VOOZH about

URL: https://huggingface.co/clem/gemini/discussions/1

⇱ clem/gemini · Testing multi-modal capabilities

Testing multi-modal capabilities

#1
by clem - opened

In February, Satya Nadella said that "I want people to know that we made them dance". Let's see if Google is now finally ready for an epic dance-off!

[EDIT]: This is probably not Gemini, please see below posts

Trying their own example ("we first gave gemini a screenshot of this figure then we asked it to generate the code require to plot it"). All 3 drafts have error in code and don't run..
👁 image.png

👁 image.png

People are missing that it literally is only Gemini Pro for text based prompts. As soon as you give it an image to process it's PaLM2

Trying their own example ("we first gave gemini a screenshot of this figure then we asked it to generate the code require to plot it"). All 3 drafts have error in code and don't run..
👁 image.png

👁 image.png

Not Gemini pro

Thanks @masonadams22 ! Sorry for the misleading post

Thanks @masonadams22 ! Sorry for the misleading post

No problem!

· Sign up or log in to comment