Every week, I organize 400 to 700 links into roughly 60 categories as part of my ongoing effort to learn about AI. This is my personal notebook, which I enjoy sharing with friends… a hobby and a labor of love, rather than a commercial publication or product.
If you arrived here through a search or shared link, this page collects the links I found for Video for the week ending August 28, 2026.
As part of my learning process, I like to automate the category covers. It gives me a chance to learn Python and APIs.
This week’s cover prompt was written using Claude Opus 4.7, and the image was generated using Nano Banana 2.1.
Category Cover Image Prompt: A mid-1980s murder-mystery movie poster of a wide three-story Victorian mansion in stark black-and-white pen-and-ink engraving on pure black, with warm amber windows framing costumed suspects (a beret-wearing director with megaphone, a glamorous starlet with boom mic, a shadowy figure snapping a clapperboard) and still lifes of film reels, storyboards, and a vintage movie camera on a tripod, with one window showing celluloid unspooling mid-fall; the central open door reveals an upright silver-haired butler with pencil mustache in black tailcoat holding a silver tray with a sealed envelope marked with a tiny clapperboard; fat rounded white sans-serif title Video centered above the roofline, 16:9, campy theatrical lighting, high-contrast crosshatching.
This Week in Video News
Summary by Claude Sonnet 5.5 based on this week’s links:
- Fast, controllable generators: Google's Gemini Omni 1.1 Flash adds scene extension, first and last frame control, 360p drafts and 4K upscaling. Arena reported it at #1 in Text-to-Video. Separately, fal's H3 Max, a post-trained MiniMax H3, topped the Image to Video board at Artificial Analysis.
- Speed becomes the headline: Ethan Mollick said H3 Max made a reasonably high quality clip in less time than it takes to watch it, prompt enhancement included. Krea claims 15 seconds of video in 5 seconds.
- Video as robot training data: Figure's Index platform says it has 16M uploaded videos and plans to spend $1B on data and compute over 12 months. Skild's S1 reportedly hit 66% on unseen tasks from one video demonstration, versus 9% when prompted with language.
This summary was generated by Claude Sonnet 5.5 to help you explore the links below. Rest assured, I select, organize, and check the links by hand in Google Sheets, and write the introduction and personal commentary in The Main Newsletters myself each week as a labor of love.
This week's links related to Video
Alibaba launches Wan3.0 AI video model after record $10 billion share sale
https://finance.yahoo.com/technology/ai/articles/alibaba-launches-wan3-0-ai-131300534.html
Introducing Index Today we’re coming out of stealth with Index, the largest & most diverse robot dataset in the world → 30min of video uploads/sec → 16M video uploads → Paid $15M to date → 264k downloads We’re committed to spending $1B the next 12 months on data & compute”
https://x.com/adcock_brett/status/2092303633559982106
Figure takes vertical integration to another level. Figure built its own egocentric data collection pipeline. Index is a crowdsourcing platform where anyone can collect data. – 264K app downloads across 108 countries – 44K weekly active contributors – 16M videos uploaded, 30″
https://x.com/TheHumanoidHub/status/2092388111083065555
We’re excited to release the best open-weight model for robotics. Isaac 0.5 is a 36B, 2.5B active per token model, one sparse backbone serving video perception, embodied reasoning and robot control.”
https://x.com/ArmenAgha/status/2092682391794155885
A line in AI video was crossed, in my experiments with just the web interface, H3 Max can now create reasonably high quality AI video in less time than it takes you to watch it. This is realtime from the moment I pushed the “generate” button (and also includes prompt enhancement)”
https://x.com/emollick/status/2093082102312923351
Introducing H3 Max by fal
https://blog.fal.ai/introducing-h3-max-by-fal/
Introducing H3 Max, new post-trained video model by fal Research. H3 Max ranks #1 for overall quality, prompt understanding, and aesthetics against leading video models, on both first-party and third-party independent evaluations while generating a 5-second 720p video under 3″
https://x.com/fal/status/2092710676431020376
Mixedbread is retrieval infrastructure for AI agents to find the right evidence across text, PDFs, tables, images, audio, and videos. We process millions of documents and searches every week. Our control plane runs on @planetscale Metal. → 0.05 ms p99 for our busiest”
https://x.com/mixedbreadai/status/2092654670988628223
How is @cognition working with Devin in Slack Code? 👀👇 Devin follows the work as it happens, picks up a task from the engineering channel, opens a PR with a demo video, and brings in a designer to finish the UI. All without leaving Slack or waiting to be tagged. The agent”
https://x.com/SlackHQ/status/2090874396739092779
This is very nice work from NVIDIA. Like all high-performing approaches on ARC-AGI-3, it uses deep learning-guided on-the-fly synthesis of symbolic world models, i.e. navigating the world by generating programs to represent what you know. To be clear, like with several other”
https://x.com/fchollet/status/2090838046937645398
Throwback to the “dinosaur input device” that was used to animate the stellar T-Rex dinosaur in the first Jurassic Park movie. Everything that has happened before will happen again, so now it’s a spatial 3D harness you can control with a Vision Pro and hand tracking.”
https://x.com/bilawalsidhu/status/2091641023487226143
Qwen-Video-Edit: Instruction-Based Video Editing by Repurposing an Image Editing Model” TL;DR: repurposes Qwen-Image-Edit for video by editing Wan 2.1 video-VAE latents directly, using lightweight projections instead of a video-pretrained transformer.”
https://x.com/Almorgand/status/2091925153588326411
AR guitar tutor! I’ve wanted something like this for so long. Check out this prototype by Allen Van Wert. Rocksmith is cool and all but this feels like the future. Makes me curious if others are building something like this? Should use monocular video & audio and work with”
https://x.com/bilawalsidhu/status/2092973390751473946
Excited to bring Gemini Omni Flash 1.1 to the world, this is an update to our anything in, anything out world model. It now supports: – 360p drafts, 4K up samplers – up to 10 seconds of video context when extending – video extensions in 10 second increments – video references”
https://x.com/OfficialLoganK/status/2093014204324417881
Joining the MTS stream today at 10am PST to yap about world models and spatial intelligence!”
https://x.com/bilawalsidhu/status/2090836155906289667
Learning How the World Evolves Extrapolative Video World Models via Latent Dynamics Reasoning paper:
https://x.com/_akhaliq/status/2091958146596041142
Thanks so much for sharing! @_akhaliq 🥰 The core idea is to learn how the world evolves, rather than directly predict what the future looks like. LDR maps past frames into structured latent states and rolls them forward with kinematic integration, learning only the higher-order”
https://x.com/haodongli00/status/2091961954562887884
Two days in and we’re at 5.5K GitHub stars, 1.4K forks, and 2.3M views on the launch videos. YouTube long form alone is past 200K views. I knew y’all wanted the code, but this is pretty damn wild. Thank you!”
https://x.com/bilawalsidhu/status/2092780364502597674
MiniMax H3 Max, a post-trained version of MiniMax H3 developed by fal, debuts at #1 in Image to Video and #3 in Text to Video on the Artificial Analysis Video Leaderboards with Audio, ahead of the base MiniMax H3 on both MiniMax H3 Max is built and served by fal, and”
https://x.com/ArtificialAnlys/status/2092717615739494424
Big news: Gemini Omni 1.1 Flash has landed #1 in the Text-to-Video Arena and #2 in the Image-to-Video Arena! For Text-to-Video the latest 1.1 model is +20pts above FLUX 3 Video at #3 (1495 pts). For Image-to-Video the release is a strong +25pt improvement from Gemini Omni Flash”
https://x.com/arena/status/2093015572212846673
Figure campus is a sci-fi movie”
https://x.com/adcock_brett/status/2091663840832618591
Gemini Omni 1.1 Flash is our newest multimodal model for video generation and editing. It delivers a new suite of creative capabilities and controls for developers 🎥 With this update you can: 🎬 Extend your scenes 🎯 Specify starting and ending frames of a shot ➕ Add video”
https://x.com/Google/status/2093008576487072064
introducing Gemini Omni 1.1 Flash this model brings a new suite of creative controls and generative video capabilities to developers – extend scenes for longer storytelling – specify first and last frames – draft videos more efficiently in 360p – upscale up to 4K resolution -“
https://x.com/GoogleAIStudio/status/2093008678118998298
Meet Gemini Omni 1.1 Flash ⚡️ Our newest multimodal model for video generation and editing. It now features your favorite creative controls from Veo, plus brand new capabilities. Enjoy features like 4K upscaling, first / last frame control, and fast 360p drafting. But, the”
https://x.com/GoogleAI/status/2093008998987403303
New models to know this week ▪️ MoE-ViE … Meta’s sparse mixture-of-experts vision encoder for efficient image and video understanding. ▪️ τ0-VLA – robot foundation model that “thinks” through possible outcomes before acting (AgiBot Finch) ▪️ 4DAnyone – turns a single casual”
https://x.com/TheTuringPost/status/2092420798539833839
H3 Max is now live on Krea. 50x faster than any other high quality video model … generate 15s of video in just 5s. try it now 👇”
https://x.com/krea_ai/status/2092990757506322661
Humanoid robots can now play tennis in the style of Nadal, Federer, and Djokovic, learned from broadcast footage. AdaPT (Noitom Robotics, Shanghai AI Lab, Dobot, SJTU) extracts professional player motions from TV broadcasts, retargets them to a humanoid, and learns both”
https://x.com/TheHumanoidHub/status/2090670770808848539
[1/7] 🚨 We’re releasing LAION-BVD: a 10-million-hour open video dataset for multimodal pre-training. – 1.3B video URLs from CommonCrawl – 80M downloaded videos – 10M video hours – 55M captioned clips – 300M frame-caption pairs 🌐:
https://t.co/dNGwHsygF7 🧵👇”
https://x.com/ahochlehnert/status/2092648676829413778
Can we gamify that? The innovators turning investigations on spying scandals and vote rigging into video games | Nieman Journalism Lab
https://www.niemanlab.org/2026/08/can-we-gamify-that-the-innovators-turning-investigations-on-spying-scandals-and-vote-rigging-into-video-games/
The @SkildAI team put a number on what a video demonstration is worth: roughly 380 teleoperation episodes. On tasks it had never seen, Skild’s S1 hit 66% from a single video demonstration. Same data, same architecture, prompted with language instead… 9%. If you are really into”
https://x.com/IlirAliu_/status/2092307596166168716
AI can write code, generate video and pass some of the hardest exams we can throw at it. But ask a robot to clear your kitchen table and things get complicated very quickly. That gap is exactly what @onticlabs_io is going after. I spoke with co-founder @omidtaherii yesterday.”
https://x.com/IlirAliu_/status/2092235796921430036
Show it a single human demonstration of a long-horizon task and the robot performs it right away. No fine-tuning, no retraining. Skild has released S1, a robot foundation model where you specify the task with a video demonstration instead of a language instruction. Why video,”
https://x.com/TheHumanoidHub/status/2092301463989203250
Predatorgate is a new video game based on an investigation into the Predator spyware scandal in Greece.”
https://x.com/NiemanLab/status/2091586427268026522
Leave a Reply