VeganCheesecake

Bitwarden inserts them automatically, and if I ever have to do it manually for some reason, it just doubles the fun. Hasn't happened to me yet, though.

I have relatively long Passwords, because why not, and had problems with pages restricting the number of characters you can enter in the login window, but not the registration window. Or restricting password length and cutting your password off, but not telling you about it, so you gotta figure out that they set the first 30 characters of the saved password as your password.

Always fun to deal with. I could make it a lot easier for me by just using shorter passwords, but I think deep down I'm a masochist.

But you only need one factor, access to your inbox?

Perform better is pretty relative. My Pi 4 running home assistant is super responsive, while also using little power and being completely silent, but it only runs a network of zigbee lights and sensors, controlled by zigbee switches.

I agree that more power is necessary for any local voice applications, but depending on the use case, the pi probably isn't worse than the alternatives.

What problems are you having? For me it was pretty straightforward. Just had to clone the git repo, run the start.sh script, and visit localhost:8000 in a browser.

Honestly, I know the feeling, and I'm not really all that old. I'm kinda busy at the moment, but I'll try to remember pinging you if I make a proper post.

I use a frontend called Silly Tavern to create a group with several "Personas" that I write a character definition for, in which I also outline the ruleset of the rpg framework I'm using. I then either run an LLM locally, or plug in an API Key for a cloud-based provider.

I then present them with the plot as Game Master and have them react, while doing their throws myself. Works surprisingly well, and is less dry than just going through the adventure you've written step by step.

Playtesting ttrpg campaigns, mostly. Can be more helpful than just playing it through solo, but LLMs tend to be really fucking uncreative.

I'm gonna keep not buying Teslas all year.

If you really want to use gpt-4 for a cover letter (don't think it'll help that much, but I won't judge), just get yourself an API Key and use the API with a local frontend. The requests you need for a cover letter will likely amount to a few cents.

I get the whole pirate spirit thing, but this all seems wonky at best. If you want fully free gpt-4, there's always Bing Chat.

I mean, it's Forbes. They probably assume you lease your appliances and have them replaced with the hot new model every 12 Months, or some shit.

If you really want that for some reason, that sounds like a job for one AI Smart Assistant. Doing it by having a different App and LLM implementation for every appliance seems stupid in so many ways.

Especially if they don't run them local, but essentially bundle the completely different service of a cloud hosted LLM with a fucking Tumble Dryer.