AI companies should not pick up naming models after astrological signs, after a while it will be hard to tell apart model reviews from horoscope.
Llama seems to be tricked up by simple puzzles that Gemini does not struggle with, in my experience.
I've found Gemini Pro to be the most reliable for function calling.
> Geminis are unusable
how so?
In my experience, Gemini models are far worse than any other frontier model when it comes to hallucinations. They are also pretty bad at getting caught in loops where pointing out a mistake makes it flap between two broken solutions. And obviously the overzealous softly stuff that other people have mentioned.
Yep, idk why would anyone use gemini instead of chatgpt or claude.