Poetiq system achieved 54% score on ARC-AGI-2 benchmark, surpassing Gemini 3 Deep Think at more then twice lower compute cost. Poetiq (Mix) is a combined self learning system that leverages Gemini 3 and GPT-5.1 models. We want to do SVG tests
CREATIVE AI
-
Pixar Adopts NVIDIA RTX PRO 6000 for Advanced Rendering
By
–
99% of Pixar shots will now render entirely on NVIDIA RTX PRO 6000 GPUs.
— NVIDIA AI (@NVIDIAAI) 6 décembre 2025
RenderMan XPU, is reshaping Pixar’s workflow—bigger scenes, faster rendering, and unprecedented freedom coming for Toy Story 5… and beyond.
🎬 Watch the story behind the tech: https://t.co/0s9k2ZUPA7 pic.twitter.com/vNywStGhTP99% of Pixar shots will now render entirely on NVIDIA RTX PRO 6000 GPUs. RenderMan XPU, is reshaping Pixar’s workflow—bigger scenes, faster rendering, and unprecedented freedom coming for Toy Story 5… and beyond. Watch the story behind the tech: https://
youtu.be/Wz5vijQjpVM -
Using Gemini to generate web animations for motion design
By
–
Purée je viens d’avoir une idée avec ca , générer des motions design avec de l’animation web générer par gemini 3. Nice.
-
Krea Creator Partner Program Reopens with New Benefits
By
–
CPP is officially OPEN again We’re refreshing our Creator Partner Program and bringing in a new wave of creators. If you want perks, credits, early tools, reposts, and to be part of the Krea family… Sign up here: http://
krea.ai/cpp We can't wait to see who joins -
OpenAI May Release GPT-5.2 Soon
By
–
BREAKING : OpenAI may release GPT-5.2 as early as December 9 according to The Verge. RedGPT
-
Gen-4.5 Creates Worlds with Specific Aesthetic and Atmospheric Characteristics
By
–
With Gen-4.5 you can explore worlds that represent very specific points of view and aesthetic characteristics. The model allows you to precisely generate the look, feel and atmosphere of the world you want to create and the stories you want to tell. pic.twitter.com/EOKRzJQ90f
— Runway (@runwayml) 5 décembre 2025With Gen-4.5 you can explore worlds that represent very specific points of view and aesthetic characteristics. The model allows you to precisely generate the look, feel and atmosphere of the world you want to create and the stories you want to tell.
-
BulletTime: Decoupled Control of Time and Camera Pose for Video
By
–
BulletTime
— AK (@_akhaliq) 5 décembre 2025
Decoupled Control of Time and Camera Pose for Video Generation pic.twitter.com/AwLyi6DvToBulletTime Decoupled Control of Time and Camera Pose for Generation
-
Real-time Audio-Driven Avatar Generation Streaming Technology
By
–
Live Avatar
— AK (@_akhaliq) 5 décembre 2025
Streaming Real-time Audio-Driven Avatar Generation with Infinite Length pic.twitter.com/Bqj3yP4bNKLive Avatar Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
-
NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation
By
–
NeuralRemaster
— AK (@_akhaliq) 5 décembre 2025
Phase-Preserving Diffusion for Structure-Aligned Generation pic.twitter.com/y2m7LhcUS8NeuralRemaster Phase-Preserving Diffusion for Structure-Aligned Generation
-
Exceptional Design Quality in Recent AI Work
By
–
The design quality here is the highest I have seen in recent times. Incredible work by @camronsackett pic.twitter.com/xxssRPI7Tl
— Aravind Srinivas (@AravSrinivas) 5 décembre 2025The design quality here is the highest I have seen in recent times. Incredible work by @camronsackett