npz

joined 1 year ago
MODERATOR OF
[–] [email protected] 142 points 2 weeks ago (4 children)

Newsweek was unable to independently verify at the time of publication whether the people on the boat were from the antifa movement.

Oh, fuck off. I'm unable to independently verify whether the people on the boat were Newsweek employees.

[–] [email protected] 161 points 1 month ago (41 children)

Well they're still blowing up kids with these things so idk if it's the most brilliant targeting technique

[–] [email protected] 9 points 3 months ago (2 children)

I think there's different meanings in different contexts. You don't want to be the "creepy weirdo" kind of weird, but then there are people who are into weird art or have weird kinks and they are great

[–] [email protected] 23 points 3 months ago (1 children)

Ian Miles Cheong's Twitter-fame is baffling to me. I often follow conservative people on there if they're in an important position of some sort, but this guy has accomplished nothing that makes his perspective more relevant than the average schmuck.

[–] [email protected] 22 points 3 months ago (21 children)

It seems like such a lazy non-solution. Essentially telling shooters "Hey, from now on, you can only use ALL THE OTHER GUNS" as if that solves something.

[–] [email protected] 5 points 4 months ago* (last edited 4 months ago) (12 children)

Unless there's some agreement / licensing thing prohibiting it, and considering that lyrics don't change, they should be able to do some caching for a total of 1 API call per song

[–] [email protected] 19 points 4 months ago (1 children)

Wonder what the percent of AI datasets being propaganda is

[–] [email protected] 7 points 4 months ago

I'm glad they're adding support, but I also feel like this is a hard one to sell to the general public. If it creates a better experience, word will get around about it, but going on stage and talking at length about how there's a new messaging protocol would have been a challenge for non-technical viewers

[–] [email protected] 5 points 4 months ago (3 children)

I just read they decided to default it to off. They should remove it entirely imo, but with this move, it costs IT departments $0 and 0 hours of their time to worry about.

I think business + government + education usage is more important for them than personal, and as long as this costs them nothing, I doubt it makes a dent in anyone's plans. Could have been an apocalypse if defaulted to on though.

[–] [email protected] 10 points 5 months ago (1 children)

I don't think Steam supports any sort of sliding scale system and they have a price parity rule which would be broken by offering it elsewhere

[–] [email protected] 55 points 8 months ago* (last edited 8 months ago) (18 children)

(for demonstration purposes only, please don't think I'm like this)

1
submitted 1 year ago* (last edited 1 year ago) by [email protected] to c/[email protected]
 

https://github.com/ghostpad/ghostpad

This is a major change behind the scenes, which greatly simplifies the install process - it's now exactly the same as Kobold's install process. npm is no longer required, and the process to run Ghostpad is now exactly the same as the process to run Kobold. Upon installing, you have three UIs to choose from

Ghostpad @ [host]:5000

UI2 @ [host]:5000/new_ui

UI1 @ [host]:5000/classic

Full changelog

- Ghostpad's frontend is now 100% static, built using Bun and Vite.
- Removed "game started" check in chat mode - it will now use chat formatting 100% of the time, even if the story is empty.
- Merged with latest revision from henk's branch
- Changed hostname setting to "Hostname Override".  This will now default to empty, and the socket connection will default to the current URL
 
  • Eliminated many excessive React renders
  • Fixed a bug where an action was being updated by index instead of ID, causing broken story updates in some cases
  • Added Audio Input and Audio Output options to the top-right menu. With both of these enabled in desktop Chrome, you can now have an audio-only conversation with your AI. These are based on the open Web Speech API spec, but have cross-browser issues and should not be considered a stable feature.

Important: Chrome's implementation of the speech recognition API is not offline - it will send your data remotely.

TLDR: Better performance. less bugs. don't use audio features yet if you dislike Chrome or value privacy

If you are serving Ghostpad from a different host than localhost and want to use speech recognition, you need to enable Insecure origins treated as secure and add that URL in chrome://flags

1
submitted 1 year ago* (last edited 1 year ago) by [email protected] to c/[email protected]
 

First post in this brand new community! Welcome.

Ghostpad is an interface built on top of a light fork of KoboldAI. You can check out the project repo for more information.

I'll be sharing updates here as they happen, as well as in the KoboldAI Discord in #ghostpad

This weekend there were a few important backend changes:

  1. Support for Exllamav2. After manually installing exllamav2 into the Kobold environment, it should be detected and available in your list of model backends. The reason I'm not auto-installing it is because I've heard this can be quite the project in Windows. My experiences in Linux have been smooth. I hope to make this a more automated process once the build process is simplified.

In Linux, the process should be as simple as cd'ing to your Kobold directory and entering

git clone https://github.com/turboderp/exllamav2.git
sh commandline.sh
pip install ./exllamav2
  1. Support for AutoAWQ. If you follow the latest Llama model releases in Huggingface, you've probably noticed a huge number of releases in this format. AutoAWQ is now an auto-installed dependency of koboldai-ghostpad and should not require any additional steps to use. There is a "fuse layers" option which can greatly improve performance, but I've encountered random errors when using it, so I recommend leaving it off for now.

  2. Python 3.10 bump. Official KoboldAI is still on Python 3.8, but I'm making the leap so that I can support the type-hinting features used in AutoAWQ. It's possible that this may lead to some unexpected issues, but it's been stable for me so far.

I don't want to make any promises, but one of the features I'm most interested in implementing next is a combination of speech-to-text and text-to-speech, allowing for you to have audio-only conversations with your AI.

view more: next ›