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.

BREAKING 🚨: First look into Video Overviews, which are generated by the same model that will power NotebookLM soon. These are 4 "Sparks", 1-3 minute videos in different styles generated from various sources.

TestingCatalog News 🗞

53,355 subscribers

178,639 views • 1 year ago •via X (Twitter)

Science & Technology News & Politics

Anya Rossi• Live Now

Private livecam show

10 Comments

TestingCatalog News 🗞1 year ago

"100% AI-generated" potentially means that the video and audio are generated by a single model. Full scoop 🗞

TestingCatalog News 🗞1 year ago

More stuff 👀

TestingCatalog News 🗞1 year ago

More stuff 2 👀

Rainmaker2 years ago

Can Machine Learning beat the market? Check out this post on my free Substack where I share code and commentary for an XGBoost model and a Random Forest model that both deliver powerful performances.

Jimmy Apples 🍎/acc1 year ago

Damn not bad at all.

TestingCatalog News 🗞1 year ago

Wondering how many attempts it takes to generate such decent vids. If it is on a par with what Audio Overviews offered, it will be huge.

Andrew Curran1 year ago

The design one is impressive.

TestingCatalog News 🗞1 year ago

I like the Pixel One the most 🤩

Micah1 year ago

YouTube shorts is cooked

Charlie L.1 year ago

Google took this next level im in awe

Related Videos

Today we are launching Dream Machine, our first AI model that generates cinematic and fluid videos from text instructions and images. I generated this 1-minute 60 fps video entirely from our model. Try Dream Machine → Join us →

Today we are launching Dream Machine, our first AI model that generates cinematic and fluid videos from text instructions and images. I generated this 1-minute 60 fps video entirely from our model. Try Dream Machine → Join us →

Dan Kondratyuk

38,992 views • 2 years ago

We are developing a custom Gaussian Splatting Viewer, which enables to compare different models side by side in a single interface. Online soon The 3d model generated by the new polycam

We are developing a custom Gaussian Splatting Viewer, which enables to compare different models side by side in a single interface. Online soon The 3d model generated by the new polycam

Center for Spatial Technologies

14,217 views • 3 years ago

Introducing Cinematic Video Overviews, the next evolution of the NotebookLM Studio. Unlike standard templates, these are powered by a novel combination of our most advanced models to create bespoke, immersive videos from your sources. Rolling out now for Ultra users in English!

Introducing Cinematic Video Overviews, the next evolution of the NotebookLM Studio. Unlike standard templates, these are powered by a novel combination of our most advanced models to create bespoke, immersive videos from your sources. Rolling out now for Ultra users in English!

Gemini Notebook

3,520,463 views • 6 months ago

It is possible to get Genie 3 to make worlds that are visually interesting. I have been using images I generated in Midjourney of vast megastructures & odd cities in various styles. After 20 seconds I can freely wander around them. (Yes, I controlled the cat in the first scene)

It is possible to get Genie 3 to make worlds that are visually interesting. I have been using images I generated in Midjourney of vast megastructures & odd cities in various styles. After 20 seconds I can freely wander around them. (Yes, I controlled the cat in the first scene)

Ethan Mollick

56,351 views • 7 months ago

Sneak peek of OpenAI's GPT-6 Astra, generated by Peter Gostev. This model is coming to Arena.ai soon. Stay tuned to test Astra yourself, your votes will power the leaderboard! In the meantime, check out Peter’s first impressions in full on YouTube:

Sneak peek of OpenAI's GPT-6 Astra, generated by Peter Gostev. This model is coming to Arena.ai soon. Stay tuned to test Astra yourself, your votes will power the leaderboard! In the meantime, check out Peter’s first impressions in full on YouTube:

Arena.ai

29,713 views • 15 days ago

These AI-generated videos circulating on Chinese social media are getting wilder and wilder… here in this video 🇨🇳 Unitree humanoid robot soldiers in that “CMG 2026 Spring Festival Gala” outfit are defeating the US military à la The Avengers..

These AI-generated videos circulating on Chinese social media are getting wilder and wilder… here in this video 🇨🇳 Unitree humanoid robot soldiers in that “CMG 2026 Spring Festival Gala” outfit are defeating the US military à la The Avengers..

Byron Wan

36,761 views • 7 months ago

PLEASE SHARE! AI slop has become practically impossible to tell apart with wildlife photography and this is about to introduce SO many real life issues! 🚨🦜 ALL these images in this video are AI generated, but they look EXACTLY like the species down to the feather. 😵‍💫(1/4)

PLEASE SHARE! AI slop has become practically impossible to tell apart with wildlife photography and this is about to introduce SO many real life issues! 🚨🦜 ALL these images in this video are AI generated, but they look EXACTLY like the species down to the feather. 😵‍💫(1/4)

Nick Volpe

41,599 views • 5 months ago

UP CM Yogi Adityanath said that videos of demolition of ancient temples at Varanasi’s Manikarnika ghat are AI generated and attack Congress. But, the same videos and photos were attached in the letter written by family of Ahilyabai Holkar to PM and CM. Are they lying too?

UP CM Yogi Adityanath said that videos of demolition of ancient temples at Varanasi’s Manikarnika ghat are AI generated and attack Congress. But, the same videos and photos were attached in the letter written by family of Ahilyabai Holkar to PM and CM. Are they lying too?

Shantanu

80,387 views • 8 months ago

[ Truth & Inference ] (1/2) Here are different videos of players from the Chinese server giving a showcase of the Prospector's Truth & Inference costume, accessory, and emote. ※ Video 1: ※ Video 2: ※ Video 3: ※ Video 4:

[ Truth & Inference ] (1/2) Here are different videos of players from the Chinese server giving a showcase of the Prospector's Truth & Inference costume, accessory, and emote. ※ Video 1: ※ Video 2: ※ Video 3: ※ Video 4:

Identity V | News

86,695 views • 11 months ago

Is VideoGen starting to become good enough for robotic manipulation? 🤖 Check out our recent work, RIGVid — Robots Imitating Generated Videos — where we use AI-generated videos as intermediate representations and 6-DoF motion retargeting to guide robots in diverse manipulation tasks: pouring, wiping, mixing, and more. 🔗 Key takeaways: - VideoGen starts to become good enough for robotics - As the field progresses, we are expecting much better results in the coming years - Depending on whether video prediction models take actions or not (VideoGen vs Action-Conditioned Video Prediction), there are different ways to use them. - Controllability & steerability are still issues In the paper, we explore: – How do different video generation models compare for robotic imitation? – Can generated videos replace real videos for imitation? – What causes failure of imitation given high-quality videos? – How does imitating from video compare with other representations (e.g., keypoint constraints like ReKep)? 🎥 Watch the video for (1) AI-generated inputs, (2) robot executions, and (3) the 3D intermediate representation bridging the embodiment gap.

Is VideoGen starting to become good enough for robotic manipulation? 🤖 Check out our recent work, RIGVid — Robots Imitating Generated Videos — where we use AI-generated videos as intermediate representations and 6-DoF motion retargeting to guide robots in diverse manipulation tasks: pouring, wiping, mixing, and more. 🔗 Key takeaways: - VideoGen starts to become good enough for robotics - As the field progresses, we are expecting much better results in the coming years - Depending on whether video prediction models take actions or not (VideoGen vs Action-Conditioned Video Prediction), there are different ways to use them. - Controllability & steerability are still issues In the paper, we explore: – How do different video generation models compare for robotic imitation? – Can generated videos replace real videos for imitation? – What causes failure of imitation given high-quality videos? – How does imitating from video compare with other representations (e.g., keypoint constraints like ReKep)? 🎥 Watch the video for (1) AI-generated inputs, (2) robot executions, and (3) the 3D intermediate representation bridging the embodiment gap.

Yunzhu Li

16,540 views • 1 year ago

BREAKING 🚨: Early look at Claude Task Mode agent workflow. What do we know so far? - Claude Tasks will operate various Skills and MCPs to achieve the goal. - Claude will ask clarifying questions before the execution or skip it after a timeout. - Claude will generate an action plan for complex tasks. - Users will be able to modify the plan on the fly or send additional context to the workflow while Claude is working. - Generated artefacts can be previewed in a separate panel. - All artefacts, Skills, scripts and generated files will be stored in the working files directory. - And more details in the post 👀 NotebookLM on Skills 🔥

BREAKING 🚨: Early look at Claude Task Mode agent workflow. What do we know so far? - Claude Tasks will operate various Skills and MCPs to achieve the goal. - Claude will ask clarifying questions before the execution or skip it after a timeout. - Claude will generate an action plan for complex tasks. - Users will be able to modify the plan on the fly or send additional context to the workflow while Claude is working. - Generated artefacts can be previewed in a separate panel. - All artefacts, Skills, scripts and generated files will be stored in the working files directory. - And more details in the post 👀 NotebookLM on Skills 🔥

🚨 AI News | TestingCatalog

77,586 views • 9 months ago

I am back!! I will be talking and writing here often.. Yes my X account has been in trouble as it got hacked in February. Now I have finally had the help from the X team after lot of struggles in establishing a proper communication. All is well!! Now I am here. Also, there are many weird ads that are running which are articles about me with very absurd headlines and AI generated pictures. These are click baits, which lead to spam / fraudulent links. Please keep reporting these ads. I have no power in putting them down. I have tried my best. These are X ad regulations, which allow such ads to run. Hope they solve these matters soon.

I am back!! I will be talking and writing here often.. Yes my X account has been in trouble as it got hacked in February. Now I have finally had the help from the X team after lot of struggles in establishing a proper communication. All is well!! Now I am here. Also, there are many weird ads that are running which are articles about me with very absurd headlines and AI generated pictures. These are click baits, which lead to spam / fraudulent links. Please keep reporting these ads. I have no power in putting them down. I have tried my best. These are X ad regulations, which allow such ads to run. Hope they solve these matters soon.

Shreya Ghoshal

481,660 views • 1 year ago

MLB should look into these bats the Yankees are using. Aaron Judge has 4 home runs in 3 games and he was never a power hitter before this year.

MLB should look into these bats the Yankees are using. Aaron Judge has 4 home runs in 3 games and he was never a power hitter before this year.

A.J Rodriguez

668,134 views • 1 year ago

Can y’all tell this movie is fully AI-generated? 👀 These are clips from The Cully Hill Boys, a 110-minute film made entirely with @Higgsfield’s Cinema Studio 4.0, powered by Seedance 2.5. It took 4 weeks, a crew of 28, and ~$2M to make.

Can y’all tell this movie is fully AI-generated? 👀 These are clips from The Cully Hill Boys, a 110-minute film made entirely with @Higgsfield’s Cinema Studio 4.0, powered by Seedance 2.5. It took 4 weeks, a crew of 28, and ~$2M to make.

Tiffany Fong

46,921 views • 1 month ago

What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵

What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵

Google DeepMind

3,740,957 views • 1 year ago

I know people from Kai x Speeds production team and they told me that these Minecraft boss battles are pre recorded and are really being played by Minecraft experts. Kai x Speed are pretending to be the players in order to milk the add revenue that is being generated for the marathon.

I know people from Kai x Speeds production team and they told me that these Minecraft boss battles are pre recorded and are really being played by Minecraft experts. Kai x Speed are pretending to be the players in order to milk the add revenue that is being generated for the marathon.

GEM

238,776 views • 1 month ago