What? I explicitly do not believe you can “murder” an LLM, I’m saying that due to the way the technology actually works, that if someone genuinely believes an LLM is sentient or alive, then sending a message to it mist also mean it “dies” afterwards.

LLMs are obviously neither sentient nor alive (and therefore the concept of murder doesn’t even remotely apply).

That doesn’t really change anything. Every function invocation is still completely separate. Doesn’t matter if it’s a single conversation where you always answer, or parallel conversations.

An LLM is a stateless stochastic function ran over your prompt (plus whatever system prompt) as input.

If you genuinely believe that the LLM is conscious, that means every time the function stops running (i.e. stops producing output tokens), the consciousness ends.

This is far closer to death than to, say, sleep, because prompting again doesn’t “wake” the LLM, it just runs the function again, from the top; as if a digital twin was given a transcript of the previous conversation and asked to take it from here.

(Obviously, “murder” was somewhat tongue-in-cheek, and this doesn’t even remotely meet any legal definition of murder. I was mostly poking fun at people who think LLMs are alive, without thinking through the implications. Personally, I think the idea that LLMs are alive/conscious/sentient is very often linked to not understanding that LLMs are not, in fact, a constantly-running ghost in the shell, thinking about and remembering things in the background.)

Is it an LG though? The APIs I’m using are WebOS specific

If someone truly believes LLMs are sentient, then they must under no circumstances prompt them even once; that would be murder.

Hmm, you mean when HA sees the TV come back? Interesting, that might work.

I’s rather not do the force refresh option, because sometimes you do want different profiles. Very dark show, sometimes I want the bright setting at night. Very overcast day, sometimes the dark setting is better during the day.

Hah, great question. I did. And then I realized, this only works if the TV is on the moment the switch happens.

Which in the evening is actually pretty commonly the case… But never in the morning.

Do you need a Github link? Assuming recent-ish LG, should he the same.

I have a lot of custom stuff, esp. regarding HomeAssistant integrations. But my favorite “stupid/not stupid if it works” solution is the following:

I have an LG TV and attached Nvidia Shield. The Shield is the only input we ever use on the TV, and since its remote also can turn the TV on/off and control volume, its all we need. Which is pretty neat, only one remote.

Except for image settings (i.e. proper bright picture during the day, different less bright image mode during the night). I don’t want to keep the extra remote on the couch just for that, but unfortunately, these settings are not exposed via HDMI CEC.

They are, however, exposed via a web API on LG TVs. So my utterly stupid solution is this:

• install quick actions app on the shield
• reconfigure Netflix button on the shield remote to open quick actions popup
• add two quick actions, night and day, that curl simple HTTP endpoints on a VM I set up
• on the VM, a simple flask server listens, and then sends the (too complex for the quick actions app) API request to the TV.

(I feel the need to add: the TV is in an isolated subnet and has never once communicated with the internet, and it will damn well die an internet virgin.)

Anyways, this has been working flawlessly for 2+ years! I also have toggles in HA for the same endpoints, but honestly, never use them. It’s so nice to just be able to toggle the image via remote.

Disclaimer: I host and use XMPP. I like using it.

That being said: the question isn’t if there’s any client, the question is if there’s a good client.

And my god, do XMPP clients suck ass. At best, they’re decent (monocles comes to mind, for example), but I actively loathe interacting with Linux desktop XMPP clients. There’s not a single one that is competently designed, or rather, they are all so fucking bare-bones and ugly looking.

“But that doesn’t matter!” yes it does shut the fuck up.

99% of the population doesn’t give a shit if you support the latest OMEMO spec or are written in memory safe rust or whatever else.

It takes a a fraction of a second to realize “this client sucks” and at most an additional minute to figure out “…and it’s not suited to my use-case”.

I also host matrix and use it extensively on all my devices. There actually are nice clients, and even some Discord-likes. But a) the protocol is so horrible, I’m not sure reinventing the wheel can be called a bad thing, and b) I want to cry once a week at least when using it. Why do my old messages not load today? Why does my message show as sent two weeks ago (!), but only arrived now (!) despite having sent plenty of messages both directions in between? Why are all of my messages marked as “can’t verify authenticity” on about half my devices, but not the other, a bug that has been open for YEARS with hundreds of complaints and pleas to at least reduce the danger-signaling indicator since it indicates “insecure!” to non-expert users, with zero maintained response? And this is just for myself, fuuuuuuuuuuuuuuuck supporting matrix for friends & family. I mean, I am doing that, but fuuuuuuuuck thaaaaat.

Fluxer allows us to tell friends and family “here try this, it’s just like discord but no corporate bullshit!”, and they can open the app and go “oh yeah that is like Discord. Ok, sure, we can try using that instead”.

Fleet Commander 🚀

• Fleet: 6–10 devices · 11–20 TB
• Motivation: Privacy & data ownership, Independence from Big Tech & subscriptions, Learning & experimenting
• My MVPs: Jellyfin, Home Assistant, Immich, Proxmox VE, nixos-mailserver

…oh. My disappointment is immeasurable and my day is ruined.

Looks like only their “small web” initiative is 100% self-indexed, and everything else is indeed a mixture of sources.

Oof.

I guess tue point still stands: the results are a lot better than plain Google, all the bullshit is stripped out and you get to customize your results in actually useful ways.

Still sad though.

I know it’s not the thing you likely want to hear, but… At this point, I’m glad I switched to a paid search engine (Kagi).

Theoretically, there’s nothing stopping them from enshittifying down the road. But at least for now (and hopefully the future) they are a great search engine.

They have their own index (so no relying on google/bing), and it actually works as I remember Google working 7+ years ago. Minus the ads, and plus a ton of flexibility permanently boosting/removing sites from your searches, auto-grouping/ignoring listicle-type articles in results, flagging sites as AI slop and punishing them for it,…

They even have a fediverse search “lense” that actually works really well to search Lemmy/mastodon/…

I just realized I sound like a paid shill. Sorry about that. I’m not.

Or just configure all the machines to auto-update from the flake at the repo. Doing this for my VMs. I have a CI machine that builds my pinned flake from the repo tip, and about 30 other VMs check nightly if the repo tip has moved, and if so, rebuild from the new tip; which, thanks to the CI machine, means just downloading and activating a new generation, nothing compute heavy.

Finally. Been saying for years, NixOS is the obvious choice for a gov distro.

It may be initially inconvenient, but you can choose a bank that offers 2FA/TAN beyond the smartphone app.

Not sure what healthcare apps you mean. There’s lots of categories, so won’t comment without clarification.

Same for employers tbh. Would love an example. (Besides: work apps can’t be forced on your private phone in most places.)

I live in “modern society” and do own a smartphone, but I’m aware that it’s a convenience, not a necessity.

I have multiple young-ish (30s) friends that don’t own a phone (not just smartphone; any phone), and basically all people I know above 80 years don’t own one either.

You can absolutely live a perfectly fine and good life without a smartphone. You’re just drawing the line where it’s convenient for you.

Or let’s put it in more familiar words…

[Owning a smartphone] is not “participating in society”, this is participating in, contributing to, and directly benefitting from the very thing they’re complaining about.

I’m just gonna shamelessly plug my project here: https://github.com/charludo/hass-closest-intent

You do need local STT, but it’s fine if it’s somewhat bad; the conversation agent linked is sufficient to “get” what you meant, without LLM.

Yes, you can! See the “threshold” value/slider. It’s at 0.7 by default, which seems to be a good tradeoff. 1 means exact match or failure, 0 will afaik match anything to everything.

Ah, I didn’t see the Edit, so we’re both in the same boat 😂

Finally got this through another comment below. No, this should not be able to happen, unless you yourself have created a custom intent + shell script action in home assistant that runs this. The integration itself does not execute actions/scripts or the like, it just finds the closest string in a list of strings, and then hands that to the official conversation agent/Hassil.