Apple: AI video tools inside Final Cut Pro 11 Magnetic Mask to isolate people/objects without manual rotoscoping Transcribe to Captions for auto captions on the timeline
Both are built to speed up real editing work, not just generate clips. https://
buff.ly/EvqUOS7
MULTIMODAL AI
-
Apple Launches AI Video Tools in Final Cut Pro 11
By
–
-
Reasoning music models: future of AI-generated audio
By
–
My wish is that we get reasoning music models, but didn't put that into predictions because I doubt this will actually happen
-
Using AI Context Profiles to Enhance Business Automation
By
–
running automations without context about your business is like running a frontier AI model on a nokia phone you can fix that with context profiles i added context profiles inside our automations bundle → AI interviews you about your business → generates JSON profile (ICP,
-
Questions on Demo Statistics, Failure Modes, and Bimanual Grasping Correlations
By
–
Kudos on this elegant demo! Can you share some stats and failure modes? Are any of these items in the training set? Bimanual grasping seems to correlate w/ size. Are there counterexamples? Eg, a full-sized paper grocery bag w/ handle that it grasps w/ one hand? https://t.co/nITsKLCgG1
— Ken Goldberg (@Ken_Goldberg) 24 décembre 2025Kudos on this elegant demo! Can you share some stats and failure modes? Are any of these items in the training set? Bimanual grasping seems to correlate w/ size. Are there counterexamples? Eg, a full-sized paper grocery bag w/ handle that it grasps w/ one hand?
-
VLMs Struggle with Physical World Reasoning from Videos
By
–
‼️VLMs/MLLMs do NOT yet understand the physical world from videos‼️ In our recent work, we found that even the most advanced AI models still lag behind humans in one key aspect: reasoning about the kinematic properties of objects from videos. Takeaways: 1. ChatGPT 5.1 leads overall among 21 advanced VLMs, followed by Gemini 2.5 Pro/Flash. 2. Grok 4.1 delivers impressive performance at the lowest API cost. 3. Qwen3-VL is the top-performing open-source model. Read here: quantiphy.stanford.edu/ 🧵1/N
-
Grok Imagine dresses @1x_tech Neo impressively
By
–
Grok Imagine lets me imagine the @1x_tech Neo with different clothing. I haven’t played with it for a while. Damn it is good. pic.twitter.com/SvVseT52oX
— Robert Scoble (@Scobleizer) 24 décembre 2025Grok Imagine lets me imagine the @1x_tech Neo with different clothing. I haven’t played with it for a while. Damn it is good.
-
Sora 1.5 Pro: Cinema Video Generation with Synchronized Audio
By
–
Seedance 1.5 Pro is here
— Replicate (@replicate) 23 décembre 2025
ByteDance's latest audio-video generation model. Create cinema quality videos with native synchronized audio in a single pass, with multilingual support, character consistency, and cinematic camera controls pic.twitter.com/4dOBUWUYl0Sora 1.5 Pro is here ByteDance's latest audio-video generation model. Create cinema quality videos with native synchronized audio in a single pass, with multilingual support, character consistency, and cinematic camera controls
-
Qwen-Image-Edit-2511 Released with Enhanced Consistency and Speed
By
–
Qwen-Image-Edit-2511 is here An enhanced version over Qwen-Image-Edit-2509, featuring multiple improvements including notably better consistency We've worked with @PrunaAI again to deliver you the fastest speeds possible
-
AI Generates Realistic Historic Selfies with Iconic Figures
By
–
👀📽️🤷🏽♀️ If AI let you take ONE selfie from history… who are you choosing?
— Catherine Adenle (@CatherineAdenle) 23 décembre 2025
MLK?
Malcolm X?
Maya Angelou?
Harriet Tubman?
Lincoln?
John Lennon?
Someone just did it, and it actually looks real.
A creator dropped a video that feels like a casual photo walk with historic icons.… pic.twitter.com/8rVp0yY9lHIf AI let you take ONE selfie from history… who are you choosing? MLK?
Malcolm X?
Maya Angelou?
Harriet Tubman?
Lincoln?
John Lennon? Someone just did it, and it actually looks real. A creator dropped a video that feels like a casual photo walk with historic icons. -
NotebookLM previews new British English AI narration voices
By
–
NotebookLM is teasing new voices with British English narration that are planned to arrive in 2026. These voices are available for listening in the "Archive 1945" featured notebook, created in partnership with The Economist. Stay tuned for the first TC notebook today