is it pronounced beaucoup?

idk what to tell you, because I just tried it and it works

ah, this puts it together and it’s exactly what I was looking for, thanks

ah yes, I stopped watching the guy because of that and the clickbait, but he does make some interesting content sometimes.

so you haven’t tried it recently

maybe last you tried it was over 6 months ago, maybe you’re using the old google assistant, or idk, but it definitely works for me

yeah, that’s what I’m looking for. Do you know of a way to integrate ollama with HA?

1. They can and do; 2. LLMs can do tool calling just fine, even self-hosted ones.

I’ve been using more https://cheat.sh/ or --help on specific commands and subcommands.

It’s usually less noise than in a man page, and no need to install a specific man page for each command you want.

I don’t quite get what this is supposed to do. Is it basically a software to allow jellyfin/plex users to request media without needing a radarr/sonarr account?

it just means they’ll be a passive node, but still able to seed if they connect to the other node (edited). It’s the setup I have and I manage to keep an overall ratio >1, especially if the torrent is popular.

Even if you’re into AI coding, I never understood the hype around cursor. In the beginning, they were just 3 months ahead of alternatives. Today you can’t even say that anymore and they’re still “worth” billions. You can get a similar prediction quality from other editors if you know how to use them, paying a fraction of the price.

Cursor also chugs on tokens like a 1978 Lincoln Continental, that’s how they get marginally better results, so bringing your API is not even a viable option. The first time I tried it, I asked a simple 1-line edit on a markdown and it sent out 20k tokens before I could say “AGI is 6 months away” and still got the change wrong.

it works!!!

I miss start menu ads, intrusive bing searches, copilot upselling, MSN news, and uninstallable things I’ll never use on my PC like Xbox.

yes, the system will likely use some swap if available even when there’s plenty of free RAM left:

The casual reader1 may think that with a sufficient amount of memory, swap is unnecessary but this brings us to the second reason. A significant number of the pages referenced by a process early in its life may only be used for initialisation and then never used again. It is better to swap out those pages and create more disk buffers than leave them resident and unused.

Src: https://www.kernel.org/doc/gorman/html/understand/understand014.html

In my recently booted system with 32GB and half of that free (not even “available”), I can already see 10s of MB of swap used.

As rule of thumb, it’s only a concern or indication that the system is/was starved of memory if a significant share of swap is in use. But even then, it might just be some cached pages hanging around because the kernel decided to keep instead of evicting them.

if my system touches SWAP at all, it’s run out of memory

That’s a swap myth. Swap is not an emergency memory, it’s about creating a memory reclamation space on disk for anonymous pages (pages that are not file-backed) so that the OS can more efficiently use the main memory.

The swapping algorithm does take into account the higher cost of putting pages in swap. Touching swap may just mean that a lot of system files are being cached, but that’s reclaimable space and it doesn’t mean the system is running out of memory.

you haven’t seen my frontend code

potentially relevant: paperless recently merged some opt-in LLM features, like chatting with documents and automated title generation based on the OCR context extracted.

https://github.com/paperless-ngx/paperless-ngx/pull/10319

Python stack traces give you all files involved in the error, with their lines. I don’t know what you’re talking about

how’s that the same thing as in the picture?