A place for developers to talk about building on Farcaster.

/dev

Chat gpt, Claude, Perplexity all are down for me 
It's time to use my mind abit🫠

groq is working perfect rn, set the model to "llama3 70B "
Its performance is close to gpt4 and super fast.

groq is working perfect rn, set the model to "llama3 70B "
Its performance is close to gpt4 and super fast.
https://groq.com/

Exploring new horizons, one day at a time
A simple geek

e/acc || Building @ /imgn || Dogecoin core dev 2013/14

Its still grok for me😅 
I didn't expect Meta to release it, open models will win imo

..that is really unfortunate naming.

I didn't even see the "q", I just assumed X's Grok. Which is barely worth 4GB of VRAM, let alone its titanic MoE size.

llama3 70b is genuinely frightening. I thought the 400b model might rival an early gpt4, but 70b is already on its heels.

Absolutely insane lift from meta tbh