Very cool to see Chatbot Arena adding image uploads capability. Human preferences and vibe are the ultimate evals. They have a made a clear distinction between LLMs and it's nice to see that happening for multimodal models as well.
— Jean de Dieu Nyandwi (@Jeande_d) 20 juin 2024
Vibe-Eval(https://t.co/PinId9novu) shows a nice… https://t.co/CE8xxXetG0 pic.twitter.com/RCQowXFeSu
Very cool to see Chatbot Arena adding image uploads capability. Human preferences and vibe are the ultimate evals. They have a made a clear distinction between LLMs and it's nice to see that happening for multimodal models as well. Vibe-Eval(
https://
arxiv.org/abs/2405.02287) shows a nice