Content pfp
Content
@
0 reply
0 recast
2 reactions

Kazi  pfp
Kazi
@kazi
Nvidia silently just dropped a 70B open model that beats gpt-4o and sonnet 3.5 lol. Looks like the actual Arena-Hard score is 70.9, which is wild considering llama-3.1-70b-instruct is 51.6
2 replies
3 recasts
29 reactions

shoni.eth pfp
shoni.eth
@shoni.eth
Why dev tho
2 replies
0 recast
5 reactions

Pain🖤🌹 pfp
Pain🖤🌹
@painn.eth
Might not have access to /ai
1 reply
0 recast
2 reactions

shoni.eth pfp
shoni.eth
@shoni.eth
I had no idea you felt this way about me
2 replies
0 recast
1 reaction