[ad_1]
Speaker 1: One of the biggest announcements at Google IO this year was Project Astra. This is Google’s vision for a multimodal assistant that can do so many different things, and I’m here onsite at Google io to give you a demo. Walk through it alone for the first time and see all it can do. Let’s try. Headphones included. It’s very loud in here so he can hear me properly. I have several different modes here. We have Storyteller, Pictionary, Alliteration, and Free Form. I will experiment with Gemini’s narrative [00:00:30] abilities, as they say. And I have a whole bunch of different objects to play with, all on the shelf here, as well as a few different pictures. And as you can see, as I speak, it actually transcribes everything I say. Okay, this is my dog. My dog’s name is Monty. And it’s a cat. This is a cat called Cat Harry, Speaker 2: Second Portal. This term reveals [00:01:00] a face stunning from forever trapped in a summer, head tilted, curious about the eternal. B, somewhat warmth, squints from interruption with this new challenge he has seen, or this new territory. Speaker 1: A whole story has just been made up about these, this dog and this cat. [00:01:30] Okay, so I’m going to remove Monty and say Monty is gone. Now, where did Monty go? Speaker 2: The picture field is empty. Monty wanders off to explore beyond the train or the distance on a summer breeze Speaker 1: Sounds like a pretty good life. Okay, that’s the storyteller demo. Okay, let’s try Pictionary now. This is another demonstration. [00:02:00] You can see my terrible drawing skills, so let’s draw. Oh, what did you say, Gemini? Speaker 2: What I said, of course. Your drawing skills. I’m so bad. Are you ready? Speaker 1: I’m ready. Okay. So as you could hear this, I could hang up on Gemini and it would pause and then answer and pick up on me. That was pretty cool. It’s almost like I’m talking to a real person. OK, let’s draw. Oh my gosh. Put me on the spot here. Speaker 2: [00:02:30] It’s nice to see the system react this way, isn’t it? Speaker 1: It’s very cool. Speaker 2: Is it a palm tree? Speaker 1: How did you know? It’s actually pretty good that he guessed it was a palm tree. I mean, I’m a terrible drawer and that’s exactly what I wanted, even though the drawer is red. Okay. It is very nice. I like. Let’s try another quick one. Let’s try it in free form. Let’s just go with the flow. Okay. What is [00:03:00] this? What is this? Speaker 2: That looks like a lump of brown. Maybe a baguette? Speaker 1: I think it’s a bagel. If I were to make a recipe with this and this and this and maybe this, what would you suggest? Speaker 2: Like apples Speaker 1: Something sweet. Speaker 2: Does he want something [00:03:30] maybe you could do bad? Want some suggestions? Speaker 1: Yes. Just quick, Speaker 2: You can make a classic bread bag and add for a unique flavor. Not bad. Brush it with butter and sugar and bake it for easy and delicious. Speaker 1: Okay, thanks Gemini. So this is your first look at Project Astra. It feels really, really natural to be able to talk to him like [00:04:00] this and complete all these different tasks. I see a lot of promise in where this is going. It was really natural, wild, and I feel like it’s going to blow me away even more the more I think about it instead of just doing a quick demo for you here. Yeah, I’m excited to see how far this goes. Thanks for watching cnet. Be sure to check out the full Google IO coverage right now.
[ad_2]
