Categories
Entertainment

Genie 2 de Google DeepMind puede crear mundos interactivos en 3D

[ad_1]

Google acaba de revelar DeepMind genio 2que es una IA de modelado mundial capaz de crear mundos 3D y mantener esos entornos durante un período mucho más largo. Genie 2 no es un motor de juego. Es un modelo de publicación que crea imágenes a medida que el jugador (ya sea un humano u otro agente de IA) se mueve por el mundo simulado por el software. Todo lo que necesita para comenzar es una única foto generada por IA o a partir de una foto real.

Hay limitaciones: DeepMind dice que el modelo puede crear mundos “consistentes” durante hasta 60 segundos, y la mayoría de los ejemplos que la compañía compartió el miércoles duran mucho menos: la mayoría de los videos duran entre 10 y 20 segundos. La calidad de la imagen también se degrada y disminuye cuanto más tiempo le toma al Genie 2 mantener la ilusión de un mundo consistente.

– Matt Smith

Reciba esto diariamente directamente en su bandeja de entrada. ¡Suscríbete aquí!

Las historias tecnológicas más importantes que te perdiste

HechoHecho

Bethesda

Indiana Jones y el Gran Círculo aquí. Claro, este no es Harrison Ford, pero esta personificación de Troy Baker es una excelente película independiente, reforzada por una escritura, un sonido y una dirección que la hacen sentir como una película clásica de Spielberg y Lucas. El juego tiene algunas asperezas, pero todas son descaradamente Indiana Jones.

Continúe leyendo.

HechoHecho

ora

Oura está implementando la detección de enfermedades respiratorias para los usuarios de Ring Gen 3 y Ring 4. Los usuarios con una suscripción activa deberían obtener Symptom Radar antes del 11 de diciembre. La función analiza métricas, incluida la frecuencia cardíaca en reposo, la temperatura de la piel, los datos del sueño y la frecuencia respiratoria, para ver si hay alguna diferencia con las estadísticas de referencia. Si es así, Oura podrá indicarte que ha detectado posibles síntomas de resfriado o gripe. ¡Justo a tiempo para las vacaciones!

Continúe leyendo.

[ad_2]

Source Article Link

Categories
News

Google DeepMind presenta el modelo de IA Genie 2, que puede crear mundos 3D jugables para entrenar agentes de IA

[ad_1]

Google DeepMind Genie presentó el miércoles el sucesor de su modelo de inteligencia artificial (IA) Genie, que puede generar infinitos mundos de juegos en 2D. El nuevo modelo de IA, llamado Genie 2, es capaz de crear entornos 3D únicos que pueden controlarse y operarse en base a un único vector de imagen. La compañía describió a Genie 2 como un “modelo universal” de inteligencia artificial y afirmó que puede crear entornos de hasta un minuto de duración utilizando objetos consistentes. La compañía dijo que estos mundos generados pueden ser jugados por humanos o usarse para entrenar agentes de inteligencia artificial.

Google DeepMind presenta el modelo de inteligencia artificial Genie 2

en un Publicación de blogLa empresa detalló el nuevo modelo de IA y sus capacidades. mientras predecesor El modelo de IA Genie 2 solo puede crear mundos de juego para plataformas 2D y puede crear mundos 3D completos con modelos consistentes con los que interactuar. Esto significa que los humanos o agentes de IA pueden caminar, correr, nadar, trepar y realizar más acciones en estos entornos.

Las capacidades generativas permiten a Genie 2 crear caminos, edificios y objetos que no se pueden ver en la imagen de entrada. Estos elementos son diseñados y presentados por el modelo desde cero. Además, el modelo básico también puede mantener la coherencia en estos entornos. Esto significa que incluso cuando el jugador se aleja de un área y regresa, los entornos siguen siendo los mismos.

Aparte de esto, Genie 2 es capaz de generar diferentes puntos de vista como puntos de vista en primera persona, puntos de vista isométricos o puntos de vista en tercera persona. Además, los usuarios también pueden interactuar con objetos en los mundos generados y realizar acciones como abrir una puerta, inflar un globo o subir una escalera. También se le puede pedir al modelo que cree efectos relacionados con la física, como ondas de agua, humo, gravedad, iluminación direccional, reflejos y más.

En términos de detalles técnicos, DeepMind explicó que Genie 2 es un modelo de difusión latente autorregresivo y fue entrenado en un gran conjunto de datos de video. La arquitectura Transformers también incluye un codificador automático que permite generar estos mundos cuadro por cuadro.

En particular, DeepMind también Liberado Un modelo de IA denominado Scalable Instructable Multiworld Agent, o SIMA, a principios de este año, es esencialmente capaz de realizar funciones de agente de IA en mundos 3D. La compañía dice que Genie 2 es capaz de proporcionar entornos únicos para agentes de IA similares y entrenarlos en diferentes escenarios de la vida real.

Dado que el modelo global puede crear entornos únicos, Google dice que esto eliminará el riesgo de contaminación de datos y permitirá a los desarrolladores evaluar adecuadamente las capacidades del agente de IA.

[ad_2]

Source Article Link

Categories
Entertainment

Se avecinan cambios en el servicio Genie+ de Disneyland

[ad_1]

Nuevos cambios están llegando a Servicio Disneyland y Walt Disney World + Genieun servicio pago sin colas en los parques, a partir de julio.

Disney Genie+ y Lightning Lane en los dos parques temáticos costeros cambiarán de nombre a partir del 24 de julio. Disney Genie+ pronto se conocerá como Lightning Lane Multi-Pass, mientras que los Lightning Lanes individuales pronto se conocerán como Lightning Lane Single Pass.

En Walt Disney World, los visitantes pronto podrán comprar un pase múltiple Lightning Lane o un pase único Lightning Lane antes de su visita planificada. La opción de reservar viajes y atracciones con anticipación desapareció en 2021 cuando Disney presentó por primera vez su nuevo servicio sin colas.

Más cerca de casa en Disneylandia, “La forma en que los visitantes compran, seleccionan y canjean boletos de Lightning Lane en Disneyland Resort seguirá siendo la misma”, dice el sitio web. Blog de parques de Disney.

Los beneficios gratuitos de Disney Genie seguirán estando disponibles a través de las aplicaciones Disneyland y My Disney Experience.

Los nuevos cambios en Disney Genie+ se deben en parte a los comentarios de los huéspedes, según la publicación del blog.

[ad_2]

Source Article Link

Categories
News

Create interactive virtual worlds from text prompts using Genie 1.0

Create interactive virtual worlds from text prompts using Genie 1

Google has introduced Genie 1.0, an AI system that represents a significant advancement toward Artificial General Intelligence (AGI). Genie 1.0 is a generative interactive environment that can create a variety of virtual worlds from text descriptions, including synthetic images, photographs, and sketches. It operates on an unsupervised learning model trained on low-resolution internet videos, which are then upscaled. This system is considered a foundational world model, crucial for the development of AGI, due to its ability to generate action-controllable environments.

Google has made a striking advancement in the realm of artificial intelligence with the unveiling of Genie 1.0, a system that edges us closer to the elusive goal of Artificial General Intelligence (AGI). This new AI is capable of transforming simple text descriptions into interactive virtual environments, marking a significant stride in the evolution of AI technologies.

At the core of Genie 1.0’s functionality is the ability to bring written scenes to visual life. This goes beyond the typical AI that we’re accustomed to, which might recognize speech or offer movie recommendations. Genie 1.0 is designed to construct intricate virtual worlds, replete with images and sketches, all from the text provided by a user. It relies on an advanced form of machine learning known as unsupervised learning, which empowers it to identify patterns and make informed predictions without needing explicit instructions.

One of the most fascinating features of Genie 1.0 is its proficiency in learning from imperfect sources. It can take low-resolution videos from the internet, which are often grainy and unclear, and enhance them to a more refined 360p resolution. This showcases the AI’s ability to work with less-than-ideal data and still produce improved results.

Google Genie 1.0 another step closer to AGI?

Here are some other articles you may find of interest on the subject of Artificial General Intelligence (AGI) :

Understanding Artificial General Intelligence (AGI)

The driving force behind Genie 1.0 is a robust foundational world model, boasting an impressive 11 billion parameters. This model is a cornerstone for AGI development, as it facilitates the generation of dynamic and manipulable environments. Such environments are not just static but can be altered and interacted with, paving the way for a multitude of potential uses.

The versatility of Genie 1.0 is evident in its ability to process a wide array of inputs, suggesting that its future applications could go far beyond the creation of simple 2D environments. Although it currently functions at a rate of one frame per second, there is an expectation that its performance will improve over time. As Google continues to enhance Genie with future iterations, we can expect a broadening of its capabilities.

The practical uses for Genie 1.0 are vast and varied. In the field of robotics, for instance, combining Google’s robotics data with Genie could lead to the creation of more sophisticated AI systems. The gaming industry also stands to benefit greatly from Genie, as it has the potential to revolutionize game development, offering novel experiences and serving as a platform for training AI agents in simulated environments.

While Genie 1.0 promises to significantly influence creative endeavors by enabling the generation of unique content from minimal input, it’s important to remain mindful of the concerns that accompany advanced AI systems. Skepticism about AI is not uncommon, and as technologies like Genie continue to advance, they will undoubtedly spark further debate about their impact and the ethical considerations they raise.

Exploring Genie 1.0’s Advanced Capabilities

Google’s Genie 1.0 represents a pivotal development in the journey toward AGI. Its innovative method of creating interactive virtual worlds and its ability to learn from low-resolution data highlight the immense possibilities within AI. As we look to the future, the continued refinement and application of systems like Genie will undoubtedly play a crucial role in shaping the trajectory of both technology and society.

Artificial General Intelligence, or AGI, is a type of intelligence that mirrors human cognitive abilities, enabling machines to solve a wide range of problems and perform tasks across different domains. Unlike narrow AI, which is designed for specific tasks such as language translation or image recognition, AGI can understand, learn, and apply knowledge in an array of contexts, much like a human being. The development of AGI is a significant challenge in the field of artificial intelligence, as it requires a system to possess adaptability, reasoning, and problem-solving skills without being limited to a single function.

At the heart of Genie 1.0’s functionality lies its ability to interpret and visualize text descriptions, transforming them into detailed virtual environments. This process is driven by unsupervised learning, a machine learning technique that allows AI to recognize patterns and make decisions with minimal human intervention. Unsupervised learning is crucial for AGI, as it enables the system to handle data in a way that mimics human learning, where explicit instructions are not always provided.

Genie 1.0’s proficiency in enhancing low-resolution videos to a clearer 360p resolution demonstrates its capacity to improve upon imperfect data. This is a significant step forward, as it shows that AI can not only work with high-quality data but also refine and utilize information that is less than ideal, which is often the case in real-world scenarios.

The Potential and Challenges of Google Genie

The foundational world model that powers Genie 1.0, with its 11 billion parameters, is a testament to the complexity and potential of this AI system. The ability to generate dynamic environments that users can interact with opens up a world of possibilities for various industries. For example, in robotics, Genie 1.0 could be used to create more advanced simulations for training AI, while in gaming, it could lead to more immersive and responsive virtual worlds.

Despite its current limitation of processing one frame per second, the expectation is that Genie 1.0 will become faster and more efficient with time. This improvement will expand its applications and make it even more valuable across different sectors.

However, the advancement of AI technologies like Genie 1.0 also brings about ethical considerations. As AI systems become more capable, questions arise about their impact on privacy, employment, and decision-making. It is crucial to address these concerns proactively, ensuring that the development of AI benefits society while minimizing potential risks.

In summary, Google’s Genie 1.0 is a significant step towards achieving AGI, with its innovative approach to creating interactive virtual environments and learning from various data sources. As this technology continues to evolve, it will likely have a profound impact on multiple industries and raise important ethical questions that must be carefully considered.

Filed Under: Technology News, Top News





Latest timeswonderful Deals

Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, timeswonderful may earn an affiliate commission. Learn about our Disclosure Policy.

Categories
News

Google Genie AI creates interactive game worlds from images

Google Genie AI creates interactive game worlds from images

Imagine a world where the lines between reality and the digital realm blur, where you can step into a photograph and explore it as if it were a living, breathing environment. In the ever-evolving landscape of artificial intelligence, Google’s DeepMind has made a striking advancement with the creation of Genie, an AI that can generate an endless array of 2D worlds for gaming. This innovative tool is trained on a massive amount of gaming footage and uses a complex model with 11 billion parameters to understand and create new gaming environments.

Genie is not just another AI; it’s a sophisticated system that can interpret hidden actions within data, known as latent actions. This allows it to take simple images, even children’s drawings, and turn them into interactive, playable worlds. The implications of this technology are vast, with potential applications in robotics and the pursuit of artificial general intelligence.

What sets Genie apart is its use of unsupervised learning. Unlike traditional AI, which relies on clearly labeled data, Genie learns by identifying patterns and relationships on its own. This means it can process a wide range of internet videos to learn how to create games without being influenced by existing biases. This approach is key to providing a varied and engaging gaming experience.

Google Deepmind Genie world creator

Genie’s capabilities extend beyond learning. It can take images, sketches, and photos and transform them into virtual worlds that understand and replicate physical properties, such as depth. It can even learn to mimic behaviors from videos it has never seen before, showcasing its incredible adaptability.

Here are some other articles you may find of interest on the subject of generating AI artwork :

The AI’s performance is impressive. With minimal examples, Genie can replicate the gameplay of highly skilled players, a testament to its extensive parameters and the ability to scale with computational resources. Furthermore, Genie’s training includes robotics data, highlighting its potential in creating versatile AI agents.

As a foundational world model, Genie is at the forefront of AI systems that can generate and manage virtual environments. Its development marks a significant step forward in foundational world models and opens the door to more sophisticated AI applications in gaming, robotics, and beyond.

Google DeepMind’s Genie is a remarkable AI that does more than create games; it heralds a new era of artificial intelligence. Its capacity to produce an infinite number of playable 2D worlds from image prompts is a powerful demonstration of unsupervised learning’s capabilities. The progress of Genie is a clear indicator of the vast potential AI holds for transforming various industries and the exciting possibilities that lie ahead.

DeepMind’s Genie: A Leap in AI-Driven Game Creation

DeepMind’s Genie represents a significant leap in the field of artificial intelligence, particularly in the realm of game development. By harnessing the power of a neural network with 11 billion parameters, Genie can analyze and synthesize gaming environments with unprecedented complexity and variety. This neural network is a type of machine learning model designed to recognize patterns in large datasets, similar to the way the human brain operates. The sheer number of parameters indicates the model’s capacity to process and generate intricate details within the 2D worlds it creates, making each environment unique and engaging for players.

The technology behind Genie is not only about creating visually appealing worlds but also about understanding the underlying mechanics that make a game enjoyable and functional. By interpreting latent actions, which are the implicit decisions and movements within a game, Genie can construct playable worlds that respond to player interactions in a realistic and dynamic manner. This capability is crucial for developing games that are not only fun to look at but also offer a rich and interactive gaming experience.

Unsupervised Learning: The Engine Behind Genie’s Creativity

One of the most groundbreaking aspects of Genie is its reliance on unsupervised learning. This form of machine learning does not require labeled datasets, which are typically used to teach AI systems by providing examples with predefined outcomes. Instead, unsupervised learning algorithms identify patterns and relationships within the data on their own. This approach allows Genie to learn from a diverse array of internet videos, including gaming footage, without the need for explicit instructions or guidance. As a result, the AI can develop a broader understanding of game design principles and apply them in novel ways, free from the constraints of human bias.

The unsupervised learning approach is particularly advantageous for creating a wide variety of gaming experiences. Since Genie is not limited to a specific set of rules or styles, it can generate games that are not only unpredictable and original but also tailored to an extensive range of preferences and interests. This flexibility is key to keeping players engaged and ensuring that the gaming landscapes it creates are always fresh and exciting.

Implications for AI Development and Industry Applications

The development of Genie by Google DeepMind is more than just an advancement in gaming technology; it signifies a broader shift in the capabilities of AI systems. The ability to generate an endless array of 2D worlds from simple image prompts showcases the potential of AI to understand and recreate complex systems. This technology could have far-reaching implications beyond gaming, including advancements in robotics where AI agents need to navigate and interact with unpredictable environments.

Moreover, Genie’s proficiency in creating virtual worlds that accurately simulate physical properties and behaviors suggests that AI can achieve a higher level of understanding of the real world. This understanding is crucial for the development of artificial general intelligence (AGI), which aims to create AI systems that can perform any intellectual task that a human can. As foundational world models like Genie continue to evolve, they pave the way for more sophisticated AI applications that could revolutionize not only entertainment but also industries such as healthcare, transportation, and urban planning.

In summary, Google DeepMind’s Genie is a remarkable AI system that exemplifies the power of unsupervised learning and the potential for AI to innovate across various sectors. Its ability to create infinite, interactive gaming worlds from minimal input is a striking demonstration of the progress being made in artificial intelligence, and it hints at the transformative impact AI could have on our world in the years to come.

Filed Under: Gaming News, Technology News, Top News





Latest timeswonderful Deals

Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, timeswonderful may earn an affiliate commission. Learn about our Disclosure Policy.