dmd

No, mine's a esoteric declarative data description/transform language. It's pretty damn weird.

That's the cool bit - you don't have to. CC is perfectly well aware and competent to implement it; just tell it to.

It's wild to me the disconnect between people who actually use these tools every day and people who don't.

I have done exactly the above with great success. I work with a weird proprietary esolang sometimes that I like, and the only documentation - or code - that exists for it is on my computer. I load that documentation in, and it works just fine and writes pretty decent code in my esolang.

"But that can't possibly work [based on my misunderstanding of how LLMs work]!" you say.

Well, it does, so clearly you misunderstand how they work.

The vast majority of americans have never used whatsapp, if they’ve even heard of it.

Kinda-not-really? Wayland has wl_region objects and wl_surface_set_input_region but wl_region only has axis-aligned rectangles. you'd end up approximating the circle (or whatever shape) as a union of horizontal rect slices, rather than a pixmap. you can't just hand over a pixmap mask, you have to decompose the shape into rects yourself.

I've got great news for you! https://en.wikipedia.org/wiki/Shape_extension

Yeah, in my user prompt I have "Whenever you are asked to perform any operation which could be done deterministically by a program, you should write a program to do it that way and feed it the data, rather than thinking through the problem on your own." It's worked wonders.

If you'd clicked the link, instead of just reading the title, you'd have known it was.

These days infants' hearing (including my own two childrens') are tested at birth, without them having to participate in the process at all (they can even be asleep)! https://www.audiology.org/consumers-and-patients/children-an...

It's air molecules vibrated by mucous membranes. Not real conversations.

Huh! I'm kind of stunned that we only use ~30x the power that we did back then. If I'd been asked to guess I would have added another 0 or even two of them.

“someone’s woman”?

jfc. What is the point? What do people get out of doing that?

Where does that 0.3 TW figure come from? That seems awfully high.

God forbid anyone read past the title.

Yet another person who responded to the title without clicking through to the article, which has nothing to do with support chatbots.

You wrote all of that in response to the title, without reading even one paragraph of the article? Wild. The article is not about support chatbots.

How does your assertion hold up give they've already written this code and it's used every day by millions of people?

You just have to turn it on with a MDM profile. It's just consumers they don't let use it.

I don't see how any of those require a constant-heartbeat loop. Those all work just fine in claude code / cowork.

https://github.com/obra/superpowers "brainstorming" is pretty much exactly this workflow, and it's great.

I'm guessing you're either from the midwest US, or not from the US. Am I right?

See my answer to that question is “er, yes, obviously??!” and so I assume, apparently incorrectly, that everyone is like me.

They're not even stitched together ; there's just no padding between the two images.

I can't figure out what "seals" or "break" mean in this sentence. What am I missing here?

Er - you know a magnetron doesn’t actually spin, right?

1) Like 80% of the world is smartphone-only

2) In my (wealthy, Boston area) suburb most high school students do all their work - including writing multi-page papers - entirely on their phone. They think laptops are for old people.

My overall philosophy for (my quite extensive) Home Assistant setup is “amy time a human interacts with the HA UI in any way whatsoever, that is a failure.” I don’t want dashboards, I don’t want a user interface at ALL other than for setting up new automation. The point of HA for me is the house should feel like the correct things happen by magic (and should be essentially unobtrusive and natural).

take a wild guess

I had a weird experience with thankfully very temporary aphasia 20 years ago, which I wrote a bit about here: https://dmd.3e.org/2005-11-23-aphasia-and-back-sunday-20-nov...

> Also, just to be clear-- are you saying there are blind tests where an expert tried playing multiple violins and couldn't guess better than chance which one was the Strad?

Yes, this has been done many times.