21 | Rustacean | Metallurgist | Cable Chewer
/
Joined March 2022
- Tweets24.3K
- Following733
- Followers1.9K
- Likes81K
Pinned Tweet
Introducing Hercules Agent
A local Coding agent that run on your hardware.
Support Nvidia, AMD and Apple Metal GPU
1 to 8 bit Quantized, FP8 and FP16 support
Written in Rust using Ratatui and Kramaframe for insane animation.
github.com/CosmoBunny/hercul…
I forged so much on Hercules Agent 🔥
Alpha version is now released 🚀
- support 1,2,3,4,5, ... bit quantized model
- support every GPU
- swarm mode support
Used @ratatui_rs (created by @orhundev)
Gotta make screen record and upload
Git: CosmoBunny/hercules-agent
H*ll naw
AI generated music is 1000x better than real music.
Today I canceled Spotify and SiriusXM because I finally tested Suno.
What sold me was the first prompt I gave it:
“My favorite artists are A Day to Remember, Bring Me The Horizon, Spiritbox, Bad Omens, and Sleep Token.
Analyze all their hits and generate a song I’m likely to love based on those artists.”
It one shots an absolute banger in 10 seconds.
I'll link the song in the next tweet for anyone curious.
Why would I ever go back to Spotify/SiriusXM when I can generate music perfectly tailored to my taste on command, for free?
Not affiliated with Suno in any way btw, it was just one of those moments where I was so impressed with AI’s capability I had to say something about it.
Imagine the need of RAM and GPU power to run this model
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.
ANGSUDO retweeted
.@allegrajacchia heyyy, i wanted to bring something to your attention.
it seems like X's automated filters are falsely flagging my friend @whatRanjuSaid's Muse posts for chii!ld 3Xploitation.
she already had to delete one post, and another is being flagged right now. it's just a Muse mascot with a butt
if any X employee sees this, could you please look into it? it's a false positive and we'd really appreciate your help.
Noooo, Stanky suspend again
Free the @TheKingOfstank let him do his passion, if he can't draw artwork then don't k!ll his passion atleast.
Mixed LLM maybe the next future of AI where it exist multiple LLM with boundry different LLM sector has seperate weight based on own category number. And one main switch matrix make sure which sector will be open and which one will not, it will save lot of power and memory usage.
