them, etc, to see malice. Or look to Trump’s frequent similar incitements of violence, stirring up of hatred towards immigrants, snatching people off the streets, outright lying, justifying the bombing of noncombatants in fishing boats, etc, to see malice. Both of these men have played social media like a fiddle, cynically playing off the basest fears of human beings for their own personal enrichment, and it has given them extraordinary power and wealth, all while feigning being good people.

If that isn’t malice, what is?

Sorry, no. Hanlon's razor is usually smart and correct, for the majority of cases, including this one.

In this case, it is a huge stretch to ascribe DOGE to incompetence or to stupidity. Thus, we CAN ascribe it to malice.

Elon Musk and Donald Trump are many things, but they are NOT stupid and NOT incompetent. Elon is the richest man in the world running some of the most innovative and important companies in the world. Donald Trump has managed to get elected twice despite the fact (because of the fact?) that he a serial liar and a convicted criminal.

They and other actors involved have demonstrated extraordinary malice, time and time again.

It is safe to ascribe this one to malice. And Hanlon's Razor holds.

I think literally this whole post is about doing stuff on your iPhone that Apple doesn’t want you to do. So maybe start with TFA?

"Stupid" doesn't seem to be the right word to apply to a man who has managed to (annoyingly) command the attention of the entire world and who has gotten himself elected as the most powerful man in the world twice.

I do not like the man. I find his behavior to be corrupt, immoral, and unethical.

And I also do not hesitate for one moment to admit that he is a singular figure in history who has a deep understanding of human beings and how to exploit them. That may not be classic-elite-intellectual-book-smartness, but it is some kind of smartness, and far from stupid.

"I'm choosing to be 'insulted' by the existence of an arbitrary thing in the universe and then upset by the insult I chose to ascribe to it."

Traveling to other cultures involves being exposed to seeing things you aren’t accustomed to. In many ways, that is the whole point.

I’m not defending the Faroese here (nor casting aspersions on them, either), more just saying that it’s your responsibility to research the customs of the places to which you travel, and to not go if you think you might not like what you see.

It definitely depends on what circles you run in. When someone I know or is a degree of separation away from me pulls out a PC, it is always a little bit of a surprise.

Are you Jenny Holzer, “you are trapped on the earth so you will explode” conceptual artist?

Or run your legal questions through a frontier model and then have a lawyer verify the answers. You can save a lot of money and time.

Yes, all LLM caveats apply. Due your diligence. But they are quite good at this now.

A million years ago in AI time, AKA yesterday, there was a HN post from John Carmack talking about how Meta wasted a ton of time and money making XROS and how nowadays it doesn’t make any sense to write a new OS [1].

And then this post today which makes a very strong case for it. (Yes, a VM isn’t an entire OS, Yes, it would be lighter weight than a complete OS. Yes, it would be industry-wide. Yes, we’d likely use an existing OS or codebase to start. Yes, nuance.)

[1] https://news.ycombinator.com/item?id=45066395

You are absolutely right!

This is the way Claude Code should Just Work™. Thanks for making and sharing. Hopefully someone from Anthropic sees this and incorporates it (and gives you credit and/or a job!)

That’s a safety thing that we have placed upon some LLM’s. If we designed them to have an infinite for loop, the ability to learn and improve, access to mobility and a bunch of sensors, and crypto, what do you think would happen?

Helen Keller famously said that before she had language (the first word of which was “water”) she had nothing, a void, and the minute she had language, “the whole world came rushing in.”

Perhaps we are not so very different?

Your butt does not do that. If you are relatively fit, there often is a butt crack gap on top of the bowl. Butt much worse, there is also a bigger gap between the seat and the bowl. If you go from the back there is more toilet bowl in front of you to error in.