In short
Google I/O predictions (VO4/Nano Banana Pro 2; possible 4K 10-bit HDR upgrade), DeepMind Fabula story-assist research preview, and AI-driven creative pipelines. Also covers “Image Blaster” (single-image to 3D world) plus Netflix’s new in-house AI animation studio “Netflix INK,” and several AI-in-entertainment/consumer controversies (Monet-style spoof study, Sony Xperia AI camera backlash, Disney World Muppets animatronic scooter mocap).
Guests
Addy and Joey (co-hosts of Denoised). No other guests named.
Key claims
Better AI control needs interactive visual feedback (mouse/voice + computer context). Fabula scaffolds story structure rather than generating ideas. Image Blaster uses Claude Skills + World Labs + Fall to create 3D environments (meshes, textures, physics, audio) from one image. Netflix INK focuses on GenAI-enabled workflows and scalable multi-show environments; likely starts with shorts/experiments.
Notable examples
Monet “AI inferior” spoof that was actually a real Monet crop; Xperia “before/after” AI camera assistant that was later reframed as pre-shoot creative suggestions; Disney World Muppets rebrand scooter animatronic programmed via mocap of a real scooter puppet.
Written by AI. May contain mistakes. Listen to the episode to check what was said.
Chapters
Tap a time to open that second in VOMo-Capping Innovation
0:00 to 0:15
Learn about the creative use of motion capture in animatronics.
“The animation to program the robot, they actually mo-capped a real scooter puppet that was being puppeteered by a human, mo-capped him, and then put that data onto the animatronic puppet.”
Google I/O Excitement
0:30 to 1:50
Discussion on expectations for the upcoming Google I/O event.
“So at the minimum, I'm expecting VO4 and Nano Banana Pro 2.”
Rumors on Video Updates
1:50 to 2:20
Speculation about potential upgrades to Google's video model.
“We are reimagining a 50-year-old interface, the mouse pointer with AI.”
AI and Interface Innovations
2:20 to 3:46
Exploration of AI's role in rethinking user interfaces.
“And basically Gemini sort of understanding the entire context of what's happening on your computer and then taking action.”
Gemini's Contextual Understanding
3:46 to 4:49
Understanding how AI can interpret context and take actions.
“important to have a two-way communication between the AI system and the computer itself.”
Story Writing AI: Fabula
4:49 to 5:54
Introduction to a new AI tool designed to assist in story writing.
The Challenge of Originality in Storytelling
5:54 to 7:49
Discussing the limitations of AI in creating original stories.
“I think he was on the Joe Rogan show or something where he was like, look, all these agentic story building things are just going to deduce down to the most average and the most overused story format.”
Introduction to Image Blaster
7:49 to 10:10
Overview of a new tool that creates 3D environments from images.
“Okay, this one I've been texting out to people, and everyone's going crazy over it.”
Potential of AI in Game Development
10:10 to 12:22
Exploring how new AI tools can influence game development.
“And finally, there is a companion app to view and pose all the objects that were created.”
AI and Artistic Perception
12:22 to 14:00
Examining how AI influences perceptions of art and creativity.
“I will put the link in the description, but it's called Image Blaster.”
Show all 17 chapters
AI Art Controversy and Public Reaction
14:00 to 15:00
Discussing the backlash against AI-generated art and its implications.
“Maybe that affects the sense of the depth.”
The Impact of AI on Creative Careers
15:00 to 18:12
Exploring the fears and adaptations of artists in the wake of AI tools.
“I'm sure that's going to happen sooner or later.”
The Evolution of Animation with Technology
18:12 to 21:48
Reflecting on past shifts in animation technology and their effects on artists.
“But this churn that this time around I think is the most amplified and the most impactful.”
AI and Content Authenticity in Filmmaking
21:48 to 24:41
Examining the role of AI in ensuring authenticity in video content.
“I think what you're talking about is not just an auto thing on the red, but a unified system.”
Netflix's AI Animation Studio Launch
24:41 to 28:00
Analyzing Netflix's strategy with its new AI animation studio and its implications.
“Our job is to make stuff up versus broadcast is to capture the truth.”
The Art of Animation and Control
28:00 to 28:38
Explore the complexities of animating characters and the control required for storytelling.
“Like, you know, it's not enough to like drive a character with like a video of yourself driving the character.”
Disney's Muppets Coaster Transition
28:38 to 30:36
Learn about the transformation of a classic ride into a Muppets-themed experience utilizing motion capture.
“They're rebranding it to a Muppets theme, and they're redoing the show opener stuff, and so there is an animatronic scooter that is part of the pre-show, and so it'll be a permanent robot.”
Transcript
Automatic transcript. May contain errors.0:00Addy Osmani:The animation to program the robot, they actually mo-capped a real scooter puppet that was being puppeteered by a human, mo-capped him, and then put that data onto the animatronic puppet.
0:14Joey Hurst:That's amazing!
0:20Addy Osmani:All right, welcome back to Denoised. Addy, good to see you. Hey, Joey, what's up, man? How's it going? It's been busy, I think, for both of us.
0:29Joey Hurst:it's been a couple weeks yeah we've been busy it's been a busy yeah luckily and also everyone
0:33Addy Osmani:the one i keep talking to has been pretty busy so i'm glad i am glad to hear that all right let's see let's talk about google i'll be at google io for the first time next week uh so i'm gonna check that out i'm excited to check that out and if anyone's gonna be there let me know hit me up uh we can meet up but um yeah this is sort of their developer conference where they announce a lot of stuff. So at the minimum, I'm expecting VO4 and Nano Banana Pro 2. That feels like baseline.
0:59Joey Hurst:That's the minimum expectation?
1:01Addy Osmani:That feels like, I mean, there hasn't been a big VO update in a while. We've got Sea Dance 2, we've got Kling 3. Obviously, they've been working on something. I saw some teases online of potential stuff. I didn't share it because I saw one clip and I don't really know the validity of it and I haven't seen anything else.
1:16Joey Hurst:Can I share some rumors?
1:17Addy Osmani:Sure, go for it.
1:18Joey Hurst:Google rumors. So I heard that it is very close to, Vio is very close to having a high dynamic range or some crazy resolution upgrade to the video model.
1:29Addy Osmani:Okay, that is welcome. So what's some potential 4K 16, maybe not 16 bits.
1:35Joey Hurst:Maybe not, I would say maybe 10 bit 4K is closer territory.
1:39Addy Osmani:Yeah, so hopefully you get to see that live. Hopefully, yeah. Looking forward to whatever new stuff in the creative pipeline, but then also whatever else they got cooking up. Like this video just went around from Google DeepMind. We are reimagining a 50-year-old interface, the mouse pointer with AI. So this demo is...
1:58Joey Hurst:Mouse pointer's fine.
2:00Addy Osmani:This still makes me think of just the rethinking all of our interfaces and websites and all that stuff for whatever this agentic future is. This was not fully like an agentic thing. This was more like using your mouse pointer and voice as a two pair combo to be like pointing at something and then being like, hey, do this thing. And basically Gemini sort of understanding the entire context of what's happening on your computer and then taking action.
2:26Joey Hurst:Wow, that's cool. So it's like just kind of pointed in the general direction and then Gemini has enough context to do the action for you.
2:33Addy Osmani:One of the demos was pointing at a to do list and then saying like add emojis to that. That's not the most useful example. But the other one was like pointing at an address and then being like, hey, show me the direction. So like how I would get here. And then it like loads up maps and your location and then direction to there. These are very simple things. But the idea is like it is understanding what's happening on the computer and taking action. My mind is going to things that I've hit roadblocks with trying to do with Cloud Code, like build out a fusion node in DaVinci Resolve. the cloud can kind of kind of control davinci resolve but it can't build out like complicated nodes and stuff like that uh right it also just doesn't know what it's doing it'll like control apps it's flying blind yeah it'll be like i think i did it but like i can't verify i can't see i don't know so you have to check so this is a step towards that direction too where you can kind of have better visual understanding of what's or the ai can have better understanding of what's happening on the computer to help you do things.
3:35Joey Hurst:Yeah, I think the important here is the interactive feedback type. So the AI system can see and kind of understand and read what you're trying to do, which is important to have a two-way communication between the AI system and the computer itself.
3:51Addy Osmani:Yeah. And interesting that it's because, you know, we've heard a lot about just text control and speech to text or just voice control. And this is not totally throwing out the mouse pointer. It's just like, what if you use pointing and voice in conjunction?
4:05Joey Hurst:Yeah, I would love for this to be in Blender or some crazy software where, you know, you don't have to really know it. You kind of just point the mouse. Yeah. And just kind of say.
4:14Addy Osmani:Yes. And we've seen, like in our last episode, we talked about Claude just taking over everything and integrating with everything. But yeah, there is a limit to how far you can get just through text prompting Claude and telling it what you want. you need that back and forth dynamic and this feels like it gets a little bit closer to that
4:33Joey Hurst:back and forth dynamic totally okay all right i i take it back i was i was like hey why mess with
4:38Addy Osmani:the mouse okay i guess other thing from deep mind it's still in a research preview it is called fabula and it is a story writing ai assistant that they worked with in development with a bunch of playwrights and screenwriters and based it off of story structure books and um the idea is for it to be a sidekick as you write build out your scaffolding for your story structure and sort of this again not the ai doing this stuff for you but the ai assisting you yeah it's like a assistive
5:15Joey Hurst:agentic story writer that helps you yeah build build a hierarchy of the story but not necessarily
5:22Addy Osmani:to come up with ideas and things like that yeah or helping you refine beats or story beats or building out character structure and then that that that scaffolding so as you do flesh out the story you have this baseline that you're working with okay two things i i love this i love that
5:39Joey Hurst:they're thinking about this of course this is a precursor to let's say a video model right like this could potentially be an end-to-end pipeline that's fully assisted um story agent tech story
5:50Addy Osmani:Storyboard, shots, cutting, VFX, blah, blah, blah, blah.
5:55Joey Hurst:Now, two things. One, I'm going to cite Ben Affleck. He was right about this. I think he was on the Joe Rogan show or something where he was like, look, all these agentic story building things are just going to deduce down to the most average and the most overused story format. So how do you create a story that is asymmetrical, that is completely unconventional? like how you create memento that's backwards yeah right so like that's where the art lies is the outlier stuff and so yeah i think this stuff is probably not going to be very useful for somebody who's trying to really break the mold but if you're generating a hundred videos a week you're
6:35Addy Osmani:youtube content creator you're doing verticals yeah verticals are not kill you let's go let's go Give me the Slava Sheet. Christmas in random town. Not even a Slava Sheet.
6:48Joey Hurst:Just generate all hundred of them. I don't care.
6:51Addy Osmani:Just put it out there. Yeah, you know, it just reminded me of something before the AI days and all this stuff. You know, there have been tons of screen... I can't even remember those days. From a time long ago. There were tons of, you know, screenwriting books and, like, this is how you write your screenplay. And, like, this is what you have to hit in the first... This is what you have to have on page one. This is what you have to have on, like, first act. And this is what you have to have, like, second act. Then there was always a course of screenwriters of just like, yeah, if you want to write something formulaic, then yeah, follow those screenwriting books.
7:17Addy Osmani:But if you want to be original, then throw those books out and write something completely different. And this is just the AI version of the screenwriting book. So it's like, cool, it helps you if you want the help. And if you don't want it, and yeah, sure, it will give you something that follows a formula pattern. you could argue like um you know i mean that was here with a thousand faces where like as humans we have the same story uh archetypes that we've been doing for thousands of years regardless if you want to do something completely different and throw it out the window like a pulp fiction or memento um exactly you know that's where humans that's where yeah okay i i have an idea on how
7:55Joey Hurst:to be super creative for really really cheap and very easily okay i call it the jim kramer fabula do you get it so you have fabula make the story and just reverse everything
8:11Addy Osmani:i think you could do that today too if you just go to chat gbt and you're like give me 10 ideas and it gives it to you like thank you garbage garbage yeah that's the opposite of that's the do not write list that's it that's that's how you become famous all right
8:25Joey Hurst:Jim Cramer. Jim Cramer, school of screenwriting.
8:31Addy Osmani:Okay, good. I like that. Okay, this one I've been texting out to people, and everyone's going crazy over it.
8:38Joey Hurst:Yeah, it did. I nearly blew my mind over there.
8:41Addy Osmani:So we have talked about World Labs. We've talked about generative text to 3D. Nielsen, who I believe works at World Labs, yes, built an open source tool that is basically open sourcing a 3D gen toolkit for Cloud Code. You give it an input image, and then it is basically pulling World Labs, text-to-3D models, which we'll get into in a second, and using Cloud Code to build out the full 3D space, but with your 3D models, with the world, with lighting, physics, audio. So crazy. So this is like World Labs on steroids.
9:25Joey Hurst:Yeah, this is somebody at World Labs who used Cloud Code to its full potential.
9:30Addy Osmani:And it opensourced it. Thank you. You can download the get. I have not messed with this yet, but this is high on my list because this could potentially solve a lot of things I wanted to try to do. This is exactly where AI should be heading. The skills harness against an input image and generate meshes with a combination of image generation and 3D generation. Sure. I'm assuming you could also, I think it's calling up different file APIs. So I'm assuming you could also plug and play your favorite text to 3D mesh model of choice. They might not be locked in anything. World apps is kind of the only thing that will do like a full 360 environment built.
Read the full transcript
10:06Joey Hurst:Yeah, but for them to decompose a world into individual 3D models, that's pretty freaking hard.
10:12Addy Osmani:And finally, there is a companion app to view and pose all the objects that were created. Oh, wait, there's like an actual app that you can do this into?
10:17Joey Hurst:What? Yeah, and it has physics. Like, do you see that thing get tossed around and bounce off the floor?
10:22Addy Osmani:Yeah, it's thrown around a chair and stuff, like as if it already has all this stuff built in of what it should be doing.
10:26Joey Hurst:And I think also audio, right, if I'm not mistaken.
10:29Addy Osmani:He said audio. I don't know where the audio comes in.
10:32Joey Hurst:Like if the chair hits the floor, there's a sound generated? I guess. I mean, you're getting really close to game engine territory here.
10:40Addy Osmani:So it's called Image Blaster. Creates 3D environments, sound effects, and meshes from a single image using Claude Skills, World Labs, and Fall. Yeah, I mean, this is like basically built this your 3D world, but now it has models, it has texture. So you can move things around, you can edit it, you can modify it, but you're just getting that like crazy fast, good starting point.
11:01Joey Hurst:Yeah, I mean, call me old fashioned, but this feels perfect for previous. Build this world very, very quickly, put the put the world up and then start moving things around. Put the camera where you want it. And then that goes into image model or video model for traditional 2D output.
11:16Addy Osmani:I mean, definitely previs or definitely, you know, I mean, I'm still on this path of like, can we, you know, this is like a next level up a gray boxing. Can we kind of quickly iterate a world and then feed that into some Gen AI pass and have the consistency of the 3D world from different angles? But then we get to final pixel faster.
11:39Joey Hurst:Exactly. And I think in 2026, we're mid-2026, that feels like everybody's on the same page with that is like text to video, text to image is not quite the control that I need. It's not working. I do want the traditional 3D controls, but I don't want to mess with rigging. I don't want to mess with keyframes and animation. So give me something easier there. But then I love the final quality that generative AI gets us. So finish it with that.
12:08Addy Osmani:Yeah, finish it with that. but at least I have my consistent world. So when I give you these inputs, I am getting that consistency, hopefully, in theory. Still got some kinks to work out on that one,
12:18Joey Hurst:but that's the idea, I think, where this is going. Yeah, so WildTool, open source. I will put the link in the description,
12:24Addy Osmani:but it's called Image Blaster. Shout out to Nielsen. All right, now let's talk about some of our favorite things. AI pitchforks. Someone - That's Van Gogh?
12:34Joey Hurst:No, Monet or Manet? Monet, someone, yeah. Okay.
12:36Addy Osmani:So Shlomes posted this image where he said, I just generated an image in the style of a Monet painting using AI. Please describe in as much detail as possible what makes this inferior to a real Monet painting.
12:46Joey Hurst:You're just asking for it.
12:48Addy Osmani:And so then, you know, unsurprisingly, got a bunch of critiques of saying, you know, how it's terrible, how it's wrong, how it's crappy.
12:58Joey Hurst:Yeah, you trained on Monet data. Of course, it's going to be exactly like it.
13:01Addy Osmani:Turns out it actually is a real Monet painting. And he just said it was AI to trigger people.
13:12Joey Hurst:It's just a style transfer.
13:15Addy Osmani:So this tracks his research and people systematically downgrade their aesthetic assessments of art when told it's AI generated. So basically, we have talked about this before. As soon as anyone hears that AI is involved in something, they get upset. regardless. Oh, okay.
13:29Joey Hurst:So that was spoofed in order to get actual, uh, scientific data on how. Yeah.
13:34Addy Osmani:He posted this image and it was an AI generated in the style Monet, but it's real Monet. It was a crop.
13:38Joey Hurst:This is a crop section of an actual Monet painting. This is Monet. That's what I thought.
13:41Addy Osmani:This is not AI generated.
13:42Joey Hurst:Okay.
13:43Addy Osmani:But then all of the comments were saying how there's a certain harshness, no soft blending of colors, no depth, no symbiosis of the elements. It's all borked nonsense with no sense of space, no frame, no sense of the threshold between subject and object, just colors.
13:57Joey Hurst:Okay, no frame because it is cropped. I give them that.
14:00Addy Osmani:Okay, right. It is cropped. Maybe that affects the sense of the depth. Colors are more pleasing to the eye. The brush strokes are more delicate. The water looks more...
14:09Joey Hurst:Oh, okay. Good notes. Alright. You can tell the difference. Extra different flowers.
14:15Addy Osmani:I love it. Yeah, so basically, posted it, said it was
14:20Joey Hurst:AI. People got upset, said it was crap.
14:22Addy Osmani:Turns out, it really is real money. And when people hear things are AI, regardless of the quality of the output, people get pissed about that.
14:29Joey Hurst:Wow, that's such an interesting study, man. I'm really glad you brought this up. I mean, that kind of applies to our industry in a lot of ways. I mean, I know people on both sides of this fence.
14:41Addy Osmani:I mean, you know, this is from when we first kicked off the podcast when the Brutalist crap was happening. Exactly. You know, and it was like for the clean up, a little bit of the dialogue. oh use the eye oh whatever that upset people and then um yeah all the other stuff and i think we talked about too how like netflix has been playing it smart when they're like after the fact mentioned oh by the way if we used ai for the vfx on this months after after it aired so that people
15:11Joey Hurst:weren't like ah like i'm gonna yeah not watch this thing and they're basically preparing and softening their landing right for the time when the eventual announcement comes that this movie is half generated in AI. I'm sure that's going to happen sooner or later.
15:26Addy Osmani:Yeah, well, we also got that story coming up in a second of the animation studio. That's right. But yeah, I mean, I feel, you know, you've probably experienced the same thing. Like this year, 2026, has definitely been a big vibe shift just from everyone in general of more openly talking about AI. And anyone who was skeptical or dubious before has, for the most part, at least been like, tell me about the say i stuff like realizing it's not going away and now they kind of got to get an
15:56Joey Hurst:understanding of it i mean like i'm gonna play the other side of it for one second i i do understand the fear of somebody who spent their entire career just being really good at this one thing right like when i was at dreamworks we had career modelers like they all they literally did was zbrush for like 10-15 years and they they're just so good at modeling 3d assets that they can charge people fifty thousand dollars for an object but it's the best version of that object digitally and overnight their career their craft their expertise is more or less futile so what else are you going to do i mean even if you try to learn the new tools and sort of apply your modeling knowledge to this new world, you're still not going to be as respected, as paid as you once were.
16:50Joey Hurst:So there's certain parts that I do get. Having said that, not all of us are expert modelers and we honed in on this one craft our whole life. Most of us, I think, are generalists and we're pretty well adaptable. And that's you and me for sure. And I think there's a place for us in this new world.
17:10Addy Osmani:Yeah. I mean, the specialists, it's like they still have the eye, you have the taste. It's like, how can you translate that over to, you know, whatever this Jenny I am?
17:18Joey Hurst:Yeah. And somebody was saying something really interesting to me the other day as well. They were like, hey, when we went from 2D animation, like the Lion King to the first 3D, like Toy Story and Shrek one and so on. Like, there's a lot of 2D artists that were basically out of a job because they didn't they didn't pick up computers. They were just. Yeah, they did.
17:39Addy Osmani:You know, same story with I'm blanking on his name. I know he's the super famous stop motion animator with Jurassic Park when he did a stop motion test of a T-Rex run or a Velociraptor run. And then they did a CG test. And then he saw that and he's like, I'm out of a job. He's like, yeah. He's like, I'm extinct now. So, you know, he was a world-renowned stop motion animator, but the world kind of shifted. So it's the same shift every 10, 20 years.
18:08Joey Hurst:Of people that just kind of get left behind and then some people that get elevated at the same time and so on and so forth. But this churn that this time around I think is the most amplified and the most impactful. It's amplified.
18:21Addy Osmani:It's also compounded in an easy punchy bag. We talked about this before of just like other economic issues completely outside of AI. 100%.
18:31Joey Hurst:We're just not in a good place in general for this.
18:34Addy Osmani:Yeah, exactly. If LA production was churning and was what it was early 2000s, maybe this would not be such an issue. Five years ago, LA production was fine. Yeah. Streamers are throwing a bunch of money at everything. Yeah.
18:47Joey Hurst:Okay. Monet. Monet. I'm a fan of the real Monet.
18:52Addy Osmani:We got another good AI punching bag story. Yeah. Okay. So this post came out from Sony Xperia, which honestly - The phone? Oh, is that their phone brand? Yeah. Okay. Okay, the phone brand.
19:03Joey Hurst:Those are some nice cameras on those phones, dude. Have you ever used one? I have not. But... Just kiss on those cameras.
19:10Addy Osmani:I heard this yesterday saying the new AI camera assistant with Xperia intelligence brings stories to life. And they showed this demo of these before and after photos of before. And after with the AI camera assistant. if you're listening the uh ai camera system after photos look way worse completely over
19:36Joey Hurst:processed uh blown over processed overexposed yeah the original retail shadows nuance the the ai one feels like i slop so um you know understandably the uh internet had a fun field day with this the michael jackson one come on dude show the final show
20:07Addy Osmani:they um posted a follow-up post about this today oh okay they apologized following the post about ai camera assistant we'd like to explain the feature in more detail it doesn't edit photos after shooting it suggests four settings in different creative directions based on the scene and subject you can choose any option or use your own settings too late so ruin the brand that was a horrible demo that was an awful demo of what they did before this makes much more sense this is like a this is like an auto exposure with uh you know more scene awareness and it's like trying to do some auto exposure plus whatever settings to guess how you want to take the ai part in these
20:46Joey Hurst:for suggestions. I don't see outpainting. I don't see new objects.
20:50Addy Osmani:No, I think because it's not even, it's literally, it's saying it's before you take the picture. So like, you know, auto exposure would like look at your light meter and then adjust your like shutter and aperture based on your settings. This is taking that to the next level where maybe it's adjusting your color settings. Maybe it's doing something else before you hit take photo.
21:08Joey Hurst:So it's like, yeah,
21:10Addy Osmani:that makes more sense. It was a horrible post. That was a horrible first post. That was a terrible post. This makes more sense. Like, you use it, you don't use it. It's like auto exposure on steroids. I understand that more. Terrible launch. Terrible launch.
21:25Joey Hurst:I would love a feature like this on, like, a professional camera, like a Red or a Sony Venice or something. They're going to take it out back and beat you up with that comment.
21:36Addy Osmani:Unless you're Greg Frazier, you're not exposing the camera, right?
21:38Joey Hurst:And you're not putting the light in the right place, you know? Just get suggestions on some of these things before you hit that record button and record away one terabyte.
21:49Addy Osmani:I think what you're talking about is not just an auto thing on the red, but a unified system. Your aperture lights and your camera and the vision you see is all connected. It's a look choice.
22:08Joey Hurst:So you have four different looks you can pick from. And each look will affect the LUT, you know, the ISO and everything. And you can kind of play around and just experiment more with principal photography.
22:21Addy Osmani:You heard it here first, Addy wants an automatic red camera.
22:24Joey Hurst:Yes.
22:25Addy Osmani:Give me those auto settings.
22:26Joey Hurst:No, I want a Sony Venice 2. Well, I don't know.
22:27Addy Osmani:Maybe you could...
22:29Joey Hurst:If we get a Sony Venice 2, then we'll talk great things about the Xperia on this. I want an RA with autofocus.
22:38Addy Osmani:What's that new camera? What's the Nikon that has the Z sensor? Because that might have a lot of stuff in it. The one that went to space? The one that they just launched, the first new product that came out of the Nikon Red acquisition.
22:49Joey Hurst:The Z9, I think?
22:50Addy Osmani:It was like that, wasn't it like that$2 ,000 camera? Oh, the little guy.
22:54Joey Hurst:Yeah, it's got to be like a Z90 or 900, something like that.
22:58Addy Osmani:Yeah, this one feels like that would be your Red with some type of AI assistance. Smart Red.
23:07Joey Hurst:Does Sony have an AI department? I'm sure they do. Like, for what realm? They have Xen, which we covered at NAB, which is like their spatial capture ecosystem.
23:16Addy Osmani:They have, they did release a broadcast camera. I didn't talk about this, but they released a broadcast ENG style camera that had a content authenticity credential built in. So, like, as you're recording with the camera, it's, I don't know whose system they're using or if it's their own system, but it's like embedding data that, like, says this was, you know, legit.
23:37Joey Hurst:it like this is a real person.
23:40Addy Osmani:This is this is real authentic video. I don't know what other software you need to verify and read that, but it was like the first camera that had that built in. We've talked about this before of like the different content credential systems that would be embedded in cameras to verify that footage was actually shot and not manipulated with.
23:58Joey Hurst:And the same thing goes for generations. If it's an artificial generation, then the The watermark should say that on the CAP, right? It should. I mean, yeah, Adobe has had a lot of stuff.
24:09Addy Osmani:I think the onus is going to be more on verifying authentic material versus tracking generated material because that's way easier to grow. For news and verification and authenticity of like, did someone actually film something happen? Was this an actual thing? I think the verification is going to need to be on the verifying real material rather than verifying AI stuff because you could strip that pretty easily.
24:35Joey Hurst:I can see that. And specifically on broadcast cameras because that's what goes out in the field.
24:39Addy Osmani:That's exactly. That's why I was in an ENG style camera, not like a cinema camera. Yeah. Our job is to make stuff up versus broadcast is to capture the truth.
24:51Joey Hurst:Exactly.
24:52Addy Osmani:All right. What else we got? Okay. So coming back to that Netflix story. So Netflix launched a AI animation studio called Inc.
24:58Joey Hurst:Yeah, I heard about this while we were not shooting episodes, Joey. We could have talked about it earlier. But yeah, this is big news because this is not like a team or a department. This feels like an entirely new studio that they're spinning up. It's interesting, too, because it's also like, where's the line of what Netflix is producing in-house versus where they're getting outside vendors?
25:19Addy Osmani:And this feels like a completely in-house vertical thing.
25:22Joey Hurst:Yeah, sure. I mean, the scale at which Netflix operates, I think it's impossible to make everything in-house, right? So they'll handpick the top 5 % or 2 % of the shows that they're going to make in-house. And then the rest, they absolutely have to go to vendors for. So my guess is this new studio is probably not going to be attached to anything substantial, like anything that's going to air on Netflix anytime soon, but they are going to start to spin up the production methodologies and sort of get the quality bar up and figure out how to actually make something with AI before that goes out into the streaming service.
26:03Addy Osmani:Yeah, a little bit more in the article. They haven't posted anything publicly about it. Most of this info is sourced from job listings. And so Incubator's long-term technology strategy will focus on, quote, quote, Gen.ai enabled workflows, artist tooling, and scalable, secure multi-show environments, according to one listing. Another listing says that they're about creating animated shorts and specials using experimental Gen.ai native production pipelines. So yeah, starting short stuff for now or experimental stuff to probably validate the workflows and then moving to bigger things.
26:38Joey Hurst:If you look at the budget for Blue-Eye Samurai, I think, which was like a hundred plus million dollars you can now make a lot of those shots in gen ai how much savings would that be like i think these are the questions that they're asking internally blue-eyed samurai so good one of the best one of the best animated movies ever made yeah syria syria it was a mini well it was a
26:59Addy Osmani:season right and then uh but yeah it has taken years for season two to come out well like the
27:06Joey Hurst:The difficulty with Blue Eyes Samurai is it's highly adult content, but it's animated. And so the audience is really small.
27:14Addy Osmani:But no, I think, yeah, it's not a cheap show. It just also takes a long time to make with current tools.
27:21Joey Hurst:But that's an example of complete in-house Netflix production.
27:24Addy Osmani:Was that all done in-house? Yeah. One of the few.
27:27Joey Hurst:It's interesting that they chose animation before live action to do the first AI studio. I think that's, we know that's easier to do now. Like that's. That feels like a more achievable goal. Although I will say once you get into the mechanics of it, there's so much hand-driven art in animation that AI still probably doesn't have yet. I mean, maybe Netflix does, who knows. But things like squash and stretch and like the timing of animated characters and like the way their mouth exaggerates when they have an expression. Like, you know, it's not enough to like drive a character with like a video of yourself driving the character.
28:07Joey Hurst:Like you really have to, you know, go above it. Right, because the animated characters move. It's crazy. Like how expressive it has to be. Physically not possible. That's how it works. It's beyond puppeteering. It's an art form onto itself. So like having the training data for that, to train a model, to exaggerate like that, and then to control it in a way that is meaningful for that story moment. that's the challenging part and that's the stuff they have to solve at ink and yeah i think that's
28:34Addy Osmani:i think you're right on the money with with building out these tools to figure out that level of control that animators need all right two quick ones actually this one ties into animation and this was just kind of a cool story breakdown um so at disney world florida there was the aerosmith rock and roll coaster are you familiar with this it's been aerosmith branded since they opened it 20, 30 years ago. They're rebranding it to a Muppets theme, and they're redoing the show opener stuff, and so there is an animatronic scooter that is part of the pre-show, and so it'll be a permanent robot. But the animation to program the robot, they actually mo-capped a real scooter puppet that was being puppeteered by a human, mo-capped him, and then put that data onto the animatronic puppet.
29:26Addy Osmani:I thought it was like a really super flow.
29:28Joey Hurst:Yeah, because I was looking at the picture of this puppet in a mocap suit. I was like, is that just like a costume? Turns out that's a real mocap suit.
29:37Addy Osmani:He's got a little mocap hat on it.
29:40Joey Hurst:He's got markers on his face. They're tracking like the mouth opening and stuff.
29:44Addy Osmani:That's great because that's like also this good hybrid of, you know, you're still able to keep that human touch and animation that these puppets are famous for, but translate that over to a programmed robot. Oh, I love this, Joey. Which they probably weren't able to do. You know, I don't know. Obviously, I grew up in Florida, so I have deep ties to Disney World growing up. And so there was the Muppets 4D show that was always great, kind of fell into disrepair, and then they shut it down. And so their trade-off was like, well, we're going to rebrand Rock and Roll Coaster to the Muppets. But the Muppets show had permanent robots that would kind of perform.
30:18Addy Osmani:And so I'm thinking, like oh those robots animatronics never had the same level of fidelity that you could do now with both the improvement of how robotics have gotten and then also this mocap thing so that's
30:30Joey Hurst:cute that's beautiful beautiful execution of technology for entertainment and shout out to imagineers for all of us not getting out of the park with that stuff they never fail to disappoint
30:40Addy Osmani:do they yeah they're always great stuff it's always fun cool all right and that's it for today's show uh thanks for everything we talked about as usual at denoisepodcast.com i have nothing but
30:50Joey Hurst:thank you thank you for watching and listening to us a little over a year we're getting close to our 100th episode joey i think that's two or three episodes away damn man i have not tracked this at all so i have all right we'll have to look at the actual number um yeah we'll figure
31:06Addy Osmani:this out special one damn now it's like pressure i think i gotta think of something oh yeah leave us a comment.
31:12Joey Hurst:Yeah.
31:16All right.
31:17Addy Osmani:Thanks, everyone. We'll catch you in the next episode.
From the publisher
Google I/O is around the corner, and Addy and Joey unpack what's expected — from a potential Veo HDR upgrade to DeepMind's new storywriting AI tool, Fabula, built alongside working screenwriters. They also cover Image-Blaster, an open-source tool conve...
