Lifeboat Foundation: Safeguarding Humanity
Toggle light / dark theme

Blog

Category: robotics/AI – Page 277

DeepMind’s Genie 2 can generate interactive worlds that look like video games

DeepMind, Google’s AI research org, has unveiled a model that can generate an “endless” variety of playable 3D worlds.

Called Genie 2, the model — the successor to DeepMind’s Genie, which was released earlier this year — can generate an interactive, real-time scene from a single image and text description (e.g. “A cute humanoid robot in the woods”). In this way, it’s similar to models under development by Fei-Fei Li’s company, World Labs, and Israeli startup Decart.

DeepMind claims that Genie 2 can generate a “vast diversity of rich 3D worlds,” including worlds in which users can take actions like jumping and swimming by using a mouse or keyboard. Trained on videos, the model’s able to simulate object interactions, animations, lighting, physics, reflections, and the behavior of “NPCs.”

Genie 2: A large-scale foundation world model

Games play a key role in AI research.

Generating unlimited diverse training environments for future general agents.

Today we introduce Genie 2, a foundation world model capable of generating an endless variety of action-controllable, playable 3D environments for training and evaluating embodied agents. Based on a single prompt image, it can be played by a human or AI agent using keyboard and mouse inputs.

Games play a key role in the world of artificial intelligence (AI) research. Their engaging nature, unique blend of challenges, and measurable progress make them ideal environments to safely test and advance AI capabilities.

Frontiers: A base on the Moon surface or a mission to Mars are potential destinations for human spaceflight, according to current space agencies’ plans

These scenarios pose several new challenges, since the environmental and operational conditions of the mission will strongly differ than those on the International Space Station (ISS). One critical parameter will be the increased mission duration and further distance from Earth, requiring a Life Support System (LSS) as independent as possible from Earth’s resources. Current LSS physico-chemical technologies at the ISS can recycle 90% of water and regain 42% of O2 from the astronaut’s exhaled CO2, but they are not able to produce food, which can currently only be achieved using biology. A future LSS will most likely include some of these technologies currently in use, but will also need to include biological components. A potential biological candidate are microalgae, which compared to higher plants, offer a higher harvest index, higher biomass productivity and require less water. Several algal species have already been investigated for space applications in the last decades, being Chlorella vulgaris a promising and widely researched species. C. vulgaris is a spherical single cell organism, with a mean diameter of 6 µm. It can grow in a wide range of pH and temperature levels and CO2 concentrations and it shows a high resistance to cross contamination and to mechanical shear stress, making it an ideal organism for long-term LSS. In order to continuously and efficiently produce the oxygen and food required for the LSS, the microalgae need to grow in a well-controlled and stable environment. Therefore, besides the biological aspects, the design of the cultivation system, the Photobioreactor (PBR), is also crucial. Even if research both on C. vulgaris and in general about PBRs has been carried out for decades, several challenges both in the biological and technological aspects need to be solved, before a PBR can be used as part of the LSS in a Moon base. Those include: radiation effects on algae, operation under partial gravity, selection of the required hardware for cultivation and food processing, system automation and long-term performance and stability.

The International Space Station (ISS) has been continuously inhabited for over twenty years. The Life Support System (LSS) on board the station is in charge of providing the astronauts with oxygen, water and food. For that, Physico-Chemical (PC) technologies are used, recycling 90% of the water and recovering 42% of the oxygen (O2) from the carbon dioxide (CO2) that astronauts produce (Crusan and Gatens, 2017), while food is supplied from Earth.

Space agencies currently plan missions beyond Low Earth Orbit, with a Moon base or a mission to Mars as potential future scenarios (ESA Blog 2016; ISEGC 2018; NASA 2020). The higher distance from Earth of a lunar base, compared to the ISS, might require the production of food in-situ, to reduce the amount of resources required from Earth. PC technologies are not able to produce food, which can only be achieved using biological organisms. Several candidates are currently being investigated, with a main focus on higher plants (Kittang et al., 2014; Hamilton et al., 2020) and microalgae (Detrell et al., 2020b; Poughon et al., 2020).

AI Just Beat Doctors at Diagnosing Illness (Here’s Why That’s Actually GREAT News)

A groundbreaking study just revealed AI outperforming human doctors at medical diagnosis — but before you panic, this could be the best news yet for healthcare.

This hits personally for me. From my kiddo’s misdiagnosed case of hives to my own health struggles with multiple doctors, I’ve seen firsthand why we need AI to empower (not replace) medical professionals. I’m sure I’m not the only one.

In this video, we’ll explore:

-The shocking study results (90% AI accuracy vs 74% human doctors)
–Why this means more human connection, not less.
–How AI could transform patient care for the better.
–The real reason doctors aren’t fully utilizing AI yet.

The future of healthcare isn’t AI vs doctors — it’s both working together to provide better care than either could alone. Let’s dive into what this means for you and your family’s healthcare.

Simulated AI pets gain popularity among Chinese consumers

Boosted by China’s rapid development pace in artificial intelligence (AI) technologies, more companies have noted the huge business potential in AI companionship sectors, as simulated AI pets with adorable appearances gaining increasing popularity among Chinese consumers.

Zhang Yi, CEO of the iiMedia Research Institute, told the Global Times on Sunday that consumers’ demand for emotional support and the capability of current AI technologies offer this type of products greater business potential.

A Beijing-based student in her 20’s surnamed Zhang, who is also an AI technology fan, told the Global Times on Sunday that she bought “Boo Boo,” a simulated AI robotic pet developed by Hangzhou-based Genmoor Technology.

For news, algorithmic social networks are a failed experiment

Meta might yet teach its AI to more consistently show the right posts at the right time. Still, there’s a bigger lesson it could learn from Bluesky, though it might be an uncomfortable one for a tech giant to confront. It’s that introducing algorithms into a social feed may cause more problems than it solves—at least if timeliness matters, as it does with any service that aspires to scoop up disaffected Twitter users.

For a modern social network, Bluesky stays out of your way to a shocking degree. (So does Mastodon; I’m a fan, but it seems to be more of an acquired taste.) Bluesky’s primary view is “Following”—the most recent posts from the people you choose to follow, just as in the golden age of Twitter. (Present-day Twitter and Threads have equivalent views, but not as their defaults.) Starter Packs, which might be Bluesky’s defining feature, let anyone curate a shareable list of users. You can follow everyone in one with a single click, or pick and choose, but either way, you decide.

Driving The Future Of Transportation With AI-Powered Machines

Companies currently rely heavily on simulations to ensure that new versions meet a wide range of requirements. AV 2.0 systems are more sensitive to differences between real-world data and simulated data, so simulations need to be as realistic as possible. Instead of using hand-built 3D environments and pre-programmed vehicle behaviors, future testing will need to use advanced machine learning techniques to create highly realistic and scalable simulations.

It’s crucial for car manufacturers and the wider vehicle industry to adopt AI technologies in their development processes and products. There’s enormous potential for improved autonomous driving capabilities, better interaction between humans and machines and increased productivity for developers.

Just as software revolutionized many industries, AI is set to do the same—but even faster. Companies that quickly embrace these technologies may have a first-mover advantage and the chance to set industry standards. Those that delay may quickly fall behind, as their products will lack features compared to competitors.

Closing the AI equity gap by focusing on trust and safety

AI is becoming an increasingly powerful technology that can benefit humanity and sustainable development, but empowering local AI ecosystems across all countries needs to be prioritized to build the tools and coalitions necessary to ensure robust safety measures. Here, we make a case for reimagining trust and safety, a critical building block for closing the AI equity gap.

“Trust and safety” is not a term that developing countries are always familiar with, yet people are often impacted by it in their everyday interactions. Traditionally, trust and safety refers to the rules and policies that private sector companies put in place to manage and mitigate risks that affect the use of their digital products and services, as well as the operational enforcement systems that determine reactive or proactive restrictions. The decisions that inform these trust and safety practices carry implications for what users can access online, as well as what they can say or do.

Novel framework can generate images more aligned with user expectations

Generative models, artificial neural networks that can generate images or texts, have become increasingly advanced in recent years. These models can also be advantageous for creating annotated images to train algorithms for computer vision, which are designed to classify images or objects contained within them.

While many generative models, particularly generative adversarial networks (GANs), can produce synthetic images that resemble those captured by cameras, reliably controlling the content of the images they produce has proved challenging. In many cases, the images generated by GANs do not meet the exact requirements of users, which limits their use for various applications.

Researchers at Seoul National University of Science and Technology recently introduced a new image framework designed to incorporate the content users would like generated images to contain. This framework, introduced in a paper published on the arXiv preprint server, allows users to exert greater control over the image generation process, producing images that are more aligned with the ones they were envisioning.