Back

Let's start from the end, the model is better at math, at multilingual benchmarks, is less harmful and we hope chatbot Arena results would come soon.

What's behind it?
Other models collect all your data, they don't even allow deletion (please share it with the world too https://chromewebstore.google.com/detail/sharelm-share-your-chat-c/nldoebkdaiidhceaphmipeclmlcbljmh )
But what do they really do with it? They pretrain, but the model doesn't change during the talk, or reflect or learn, but you do...

So, we changed that.
I, for example, taught it Hebrew by just talking to it here (took a few hours, sure, but just imagine the potential)
It is already so smart, it gets new concepts unbelievably fast!
https://huggingface.co/spaces/feel-fl/open-human-feedback-chat

How did a community manage to do it?
Long story, but we had fun playing with interactivity; many of us built different things and merged them. We care about people, interaction, LLMs, us
& we followed no rules

Share or build with us!
https://discord.com/invite/KMndsqwMaZ