Hands-on with Gemini: Interacting with multimodal AI

2023/12/07 00:01に公開 6分23秒

基本データ

#	Data
最高順位	9位
最低順位	27位
増加再生回数	+1407889回
ランクイン日時	2023/12/07 18:45
ランク圏外日時	2023/12/10 1:59
急上昇継続時間	2日07時間14分
再生回数	810085回

※再生回数, コメント数, 高評価数, 低評価数, 評価数合計, 高評価割合は初回ランクイン時の数値

急上昇ランキング推移

日時	順位	再生回数
2023/12/07 18:45	18位	810085回
2023/12/07 19:15	17位	852951回
2023/12/07 19:59	16位	880524回
2023/12/07 20:45	15位	912631回
2023/12/07 23:15	14位	1022021回
2023/12/08 0:45	13位	1094733回
2023/12/08 1:30	12位	1127908回
2023/12/08 2:30	11位	1184480回
2023/12/08 2:45	10位	1198375回
2023/12/08 11:30	9位	1431266回
2023/12/08 11:59	10位	1474810回
2023/12/08 14:59	9位	1561567回
2023/12/08 15:45	21位	1581182回
2023/12/08 15:59	20位	1587250回
2023/12/08 18:45	27位	1605428回
2023/12/08 21:15	21位	1694018回
2023/12/08 21:45	22位	1715575回
2023/12/08 21:59	24位	1726538回
2023/12/08 22:45	25位	1767334回
2023/12/08 23:15	26位	1781091回
2023/12/09 0:00	25位	1803948回
2023/12/09 0:30	27位	1817219回
2023/12/09 0:45	25位	1821219回
2023/12/09 1:00	26位	1830503回
2023/12/09 2:00	24位	1861595回
2023/12/09 3:45	23位	1914165回
2023/12/09 4:45	22位	1941208回
2023/12/09 8:45	23位	2028977回
2023/12/09 12:45	24位	2081662回
2023/12/09 16:15	25位	2115521回
2023/12/09 21:45	26位	2177556回
2023/12/09 23:30	27位	2193964回
2023/12/10 1:59	27位	2217974回

Gemini is our natively multimodal AI model capable of reasoning across text, images, audio, video and code. This video highlights some of our favorite interactions with Gemini. Learn more and try the model: https://deepmind.google/gemini

Explore our prompting approaches here: https://goo.gle/how-its-made-gemini

For the purposes of this demo, latency has been reduced and Gemini outputs have been shortened for brevity.

Subscribe to our Channel: https://www.youtube.com/google
Tweet with us on Twitter: https://twitter.com/google
Follow us on Instagram: https://www.instagram.com/google
Join us on Facebook: https://www.facebook.com/Google

0:00 Intro
0:19 Multimodal Dialogue
1:32 Multilinguality
2:04 Game Creation
2:31 Visual Puzzles
3:17 Making Connections
3:39 Image & Text Generation
4:06 Logic & Spatial Reasoning
4:55 Translating Visuals
5:27 Cultural Understanding

サムネイル画像（最高画質）

人気コメント

1: @dpsdps01 2023/12/07 0:42

Absolutely mindblowing. The amount of understanding the model exhibits here is way way beyond anything else.

2: @ChrisBrooksbank 2023/12/07 0:54

Im glad to see Google back in the game, this looks next level.

3: @phils2967 2023/12/07 1:32

This is impressive, the applications in surveillance are scary to think about

4: @BECHEEKHA 2023/12/07 3:50

Very impressive. Want to try it.

5: @imqwerty5171 2023/12/07 0:12

Impressive. Waiting for Microsoft and OpenAI to play their move ⏳

6: @EricaCalman 2023/12/07 3:07

Even knowing this was a curated and controlled test it's as impressive as it is worrying.

7: @Inter-Dimensions_Studios 2023/12/07 2:17

I have always thought Google has the best chance to take generative A.I. to a super level.

8: @Isaac-oe2xo 2023/12/07 0:38

It would be great that, as it generates images and audio on the go, it also could generate docs, sheets, slides and even give you some folders with elements inside, maybe in a zipped folder. I dunno, the posibilities are inspiring. When will this model be avaible to the public? It could turn into my principal AI tool!

9: @mayankmittal9900 2023/12/07 0:17

Taking AI to next level collaboration

10: @shoupastarz 2023/12/07 8:13

I knew you guys were working on something AMAZING. Glad to see ya back! This is a complete game changer! 💜

11: @Yassine-tm2tj 2023/12/07 0:13

What a journey we’re about to embark on!

12: @technophile_ 2023/12/07 4:16

Mind Blown 🤯 Kudos to every single developer who worked on this! You are amazing!

13: @jeffreymitchell4904 2023/12/07 1:41

The real-time element is by far the most impressive. These sorts of asynchronous interactions are what AI has been missing thus far.

14: @brentshaffer9773 2023/12/07 0:18

Realizing the yarn examples are displayed against the same backdrop as the AI is seeing is both impressive and creepy.

15: @user-fn9cm5lr5k 2023/12/07 3:08

the level of abstraction Gemini is capable of is mind-blowing

16: @21EC 2023/12/07 6:40

I got shocked and mind blown seeing how smart Gemini is in this video alone, it's kinda scary how advanced and smart it is, what is it? a primitive initial AGI? just WOW

17: @ShpanMan 2023/12/07 1:33

Well done Google, if the model *actually* answers these (and no, it won't be this fast), then you have not disappointed us - the wait was worth it! Now to Gemini 2...

18: @vip_bimmervip_bimmer8033 2023/12/07 8:00

Seems excellent. Coming from the AI industry, this is impressive. Good work getting back in the game of AI.

19: @horacehxw 2023/12/07 1:29

This is soooo amazing! Much more dynamic and interactive than GPT. Can't wait to give it a try!

20: @Press1ForNick 2023/12/07 1:43

This is mind-blowing! Thanks for giving us a sneak peek into the incredible progress happening in the world of tech, creativity, and communication. This has the potential to be at the heart of everything we do.

21: @JakeHaugen 2023/12/07 1:17

Absolutely next level stuff. The temporal inference was amazing. I was most impressed by it's ability to remember where the ball was and follow it. Seems well versed. What a time to be alive!!!

22: @JohnKooz 2023/12/07 12:18

I was genuinely increasingly astounded each minute of the Gemini demonstration! With its image recognition, translation capabilities, nutritional advice, geographic knowledge, intuitive features, and even humor, I think Gemini might make a good "friend"! haha! 😀

23: @MrARRMP 2023/12/07 8:11

As an Ai admirer, this blew my mind. I’ve watched it at least 3 times and I still can’t grasp how big your datasets must have been. Amazing impressive work!

24: @Abnetfikre 2023/12/07 11:50

Wow! This is incredible! I'm so excited to see Google pushing the boundaries of AI with Bard. As someone from Ethiopia, Africa, I'm especially thrilled to see this technology accessible to a global audience. The potential for Bard to bridge the information gap and empower people like myself is truly inspiring.

Great job, Google! This is just the beginning! 🤩👏🏾

25: @caelen_c 2023/12/07 0:03

I always love AI videos from Google

26: @atishpatel1908 2023/12/07 2:20

Really really impressive. If they bring Google glasses back with this AI in it, I'd buy it. 🕶️

27: @cbot9302 2023/12/07 7:49

The three most impressive parts for me were it tracking where the ball was, understanding the dot connection was a crab (I didn't even see that!) and, funnily enough, it getting things wrong! I think this last one because it is also stuff that would fool us humans (like expecting the coin to be where you saw it put, or expecting a cat to make an 'easy' jump). Super fascinating stuff.

28: @lukerimmington1049 2023/12/07 13:39

This is fascinating and awe-inspiring that a multimodal model can do this! Well done to the Google team who probably had barely any sleep when this dropped.

29: @socraplatotleus 2023/12/07 4:49

I like how we all get to benefit from the competition between OpenAI and Google.

30: @SoloPirate2003 2023/12/07 5:03

Tasteful touch at the end with the constellation drawing. So far Gemini is living up to the hype. Looking forward to using it come 2024.

31: @TicTockBrandShop 2023/12/07 3:44

I really cannot quite believe what my eyes have just shown me
For me, this is the most incredible piece of A.I advancement the world has seen.Period. Mind blown, when I try to just imagine what the A.I world will could become in just a few years from now. Amazing and every other superlative I could throw at you.

32: @journeysend1754 2023/12/07 5:12

This is going to be a huge game changer, Imagine all the applications this could have. I wonder if Gemini Nano could be baked into an AR set to play AR games or better help with tourism. Ultra I could see being really bug for industrial/commercial use.

I could seriously see this being the turning point in the AI race, like imagine shopping and Gemini can let you know (if it has the capabilities) if a vegetable is going bad or if you can purchase the same thing at a store close to you for a little less.

2024 will be an interesting year, I can't wait to see how Gemini can be implemented

33: @TacoGuy 2023/12/07 7:52

I wonder if it's going to come to non-pixel devices & PC in standalone package. This looks amazing and mind-blowing. Hope you guys get better with your other projects too, because this one sounds very promising.

34: @prem9501 2023/12/07 13:24

Happy to be alive to witness this ❤. Let's hope that all the hardwork goes into building these AI model will be fruitful and this Gemini will make the world a better place

35: @theNobs1 2023/12/07 2:04

The first interaction is definitely a nod to the movie Billy Madison. Proving the AI can draw a blue duck is the only way to pass the 1st grade. Thats quacktastic indeed!

36: @jessenaylor 2023/12/07 7:35

Very impressive, although it's a pity that this Gemini Ultra won't be available until some time early 2024, when OpenAI probably will have released GPT-5 or Q* or whatever it will be called. It makes me feel Google has had to hurry this to impress everyone despite not releasing these models yet. Maybe GPT-4 will be the best system available to the general public until GPT-5, unless Google really manages to hurry and get their stuff sorted already!

37: @user-bz9nh1fb5k 2023/12/07 2:52

That's truly mind-blowing!! looking forward to more amazing things we can do using Gemini!

38: @YTV-Hoddeok 2023/12/07 13:18

Such an interesting work!! Hope to see more incredible things in the near future

39: @rappsongs 2023/12/07 2:48

I wonder if it will outperform OpenAI’s range of models, and their APIs?
I’m curious to see if Gemini’s real-world effectiveness matches the hype Google’s giving it.

40: @danielelkadi3499 2023/12/07 3:22

That was insane. Engineering is indeed the closest thing to magic.

41: @pratikpandey6680 2023/12/07 0:44

I love how it can come up with ideas
Like the Guess the country game and one with yarn 🤩
Amazing!!!!❤

42: @devinoxman 2023/12/07 7:29

The accessibility implications of Geminis ability to perform real time image Analysis are mind blowing, as somebody who can’t see, I can’t wait to try this. This paired with a smart phone, camera or headset with stereoscopic image capture could be a total game changer.

43: @dbyoon717 2023/12/07 0:39

the most astounding features of AI models I've seen..

44: @klx6265 2023/12/07 8:00

Absolutely mind blown by the scale of context awareness here. G for Gemini.

45: @familieweber5556 2023/12/07 18:38

When this is really working as being shown it is indeed mindblowing. Great job!

46: @Viperzka 2023/12/07 17:50

That is incredibly impressive. There were clearly some hidden prompts as it kept understanding switching contexts. But still it was highly impressive.

47: @curiousmonica 2023/12/07 1:08

Incredible! Can't wait to try using them. So exciting!

48: @SiemdeNijs 2023/12/07 11:21

This is the turning point. We are about to experience the biggest leaps forward in STEM and other fields, leaps that sounded like sciencefiction or even were unimaginable. This is absolutely mind blowing, wow.

49: @vectoralphaAI 2023/12/07 3:24

That is incredibly impressive and mind blowing. To think that AI has become this capable nowadays. Now the competition is on for Microsoft/ OpenAI to see what they do because Gemini is incredible. Just making the timeline towards true AGI in 2 years(2025) even more credible and achievable.

50: @abcyz 2023/12/07 9:18

2:36 very impressive, it seems like real-time interaction