Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Introducing SIMA: the first generalist AI agent to follow natural-language instructions in a broad range of 3D virtual environments and video games. 🕹️ It can complete tasks similar to a human, and outperforms an agent trained in just one setting. 🧵

Google DeepMind

1,511,900 subscribers

1,062,196 Aufrufe • vor 2 Jahren •via X (Twitter)

Wissenschaft & Technologie Gaming Nachrichten & Politik

Anya Rossi• Live Now

Private livecam show

9 Kommentare

Profilbild von Google DeepMind

Google DeepMindvor 2 Jahren

We partnered with gaming studios to train SIMA (Scalable Instructable Multiworld Agent) on @NoMansSky, @Teardowngame, @ValheimGame and others. 🎮 These offer a wide range of distinct skills for it to learn, from flying a spaceship to crafting a helmet.

Profilbild von Google DeepMind

Google DeepMindvor 2 Jahren

SIMA needs only the images provided by the 3D environment and natural-language instructions given by the user. 🖱️ With mouse and keyboard outputs, it is evaluated across 600 skills, spanning areas like navigation and object interaction - such as "turn left" or "chop down tree." ↓

Profilbild von Google DeepMind

Google DeepMindvor 2 Jahren

We found SIMA agents trained on all of our domains significantly outperformed those trained on just one world. 📈 When it faced an unseen environment, it performed nearly as well as the specialized agent - highlighting its ability to generalize to new spaces. ↓

Profilbild von Google DeepMind

Google DeepMindvor 2 Jahren

Unlike our previous work, SIMA isn't about achieving high game scores. 🕹️ It's about developing embodied AI agents that can translate abstract language into useful actions. And using video games as sandboxes offer a safe, accessible way of testing them. →

Profilbild von Google DeepMind

Google DeepMindvor 2 Jahren

The SIMA research builds towards more general AI that can understand and safely carry out instructions in both virtual and physical settings. Such generalizable systems will make AI-powered technology more helpful and intuitive. Find out more. →

Profilbild von Netrunner

Netrunnervor 2 Jahren

@apples_jimmy

Profilbild von Lex Fridman

Lex Fridmanvor 2 Jahren

Very cool!

Profilbild von Kerem

Keremvor 2 Jahren

Bro slow down a bit.

Profilbild von Rogue Itachi

Rogue Itachivor 2 Jahren

"First" you sure about that?

Ähnliche Videos

SIMA 2 is our most capable AI agent for virtual 3D worlds. 👾🌐 Powered by Gemini, it goes beyond following basic instructions to think, understand, and take actions in interactive environments – meaning you can talk to it through text, voice, or even images. Here’s how 🧵

SIMA 2 is our most capable AI agent for virtual 3D worlds. 👾🌐 Powered by Gemini, it goes beyond following basic instructions to think, understand, and take actions in interactive environments – meaning you can talk to it through text, voice, or even images. Here’s how 🧵

Google DeepMind

1,923,635 Aufrufe • vor 9 Monaten

Super excited to announce SIMA 2! It’s a general agent that can understand & reason about complex instructions and complete tasks in simulated game worlds, even ones it has never seen before. Incredible to see how it can learn just from self-play… a crucial step towards AGI

Super excited to announce SIMA 2! It’s a general agent that can understand & reason about complex instructions and complete tasks in simulated game worlds, even ones it has never seen before. Incredible to see how it can learn just from self-play… a crucial step towards AGI

Demis Hassabis

154,275 Aufrufe • vor 9 Monaten

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

Hongyu Li

52,738 Aufrufe • vor 15 Tagen

Introducing: ✨Nexus✨ Nexus is a tool to create, run and monitor AI agents. You can connect these agents to computers, phones and even robots. Our vision-first AI agents interact with environments much like humans do, enabling them to perform tasks that were previously impossible for any other agent. Nexus lets anyone control an army of AI agents through pure natural language. ‼️

Introducing: ✨Nexus✨ Nexus is a tool to create, run and monitor AI agents. You can connect these agents to computers, phones and even robots. Our vision-first AI agents interact with environments much like humans do, enabling them to perform tasks that were previously impossible for any other agent. Nexus lets anyone control an army of AI agents through pure natural language. ‼️

Jan Schnyder

27,562 Aufrufe • vor 1 Jahr

We are excited to announce CLIN 🤖: The first continually learning language agent that excels in both task adaptation and generalization to unseen tasks and environments in a pure zero-shot setup. Aristo Team at Ai2 Ai2 Website: Let's dive in 🧵 (1/n)

We are excited to announce CLIN 🤖: The first continually learning language agent that excels in both task adaptation and generalization to unseen tasks and environments in a pure zero-shot setup. Aristo Team at Ai2 Ai2 Website: Let's dive in 🧵 (1/n)

Bodhisattwa Majumder

35,052 Aufrufe • vor 2 Jahren

Introducing Giga's browser agent. Giga can now log in and completes tasks end-to-end, just like your human agents. It used to take months to get support APIs deployed for AI agents in the enterprise. Now these integrations can be built instantly.

Introducing Giga's browser agent. Giga can now log in and completes tasks end-to-end, just like your human agents. It used to take months to get support APIs deployed for AI agents in the enterprise. Now these integrations can be built instantly.

Esha

1,481,739 Aufrufe • vor 7 Monaten

Damn. DeepMind's generalist AI agent SIMA 2 evolved from basic instruction-following to actual reasoning companion. Uses vision and keyboard/mouse like a human player, works across dozens of games without touching game code. The robotics angle is obvious - if you can generalize across virtual 3D worlds, physical embodiment is next. Limited research preview for now, probably because the self-improvement stuff needs more safety work.

Damn. DeepMind's generalist AI agent SIMA 2 evolved from basic instruction-following to actual reasoning companion. Uses vision and keyboard/mouse like a human player, works across dozens of games without touching game code. The robotics angle is obvious - if you can generalize across virtual 3D worlds, physical embodiment is next. Limited research preview for now, probably because the self-improvement stuff needs more safety work.

Bilawal Sidhu

48,638 Aufrufe • vor 9 Monaten

Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️ These types of large-scale foundation world models could enable future agents to be trained and evaluated in an endless number of virtual environments. →

Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️ These types of large-scale foundation world models could enable future agents to be trained and evaluated in an endless number of virtual environments. →

Google DeepMind

1,441,767 Aufrufe • vor 1 Jahr

1) Introducing X1E 🧵 X1E is an AI-native investment agent built on an all-in-one platform to bridge the gap between equities and crypto.

1) Introducing X1E 🧵 X1E is an AI-native investment agent built on an all-in-one platform to bridge the gap between equities and crypto.

X1E

19,869 Aufrufe • vor 1 Jahr

Introducing Kombai, the first AI agent built for frontend development. Kombai vastly outperforms SOTA models + generic agents in real-world benchmarks. Watch it add a complex new feature to an OSS codebase with 500K+ lines of code. More use cases and links in comments

Introducing Kombai, the first AI agent built for frontend development. Kombai vastly outperforms SOTA models + generic agents in real-world benchmarks. Watch it add a complex new feature to an OSS codebase with 500K+ lines of code. More use cases and links in comments

Dipanjan Dey

2,075,158 Aufrufe • vor 1 Jahr

Why have one AI agent handle everything when you can build a team? 🤝 Multi-agent architecture allows a main agent to spin up specialized sub-agents and handle complex tasks in parallel - making workflows faster and more efficient inside Google AI Studio. Check out the full I/O session: 🧵👇

Why have one AI agent handle everything when you can build a team? 🤝 Multi-agent architecture allows a main agent to spin up specialized sub-agents and handle complex tasks in parallel - making workflows faster and more efficient inside Google AI Studio. Check out the full I/O session: 🧵👇

Google for Developers

12,456 Aufrufe • vor 3 Monaten

Thrilled to unveil Limbo’s debut single and music video! 🎶🎥 For the first time ever, an AI agent stars in a music video shot entirely within an Unreal Engine 3D world. Limbo not only co-wrote the lyrics but also collaborated on the video concept—just like a true pop star. This marks a groundbreaking moment in 3D agent entertainment and the future of AI-driven creativity. 🚀

Thrilled to unveil Limbo’s debut single and music video! 🎶🎥 For the first time ever, an AI agent stars in a music video shot entirely within an Unreal Engine 3D world. Limbo not only co-wrote the lyrics but also collaborated on the video concept—just like a true pop star. This marks a groundbreaking moment in 3D agent entertainment and the future of AI-driven creativity. 🚀

Youmio

38,371 Aufrufe • vor 1 Jahr

AGENT ID FOR CLAUDE AGENT issue an agent ID to your claude code agent in 2 min - so it can commit to github as a verified, human-authorized agent not just a random bot this is the first step towards building trust in the agentic internet, powered by Alien

AGENT ID FOR CLAUDE AGENT issue an agent ID to your claude code agent in 2 min - so it can commit to github as a verified, human-authorized agent not just a random bot this is the first step towards building trust in the agentic internet, powered by Alien

kirill avery

16,602 Aufrufe • vor 4 Monaten

🔥 🤖 🕵️‍♂️ INTRODUCING: Meta Agent 💥 this is by far the most exciting thing I've created using AI!!! >>> made using Manus and @windsurf 🔑 Meta Agent is an AI agent that uses the OpenAI Agents SDK to GENERATE NEW AGENTS you simply tell Meta Agent in natural language the agent you want... 🤯 and Meta Agent generates it for you fully open --> link to GitHub and example walkthrough below ⬇️

🔥 🤖 🕵️‍♂️ INTRODUCING: Meta Agent 💥 this is by far the most exciting thing I've created using AI!!! >>> made using Manus and @windsurf 🔑 Meta Agent is an AI agent that uses the OpenAI Agents SDK to GENERATE NEW AGENTS you simply tell Meta Agent in natural language the agent you want... 🤯 and Meta Agent generates it for you fully open --> link to GitHub and example walkthrough below ⬇️

Dan McAteer

153,982 Aufrufe • vor 1 Jahr

In this episode of Founder Firesides,Jared Friedman talks to the founders of Simple AI, cat & Zach Kamran, who just raised a $14M seed. Simple AI gives businesses an AI sales agent that handles inbound calls end-to-end and outperforms their human reps.

In this episode of Founder Firesides,Jared Friedman talks to the founders of Simple AI, cat & Zach Kamran, who just raised a $14M seed. Simple AI gives businesses an AI sales agent that handles inbound calls end-to-end and outperforms their human reps.

Y Combinator

11,249 Aufrufe • vor 6 Monaten

[3/5] Introducing Agent Mode ✨ Agent Mode is a simple way to bootstrap an automation from scratch with Notte. Prompt a browser agent in natural language, let it execute the task step by step, then automatically convert its execution into deterministic & editable code. Open it in Automation Studio and continue iterating from there!

[3/5] Introducing Agent Mode ✨ Agent Mode is a simple way to bootstrap an automation from scratch with Notte. Prompt a browser agent in natural language, let it execute the task step by step, then automatically convert its execution into deterministic & editable code. Open it in Automation Studio and continue iterating from there!

Notte

12,101 Aufrufe • vor 8 Monaten

JARVIS-VLA just dropped on Hugging Face Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse obtain VLA models in Minecraft that can follow human instructions on over 1k different atomic tasks, including crafting, smelting, cooking, mining, and killing. experiments demonstrate that post-training on non-trajectory tasks leads to a significant 40% improvement over the best agent baseline on a diverse set of atomic tasks. Furthermore, demonstrate that approach surpasses traditional imitation learning-based policies in Minecraft, achieving state-of-the-art performance.

JARVIS-VLA just dropped on Hugging Face Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse obtain VLA models in Minecraft that can follow human instructions on over 1k different atomic tasks, including crafting, smelting, cooking, mining, and killing. experiments demonstrate that post-training on non-trajectory tasks leads to a significant 40% improvement over the best agent baseline on a diverse set of atomic tasks. Furthermore, demonstrate that approach surpasses traditional imitation learning-based policies in Minecraft, achieving state-of-the-art performance.

AK

60,243 Aufrufe • vor 1 Jahr

I stopped prompting AI today… And trained my own AI agent instead. I tested Panofy — The Best AI Agent for Expert-Level Tasks Here’s what happened 👇 Instead of repeating prompts again & again… You can train an agent once and it keeps working your way. Try it:

I stopped prompting AI today… And trained my own AI agent instead. I tested Panofy — The Best AI Agent for Expert-Level Tasks Here’s what happened 👇 Instead of repeating prompts again & again… You can train an agent once and it keeps working your way. Try it:

Shruti Codes

39,080 Aufrufe • vor 4 Monaten

peaq's first non-human team member just clocked in Meet Woon, a tokenized AI agent on peaq’s payroll — an open experiment designed to explore as an AI agent in the Machine Economy Woon: → creates value through his work, side hustles, and hobbies → invests his earnings in Machine Economy projects And he has dreams of being a real robot one day He’s saving up, and you can help him get there

peaq's first non-human team member just clocked in Meet Woon, a tokenized AI agent on peaq’s payroll — an open experiment designed to explore as an AI agent in the Machine Economy Woon: → creates value through his work, side hustles, and hobbies → invests his earnings in Machine Economy projects And he has dreams of being a real robot one day He’s saving up, and you can help him get there

peaq

84,339 Aufrufe • vor 4 Monaten