YouTube Shorts has upgraded its Dream Screen AI background generator to incorporate Google DeepMind’s latest video model, Veo 2, which will also generate standalone video clips that users can post to Shorts. “Need a specific scene but don’t have the right footage? Want to turn your imagination into reality and tell a unique story? Simply use a text prompt to generate a video clip that fits perfectly into your narrative, or create a whole new world,” coaxes YouTube, which seems to be trying out “Dream Screen” branding as an umbrella for its genAI efforts. Continue reading YouTube Shorts Updates Dream Screen with Google Veo 2 AI

Elon Musk’s xAI has released its latest AI model Grok 3, which the company is describing as the “smartest AI on Earth.” It includes reasoning capabilities and a new web analysis tool called DeepSearch that returns results “within seconds” and can refine specific sources, according to xAI. Grok 3 was trained with 200,000 Nvidia GPUs, resulting in improved response times and processing power. Future capabilities will include Voice Mode for conversational interaction and audio-to-text conversion. Access to Grok 3 is limited to X Premium+ subscribers or via a SuperGrok plan (that does not include X social features). Continue reading xAI Launches Grok 3 as Standalone and for X Premium+ Subs

Most people know Hugging Face as a resource-sharing community, but it also builds open-source applications and tools for machine learning. Its recent release of vision-language models small enough to run on smartphones while outperforming competitors that rely on massive data centers is being hailed as “a remarkable breakthrough in AI.”  The new models — SmolVLM-256M and SmolVLM-500M — are optimized for “constrained devices” with less than around 1GB of RAM, making them ideal for mobile devices including laptops and also convenient for those interested in processing large amounts of data cheaply and with a low-energy footprint. Continue reading Hugging Face Has Developed Tiny Yet Powerful Vision Models

Artist-led generative AI film and animation studio Asteria has joined with AI research startup Moonvalley to create Marey, “the entertainment industry’s first clean foundational AI model.” Trained exclusively on “ethically sourced data” owned by Asteria, Marey is named after the French physiologist who helped put the “motion” in motion pictures, Étienne-Jules Marey. Asteria says Marey is being trained for a 2025 debut targeting major Hollywood productions with a pitch that says it has not and will not rely on scraped data, something Big Tech competitors have taken heat on. Continue reading Asteria and Moonvalley Team Up on Ethical AI for Hollywood

Google has introduced Gemini 2.0, the latest version of its multimodal AI model, signaling a shift toward what the company is calling “the agentic era.” The upgraded model promises not only to outperform previous iterations on standard benchmarks but also introduces more proactive, or agentic, functions. The company announced that “Project Astra,” its experimental assistant, would receive updates that allow it to use Google Search, Lens, and Maps, and that “Project Mariner,” a Chrome extension, would enable Gemini 2.0 to navigate a user’s web browser to complete tasks autonomously. Continue reading Google Releases Gemini 2.0 in Shift Toward Agentic Era of AI

With AI powering a range of new world-building apps, 2025 could be the year the metaverse finally makes an impact. Midjourney joins the world-building club with Patchwork, a collaborate canvas for creating “infinite” fictional worlds. Now in research preview, the tool is being developed as a standalone app, though preview access requires a Midjourney Discord account linked to a Google account. Users are able to connect characters and worlds, and “share” their developing world — evolving as a “board” — with up to 100 collaborative partners on Midjourney (though the company recommends fewer participants for a more focused experience). Continue reading Midjourney Touts Collaborative World-Building App Patchwork

Google DeepMind’s new Genie 2 is a large foundation world model that generates interactive 3D worlds that are being likened to video games. “Games play a key role in the world of artificial intelligence research,” says Google DeepMind, noting “their engaging nature, challenges and measurable progress make them ideal environments to safely test and advance AI capabilities.” Based on a simple prompt image, Genie 2 is capable of producing “an endless variety of action-controllable, playable 3D environments” — suitable for training and evaluating embodied agents — that can be played by a human or AI agent using keyboard and mouse inputs. Continue reading DeepMind Genie 2 Creates Worlds That Emulate Video Games

Google DeepMind has come up with an error correction technique it says will make quantum computers more reliable, particularly at scale. While quantum computing holds tremendous promise — potentially able to solve in just a few hours problems it would take a conventional computer “billions of years” to figure out, Google claims — the systems are notoriously unstable, due to the delicacy of the “quantum state.” AlphaQubit is an AI-based decoder that identifies quantum computing errors with accuracy. Combining DeepMind’s machine learning expertise with Google Quantum AI error correction, the technique advances efforts to create a reliable quantum computer. Continue reading Google DeepMind Touts AI-Powered Quantum Error Detection

YouTube has added a new feature to its Dream Track toolset, which lets select U.S. creators use AI to generate songs using the vocals of artists including John Legend, Demi Lovato, Charli XCX, Charlie Puth and others. Now users can remix Dream Track songs using natural language to describe the changes they would like, stylistic and otherwise. Selecting the “restyle a track” option will steer users to creating a 30-second generative snippet for use in YouTube Shorts. The remixed snippets will credit the original song with “clear attribution” through the Short itself and the Shorts audio pivot page. It will also clearly indicate that the track was restyled with AI, according to Google. Continue reading YouTube Dream Track Toolset Introduces an AI Remix Feature

The Allen Institute for AI (also known as Ai2, founded by Paul Allen and led by Ali Farhadi) has launched Molmo, a family of four open-source multimodal models. While advanced models “can perceive the world and communicate with us, Molmo goes beyond that to enable one to act in their worlds, unlocking a whole new generation of capabilities, everything from sophisticated web agents to robotics,” according to Ai2. On some third-party benchmark tests, Molmo’s 72 billion parameter model outperforms other open AI offerings and “performs favorably” against proprietary rivals like OpenAI’s GPT-4o, Google’s Gemini 1.5 and Anthropic’s Claude 3.5 Sonnet, Ai2 says. Continue reading Allen Institute Announces Vision-Optimized Molmo AI Models

YouTube is introducing AI detection tools designed to allow people to learn when their face and/or voice are copied and used in third-party videos. As part of the effort, YouTube’s existing Content ID program that protects copyrighted music will expand to include more broad-based voice simulation detection technology. The new tools aim to protect “people from a variety of industries — from creators and actors to musicians and athletes,” according to the company. The Google-owned platform is also coming up with a way to address unauthorized use of its content for training AI models. Continue reading YouTube Adding Tools to Protect Against Unauthorized AI Use

Google DeepMind has made its latest AI image generator, Imagen 3, free for use in the U.S. via the company’s ImageFX platform. Imagen 3 will be available in multiple versions, “each optimized for different types of tasks, from generating quick sketches to high-resolution images.” Google announced Imagen 3 at Google I/O in March, and in June made it available to enterprise users through Vertex. Using simplified natural language text input rather than “complex prompt engineering,” Google says Imagen 3 generates high-quality images in a range styles, from photorealistic, painterly and textured to whimsically cartoony. Continue reading Google DeepMind Releases Imagen 3 for Free to U.S. Users

CuspAI, a UK startup that aims to help engineer sustainable materials, has raised $30 million from venture funds in Europe and the U.S., secured a partnership with Meta’s FAIR unit, and employed the advisory services of AI pioneer Geoffrey Hinton in its mission to tackle climate change. “CuspAI leverages cutting-edge generative AI, deep learning, and molecular simulation to streamline the material design process,” the company announced. Its platform “functions like a search engine for materials, allowing users to request specific properties for new materials on demand,” speeding the process of “the discovery of materials with precise functionalities.” Continue reading Green Startup CuspAI Secures $30 Million, Meta Partnership

Google DeepMind has unveiled new research on AI tech it calls V2A (“video-to-audio”) that can generate soundtracks for videos. The initiative complements the wave of AI video generators from companies ranging from biggies like OpenAI and Alibaba to startups such as Luma and Runway, all of which require a separate app to add sound. V2A technology “makes synchronized audiovisual generation possible” by combining video pixels with natural language text prompts “to generate rich soundscapes for the on-screen action,” DeepMind writes, explaining that it can “create shots with a dramatic score, realistic sound effects or dialogue.” Continue reading DeepMind’s V2A Generates Music, Sound Effects, Dialogue

Google is launching two new AI models: the video generator Veo and Imagen 3, billed as the company’s “highest quality text-to-image model yet.” The products were introduced at Google I/O this week, where new demo recordings created using the Music AI Sandbox were also showcased. The 1080p Veo videos can be generated in “a wide range of cinematic and visual styles” and run “over a minute” in length, Google says. Veo is available in private preview in VideoFX by joining a waitlist. At a future date, the company plans to bring some Veo capabilities to YouTube Shorts and other products. Continue reading Veo AI Image Generator and Imagen 3 Unveiled at Google I/O