Gemini is our natively multimodal AI model capable of reasoning across text, images, audio, video and code. This video highlights some of our favorite intera…
You must log in or # to comment.
This is an impressive demo, it seems like just making training multimodal models approaches the appearance of symbolic understanding. It’s a surprise how effective this can be.
Edit: evidently it was faked https://techcrunch.com/2023/12/07/googles-best-gemini-demo-was-faked/