Maybe similar to the imperceptibility of using the name of a famous bear in a certain country, there is an upcoming imperceptibility of using the name of a certain dish in another.

Not convincing. I was hoping it would go down the xslt path, which is a lost art. I despised and loved xslt at the same time, and there’s no question it was an artful enterprise using it.

XSLT I see as a tragedy. The match / patch processing model is so elegant, but the programming langage built around it is such a disaster (the XML, various langage semantics e.g. the implicit context, the gimped semantics, and the development environment or lack thereof).

I think a simplified Haskell-ish script host (à la Elm) with a smattering of debugging capabilities would have been amazing.

There’s an acquaintance here in Australia that has built something similar without the crazy terminology and it is pretty solid.

Quoting: “ What I’m describing is different. I’ll call it Vibe Discovery: you don’t know what you’re building. The requirements themselves are undefined. You’re not just discovering implementation - you’re discovering what the product should be.

The distinction matters:”

What is it with this pattern of phrases that screams LLM to me? Whenever I come upon this pattern I stop reading further.

Not only does it scream LLM output, I happen to find it almost always grating. It's fine enough when something is labeled as AI output, but when it's nominally a human-authored document it's maddening.

Claude tics appear to include the following:

- It's not just X, it's Y

- *The problem* / *The Solution*

- Think of it as a Z that Ws.

- Not X, not Y. Just Z.

- Bold the first sentence of each element of a list. If it's writing markdown, it does this constantly

- Unicode arrows → Claude

- Every subsection has a summary. Every document also has a summary. It's "what I'm going to tell you; What I'm telling you; What I just told you", in fractal form, adhered to very rigidly. Maybe it overindexed on Five Paragraph Essays

> Unicode arrows → Claude

Oh no!! Yet another thing I've been doing for the past decade which will now make me look like a robot. I thought my penchant for em-dashes was bad enough.

I have a keyboard shortcut to make the arrows. I think they look nice.

oh I think they look nice too but unfortunately they are a Claude thing now :( though I think if you use them judiciously then it won't make the whole document look generated, it's really when it's deployed in the way Claude does that it's noticable

One way I'd describe it is LLMs say lots of things that technically make sense but aren't quite like anyone would normally say it.

And secondly they like to use more nouns for things, in my experience.

Of course all this is just what I observe currently and could well become different for better and worse in future versions.

It’s just like my friend has a distinct way of speaking. LLMs also have a distinct voice.

Right, which is why it's so strange to suddenly see every other readme and blog post that gets shared on this site speaking with the same tone of voice. Dead Internet theory finally came here.

I don’t mind reading LLM output, but it feels like plagiarism when people won’t admit they’re doing it.

I misjudged the amount of dislike HN users have for AI generated writing. I have added a "meta" section explaining how the post itself was written by AI, directed by my own taste. Here's the meta - https://www.kikkupico.com/posts/vibe-discovery/#the-meta

To be frank, I don't think AI-generated writing is inherently bad. Since there appears to be a strong bias against it, I will stick to writing blog posts by hand.

It can be interpreted a different way too. Apple is just a channel for TSMCs technology. Also the cost to build a fab that advanced, in say a 3 year horizon, let alone immediately available, is not one even Apple can commit to without cannibalising its core business.

tap tap tap tap tap tap tap tap tap tap tap

I would see a potentially more liberal use of atomic, that if the repo state reflects the totality of what I need to get to new version AND return to current one, then I have all I need from a reproducibility perspective. Human actions could be allowed in this, if fully documented. I am not a purist, obviously.

I hear you, and mostly share the point of view, but that’s what people were saying about the instagram valuation too.

Survivorship bias, I think. Our go to is the big, high profile success. But look at the amount of money Zuck has wasted on the Metaverse. He’s most definitely fallible.

What's the dollar-per-user figure between these two examples?

Instagram only had approx 10mn users when acquired. That was a long time ago though, and Facebook was at a very different stage in its lifecycle.

The Turkish password word may be the same used for signature? I suspect so, because in Greek we have the Greek word for signature but also a Turkish loan word τζίφρα (djifra).

imza is signature while şifre is password. I imagine the conflation occurred because signatures are used like passwords for authentication...

Likewise, the monogram of the sitting english monarch (as seen on postboxes and so forth) is the "Royal Cypher".

https://en.wikipedia.org/wiki/Royal_cypher

Hmm i don’t think that one is related in Turkish — i only know of “imza” as signature, but there could also be other variants.

Isn’t a JavaScript engine interactive ?

No regular user interacts directly with a JavaScript engine, not in the sense that they interact with a text editor, a video editor, an audio editor, a CAD application, a medical imaging application etc. etc. etc.