Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

"I don't think these models really have taste." Google DeepMind’s Oliver Wang and Nicole Brichtova say real art still comes from human control, iteration, and intent. When artists shape the model, Nano Banana becomes a new kind of creative partner. Oliver Wang Nicole Brichtova Guido Appenzeller

a16z

907,163 subscribers

27,144 views • 10 months ago •via X (Twitter)

Arts Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Google DeepMind Developers: How Nano Banana Was Made In this episode, we sat down with Google DeepMind’s Oliver Wang and Nicole Brichtova to discuss how Nano Banana was created, why it became so viral, and what’s in store for the future of image and video editing. 00:00 Intro 02:00 The origin of Nano Banana 06:20 Seeing yourself in AI 11:00 Control & character consistency 17:10 AI in education and visual learning 24:10 2D vs 3D: Debate over world models 31:10 The Japan phenomenon 35:00 From images to video 41:00 Working with artists 47:30 The next era of image models 53:50 Closing thoughts Oliver Wang Nicole Brichtova Guido Appenzeller Yoko

Google DeepMind Developers: How Nano Banana Was Made In this episode, we sat down with Google DeepMind’s Oliver Wang and Nicole Brichtova to discuss how Nano Banana was created, why it became so viral, and what’s in store for the future of image and video editing. 00:00 Intro 02:00 The origin of Nano Banana 06:20 Seeing yourself in AI 11:00 Control & character consistency 17:10 AI in education and visual learning 24:10 2D vs 3D: Debate over world models 31:10 The Japan phenomenon 35:00 From images to video 41:00 Working with artists 47:30 The next era of image models 53:50 Closing thoughts Oliver Wang Nicole Brichtova Guido Appenzeller Yoko

a16z

97,860 views • 10 months ago

A father's chemistry lectures. A son trying to understand his work. Decades of technical distance. Then someone used Google's Nano Banana to create sketch notes that finally bridged the gap. Nicole Brichtova and Hansa Srinivasan from Google DeepMind share why personalized learning might be an important application of visual AI.

A father's chemistry lectures. A son trying to understand his work. Decades of technical distance. Then someone used Google's Nano Banana to create sketch notes that finally bridged the gap. Nicole Brichtova and Hansa Srinivasan from Google DeepMind share why personalized learning might be an important application of visual AI.

Pat Grady

13,485 views • 9 months ago

Counting down the days till the rumored Nano Banana 2 launch?🍌 Pat Grady and I dive in with the creators Nicole Brichtova and Hansa Srinivasan from Google DeepMind, on our latest episode of Sequoia Capital's Training Data ✨ The biggest unlock? Preserving identity - giving people a way to express and enhance who they are, from red carpets to toy boxes

Counting down the days till the rumored Nano Banana 2 launch?🍌 Pat Grady and I dive in with the creators Nicole Brichtova and Hansa Srinivasan from Google DeepMind, on our latest episode of Sequoia Capital's Training Data ✨ The biggest unlock? Preserving identity - giving people a way to express and enhance who they are, from red carpets to toy boxes

Stephanie Zhan

31,112 views • 9 months ago

.Anish Acharya says the future of AI isn’t one model to rule them all—and explains why platforms that integrate multiple models will benefit the most: "I think we're going to need and rely on all of the models." "It's sort of like if you have a team of people... if you have five people, they could all do a basic set of things pretty capably." "But then they all have their specializations. Maybe one of them is really good at closing a customer who doesn't want to sign the deal, and one of them is really good at culture and getting the best out of the team." "There are some areas in which they are going to build apps, and that will be a threat to app companies. But there are many areas in which app companies are advantaged. Cursor and Krea are great examples of this—products where you benefit from being multi-model." "When you actually use a creative tool, you don't want to just use Nano Banana, you want to have access to OpenAI, Nano Banana, Kling—all of them—Qwen, you name it. So using a single interface to access all the models is powerful." Anish Acharya on BILLIONS with Guillaume Moubeche

.Anish Acharya says the future of AI isn’t one model to rule them all—and explains why platforms that integrate multiple models will benefit the most: "I think we're going to need and rely on all of the models." "It's sort of like if you have a team of people... if you have five people, they could all do a basic set of things pretty capably." "But then they all have their specializations. Maybe one of them is really good at closing a customer who doesn't want to sign the deal, and one of them is really good at culture and getting the best out of the team." "There are some areas in which they are going to build apps, and that will be a threat to app companies. But there are many areas in which app companies are advantaged. Cursor and Krea are great examples of this—products where you benefit from being multi-model." "When you actually use a creative tool, you don't want to just use Nano Banana, you want to have access to OpenAI, Nano Banana, Kling—all of them—Qwen, you name it. So using a single interface to access all the models is powerful." Anish Acharya on BILLIONS with Guillaume Moubeche

a16z

33,251 views • 5 months ago

Demis Hassabis: AGI will be an intertwined model of Gemini, Genie and something like Nano Banana. Nano Banana shows first climps of AGI "It also has Gemini under the hood, it sort of understands what's going on semantically in those images, so I think that's sort of, it's getting towards a kind of AGIfor imaging" AGI will be the unification of the Genie 3, Nano Banana and Gemini models "And then eventually, we got to kind of converge all of those different projects. And they're intertwined. But we need to, you know, converge them all into one" Google seems to be doing everything right at the moment. With Genie 3, Gemini 3, and Nano Banana, they have all the prerequisites to create a general model that develops a true understanding of the real world.

Demis Hassabis: AGI will be an intertwined model of Gemini, Genie and something like Nano Banana. Nano Banana shows first climps of AGI "It also has Gemini under the hood, it sort of understands what's going on semantically in those images, so I think that's sort of, it's getting towards a kind of AGIfor imaging" AGI will be the unification of the Genie 3, Nano Banana and Gemini models "And then eventually, we got to kind of converge all of those different projects. And they're intertwined. But we need to, you know, converge them all into one" Google seems to be doing everything right at the moment. With Genie 3, Gemini 3, and Nano Banana, they have all the prerequisites to create a general model that develops a true understanding of the real world.

Chubby♨️

66,335 views • 8 months ago

There's not a day that goes by that I don't think of Wang Wang since I heard her story; my heart broke thinking about how much suffering Wang Wang and her babies have endured. Now the whole world will stand by you; anyone with a heart and compassion will seek justice for you. My heart aches when I think of the hard life you had; you are still a one-year-old puppy who just wants to live, love and care for your babies. Let’s keep sharing Wang Wang’s story till justice is served to her & her babies Aug.28 is world protest for wang wang, I’m thinking to host a livestream, pls join the live, the more people we unite together to speak up for wang wang, the more pressure we can put on them to get this justice for wang wang & make them pass the law to prevent animal cruelty #justiceforwangwang

There's not a day that goes by that I don't think of Wang Wang since I heard her story; my heart broke thinking about how much suffering Wang Wang and her babies have endured. Now the whole world will stand by you; anyone with a heart and compassion will seek justice for you. My heart aches when I think of the hard life you had; you are still a one-year-old puppy who just wants to live, love and care for your babies. Let’s keep sharing Wang Wang’s story till justice is served to her & her babies Aug.28 is world protest for wang wang, I’m thinking to host a livestream, pls join the live, the more people we unite together to speak up for wang wang, the more pressure we can put on them to get this justice for wang wang & make them pass the law to prevent animal cruelty #justiceforwangwang

Cat Ce

21,655 views • 7 days ago

[INFO] 240704 This music and light art installation "I'm Good" at the Cartier Trinity 100 pop-up in Shanghai is created by Jackson Wang and features original music "GoooD". It is part of the new Cartier art project titled "Imagine Infinite Circles." “this is a collaborative initiative that brings together more than 100 original works by creative figures from all over the world… Each of these artists and creators has been invited… to pay tribute to the Trinity with an original work.” 👏 #JacksonWang #王嘉尔 #잭슨 #TEAMWANG Jackson Wang

[INFO] 240704 This music and light art installation "I'm Good" at the Cartier Trinity 100 pop-up in Shanghai is created by Jackson Wang and features original music "GoooD". It is part of the new Cartier art project titled "Imagine Infinite Circles." “this is a collaborative initiative that brings together more than 100 original works by creative figures from all over the world… Each of these artists and creators has been invited… to pay tribute to the Trinity with an original work.” 👏 #JacksonWang #王嘉尔 #잭슨 #TEAMWANG Jackson Wang

Jackson Wang Global

10,712 views • 2 years ago

Ideogram CEO Mohammad Norouzi says image models need taste: "We think taste is extremely important and we really want our models to have taste, and it's very hard to explain it." "One element of taste is going outside of the normal a little bit and not conforming to the average opinion, which is a little against being on top of the leaderboard." "Ultimately, we work with all the arenas... but we care about our own internal evaluation." "AI is not very good at doing the actual taste evaluation yet, so we work with designers... to really push on the taste." Mohammad Norouzi with Yoko and Justine Moore

Ideogram CEO Mohammad Norouzi says image models need taste: "We think taste is extremely important and we really want our models to have taste, and it's very hard to explain it." "One element of taste is going outside of the normal a little bit and not conforming to the average opinion, which is a little against being on top of the leaderboard." "Ultimately, we work with all the arenas... but we care about our own internal evaluation." "AI is not very good at doing the actual taste evaluation yet, so we work with designers... to really push on the taste." Mohammad Norouzi with Yoko and Justine Moore

a16z

19,520 views • 2 months ago

Patrick Collison on what changes when biology becomes programmable: "We, humanity, have never cured a complex disease." "Most cardiovascular disease, most cancers, most autoimmune disease, most neurodegenerative disease... For none of them can we really say that we've cured it, that we understand the causal pathways in meaningful detail." "Then over the last 10 ish years... we’ve gotten three new classes of technology in biology." "If you put those together, you now have the ability… to read, think, and to write. And this starts to really feel like a new kind of Turing loop." Patrick Collison with Michael Truell

Patrick Collison on what changes when biology becomes programmable: "We, humanity, have never cured a complex disease." "Most cardiovascular disease, most cancers, most autoimmune disease, most neurodegenerative disease... For none of them can we really say that we've cured it, that we understand the causal pathways in meaningful detail." "Then over the last 10 ish years... we’ve gotten three new classes of technology in biology." "If you put those together, you now have the ability… to read, think, and to write. And this starts to really feel like a new kind of Turing loop." Patrick Collison with Michael Truell

a16z

120,120 views • 6 months ago

NEW EPISODE: “When I'm writing something, it surprises me. I don't think of it and say it. It comes from the person inside you, and you have no part in the inspiration that proceeds from inside you.” -Woody Allen

NEW EPISODE: “When I'm writing something, it surprises me. I don't think of it and say it. It comes from the person inside you, and you have no part in the inspiration that proceeds from inside you.” -Woody Allen

Tetragrammaton

41,870 views • 10 months ago

I just listened to a breakdown of Gemini jump from 2.0 to 2.5, and here's the gist. The team did not rely on lab tests alone. They scraped real user feedback from X, turned those "this broke" moments into living evals, and keep appending new edge cases with every release. It's a community driven QA loop: our failures become their benchmarks, which become our better results. If you're a creator or PM, this is a template: public feedback → evals → release → repeat. Great work Logan Kilpatrick Nicole Brichtova and whole team.

I just listened to a breakdown of Gemini jump from 2.0 to 2.5, and here's the gist. The team did not rely on lab tests alone. They scraped real user feedback from X, turned those "this broke" moments into living evals, and keep appending new edge cases with every release. It's a community driven QA loop: our failures become their benchmarks, which become our better results. If you're a creator or PM, this is a template: public feedback → evals → release → repeat. Great work Logan Kilpatrick Nicole Brichtova and whole team.

Matija Grcic

62,163 views • 1 year ago

Impeccable creator Paul Bakaus says AI should be cognitive delegation, not cognitive surrender: "Cognitive delegation is, I'm using Google Maps, and Google Maps tells me where I can go as quickly as possible." "But what if I let Google Maps decide where I want to go to? Now I kind of cognitive surrender to the application, and I think that's very true for LLMs if you're not careful." "You prompt something, and then it creates a beautiful plan, and then it's eight pages long. You're not going to read through that plan. You're going to scroll through that plan and skim it, and it's like, 'I guess the model knows what it's doing.'" "I think delegating to the model is great, but preserving that point of view, making sure that you're still the one driving is also really important." Paul Bakaus

Impeccable creator Paul Bakaus says AI should be cognitive delegation, not cognitive surrender: "Cognitive delegation is, I'm using Google Maps, and Google Maps tells me where I can go as quickly as possible." "But what if I let Google Maps decide where I want to go to? Now I kind of cognitive surrender to the application, and I think that's very true for LLMs if you're not careful." "You prompt something, and then it creates a beautiful plan, and then it's eight pages long. You're not going to read through that plan. You're going to scroll through that plan and skim it, and it's like, 'I guess the model knows what it's doing.'" "I think delegating to the model is great, but preserving that point of view, making sure that you're still the one driving is also really important." Paul Bakaus

a16z

79,882 views • 2 months ago

World Labs CEO Dr. Fei-Fei Li explains says "world model" has become an overloaded term & explains what each kind of world model does: "Right now there are three ways of calling world models when it comes to spatial intelligence." "One is what I call a renderer, when the model puts beautiful pixels on the screen." "Another kind of world model is what we call a planner. That is more for machines, more for robots." "The third kind, which I think is the linchpin of the three, is a simulator." "A simulator could become a renderer. The simulator could become a planner. But this layer is a huge critical path to unlock spatial intelligence. And that's what World Labs is working on." Fei-Fei Li at Bloomberg Tech live with Emily Chang

World Labs CEO Dr. Fei-Fei Li explains says "world model" has become an overloaded term & explains what each kind of world model does: "Right now there are three ways of calling world models when it comes to spatial intelligence." "One is what I call a renderer, when the model puts beautiful pixels on the screen." "Another kind of world model is what we call a planner. That is more for machines, more for robots." "The third kind, which I think is the linchpin of the three, is a simulator." "A simulator could become a renderer. The simulator could become a planner. But this layer is a huge critical path to unlock spatial intelligence. And that's what World Labs is working on." Fei-Fei Li at Bloomberg Tech live with Emily Chang

a16z

112,162 views • 2 months ago

“Reasoning has fundamentally changed the economics of these frontier models.” Gavin Baker says reasoning lets scaled user bases unlock a new flywheel. Users improve the model, and the model improves the product. Gavin Baker

“Reasoning has fundamentally changed the economics of these frontier models.” Gavin Baker says reasoning lets scaled user bases unlock a new flywheel. Users improve the model, and the model improves the product. Gavin Baker

a16z

23,671 views • 10 months ago

Adobe just dropped a wild update at MAX... For the next 30 days, Creative Cloud + Firefly users get unlimited generations across Firefly and partner models like Gemini’s Nano Banana, Flux, Runway, and ChatGPT + Relaxed video generation I took the chance to test Firefly 5, their new model, with different types of photography, and the results literally blew my mind. Check out these Prompts and the link to the board to see for yourself. Don't forget to bookmark this This post is sponsored by Adobe as an Adobe Firefly Ambassador. #AdobeFireflyAmbassadors #Ad #FireflyPromo

Adobe just dropped a wild update at MAX... For the next 30 days, Creative Cloud + Firefly users get unlimited generations across Firefly and partner models like Gemini’s Nano Banana, Flux, Runway, and ChatGPT + Relaxed video generation I took the chance to test Firefly 5, their new model, with different types of photography, and the results literally blew my mind. Check out these Prompts and the link to the board to see for yourself. Don't forget to bookmark this This post is sponsored by Adobe as an Adobe Firefly Ambassador. #AdobeFireflyAmbassadors #Ad #FireflyPromo

Amira Zairi

44,767 views • 9 months ago

Inferact Co-founder Simon Mo on the trajectory of open and closed models: "What really differentiates open-weight models from closed-weight models, right? In the end, there's not much differentiation. It's more about the distribution strategy and go-to-market strategy... Capability-wise, I don't really see a big gap, not even today." "It's not about just source data. It's not about where to get the data from. Rather, it's who can build the best environment and who can make the most optimization and algorithmic choices to leverage all this learning from this environment." "So the next year is all gonna be about that. It's about how open-weight model labs are differentiating and really getting the model to meet the real world." "Project out in a year, there's not gonna be any difference." Simon Mo

Inferact Co-founder Simon Mo on the trajectory of open and closed models: "What really differentiates open-weight models from closed-weight models, right? In the end, there's not much differentiation. It's more about the distribution strategy and go-to-market strategy... Capability-wise, I don't really see a big gap, not even today." "It's not about just source data. It's not about where to get the data from. Rather, it's who can build the best environment and who can make the most optimization and algorithmic choices to leverage all this learning from this environment." "So the next year is all gonna be about that. It's about how open-weight model labs are differentiating and really getting the model to meet the real world." "Project out in a year, there's not gonna be any difference." Simon Mo

a16z

33,782 views • 23 days ago

Michael Truell says we're still early in automating software: "It's really easy at an executive level to underestimate just how far away we are from the limit of automating software." "I think that there's a really, really long way to go. There's a really long, messy middle." "We are in a market that's had an iPod moment, and it's going to have an iPhone moment and another iPhone moment. And I think that there have been a couple of those so far. I think that there are definitely more in the future." Michael Truell with martin_casado

Michael Truell says we're still early in automating software: "It's really easy at an executive level to underestimate just how far away we are from the limit of automating software." "I think that there's a really, really long way to go. There's a really long, messy middle." "We are in a market that's had an iPod moment, and it's going to have an iPhone moment and another iPhone moment. And I think that there have been a couple of those so far. I think that there are definitely more in the future." Michael Truell with martin_casado

a16z

56,052 views • 2 months ago

Exa CEO Will Bryk explains why retrieval can help solve the tokenpocalypse: "We should not be using gigantic models for every task." "You should use a family of models of different sizes. The big model decides what to do, and it dishes out commands to the small models, and those small models can be way more accurate and reliable if they're using retrieval." "Retrieval helps small models act like big models... We do save our customers a huge amount of tokens because they can use smaller models and use retrieval." "We could save 20x on cost for customers compared to other providers by being very efficient in what information from the web the agent actually sees." Will Bryk with Sarah Wang

Exa CEO Will Bryk explains why retrieval can help solve the tokenpocalypse: "We should not be using gigantic models for every task." "You should use a family of models of different sizes. The big model decides what to do, and it dishes out commands to the small models, and those small models can be way more accurate and reliable if they're using retrieval." "Retrieval helps small models act like big models... We do save our customers a huge amount of tokens because they can use smaller models and use retrieval." "We could save 20x on cost for customers compared to other providers by being very efficient in what information from the web the agent actually sees." Will Bryk with Sarah Wang

a16z

25,144 views • 2 months ago