token generation of a tiny model. Hardly worth anything.

It's a one-time download shared by all websites that use the Prompt API.

What's a bigger issue is that the models on most standard PCs are both tiny and slow. I was going to try using the Prompt API to change the text of (infocom) text adventures on the fly. But for many PCs, this will currently be too slow to be feasible.

The Prompt API uses the model that's available in your browser. For Edge I believe it's Phi4.

Developing weapons is pretty high on my list of shitty things to do as humanity.

We will probably keep doing it until we encounter an alien intelligence and snap out of it.

Just curious, are you purposely mocking the LLM writing style?

That’s how everybody in academia, tech, and published authors in general used to write.

Where do you think the LLM is getting it from? ^_^

On a Mac, at least, the "correct combination of buttons" is trivial and easy to remember, even for someone like me who rarely uses em-dash. (But, I want to start using it more because I'm sick to death of people treating it as a scarlet letter.)

Option-shift-hyphen

Thanks for sticking up for my humanity ;)

On Linux, with a compose key, it's <compose><-><-><.> (at least with the settings I have, I don't think I overrode that one). "⸻" is even more fun. You can even make your own sequences, e.g. I've got <compose><O><h><m> for "Ω", and <compose><m><u> for "μ", very handy for electrical stuff like "160μA at 1.8V needs a resistance of 1.25kΩ, dissipating 288μW".

In pedantic tradition, I would like to gently remind you that there should be a space between a number and its unit, according to SI standard/NIST.

Microsoft Word changes "--" to an em-dash, by default.

> or else this person happens to know the correct combination of buttons to make that happen.

Yes, some people care about maximum impact of their words.

> at least 20-40% of social media traffic is bots (and probably higher with better LLMs), so it is usually safer to just assume.

Look around you. If you see 40% bots in HN comments, find a therapist.

If you add a web page (a PWA) to the home screen, it can do push messages on iOS since a couple of years.

The average person doesn't know this, nor what a PWA is.

Source: consulted for a company that had a PWA and paid me a lot of money to make it a native app because their users didn't know how to use the PWA.

there still a lot of jank. on ios u can only doo this with safari, and even then u loose actual safari niceties like trad browser ui. and idk why but it op ens link in actual safari even if its the same app. unless u have a single page app that does nothing this is not a viable route/.

nobody knows how to do this; they do know how to install an app

They make it difficult to find even if you’re looking for it.

The Apple story on PWA is “Fuck ‘em until our last breath.”

cortecs.ai is the EU openrouter alternative.

it is even smaller, i saw only 4 people on LinkedIn

Huggingface isn‘t european just because they have offices there.

Nvidia did with Nemo.

And they got sued :

https://www.reuters.com/technology/nvidia-is-sued-by-authors...

Every lab has been sued whether they released training data or not.

I get the feeling that with LLMs in the mix, in-house server management can do a lot more than it used to.

Perhaps it saves some time looking through the docs, but do you really trust an LLM to do the actual work?

Yes and an LLM checks it as well. I am yet to find a sysadmin task that an LLM couldn't solve neatly.

A nice bonus is that sysadmin tasks tend to be light in terms of token usage, that’s very convenient given the increasingly strict usage limits these days.

Yes, with a lot of reviewing what its doing/asking questions, 100%

By this point? Absolutely. They still get stuck in rabbit holes and go down the wrong path sometimes, so it's not fully fire and forget, but if you aren't taking advantage of LLMs to perform generic sysadmin drudgery, you're wasting your time that could be better spent elsewhere.

The internet of 20 years ago was awash with info for running dedicated servers, fragmented and badly-written in places but it was all there. I can absolutely believe LLMs would enable more people to find that knowledge more easily.