正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Most evaluations of world models ask, "Does this look right?" 🌎 We built WorldModelGym to ask a different question: if an agent actually uses this model to make decisions, does it still choose well? 🏋️🏃‍♂️🏁🦾 A simulation can look physically plausible and still lead an agent completely astray. 📉⚠️... show more

Reka

20,262 subscribers

16,290 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Voice agents are awkward, and everyone notices: You ask a question. The agent thinks. You wait. And wait... Nobody wants this. I'd rather talk to a person. If your model's response time is over 300ms, you won't make it. Unfortunately, most text-to-speech models can't get anywhere close to that. I want you to take a look at the latest model released by Inworld AI: TTS-1.5. I built a simple voice agent using the model so you can see it in action and test it on your computer. You'll find the repository link below. The latency numbers of this model are wild: • Max model → under 250ms • Mini model → under 130ms That's 4x faster than prior generations and faster than human response times!

Voice agents are awkward, and everyone notices: You ask a question. The agent thinks. You wait. And wait... Nobody wants this. I'd rather talk to a person. If your model's response time is over 300ms, you won't make it. Unfortunately, most text-to-speech models can't get anywhere close to that. I want you to take a look at the latest model released by Inworld AI: TTS-1.5. I built a simple voice agent using the model so you can see it in action and test it on your computer. You'll find the repository link below. The latency numbers of this model are wild: • Max model → under 250ms • Mini model → under 130ms That's 4x faster than prior generations and faster than human response times!

Santiago

69,455 次观看 • 7 个月前

Agent sessions work well for focused tasks, but most real projects are too broad and complex for a single context window to hold. The more an agent sees, the less reliable it becomes. We built Missions to fix this.

Agent sessions work well for focused tasks, but most real projects are too broad and complex for a single context window to hold. The more an agent sees, the less reliable it becomes. We built Missions to fix this.

Factory

45,282 次观看 • 4 个月前

I built a whole sci-fi anime series: Exile Protocol, directing it inside invideo Agent One. In this masterclass, you'll learn how I developed the visual style of Exile Protocol, how I use Agent One's context system to manage an entire world of characters and locations, and how I take a single scene from concept to final edit. From worldbuilding and character design to animation and post-production, this is a look at how I direct an original anime series - and where the craft decisions actually get made. Make sure to subscribe and check out the show!

I built a whole sci-fi anime series: Exile Protocol, directing it inside invideo Agent One. In this masterclass, you'll learn how I developed the visual style of Exile Protocol, how I use Agent One's context system to manage an entire world of characters and locations, and how I take a single scene from concept to final edit. From worldbuilding and character design to animation and post-production, this is a look at how I direct an original anime series - and where the craft decisions actually get made. Make sure to subscribe and check out the show!

S.A.V

47,328 次观看 • 2 个月前

So what does Razorpay look like in the agentic era? We started with the basics at FTX’26. • onboarding handled by an AI agent (~3 mins) • integration created from a prompt (~2 mins) • d̶a̶s̶h̶b̶o̶a̶r̶d̶ just talk to an agent for everything The first agentic fintech platform. And we timed it live. Live Demo ↓ (More to come)

So what does Razorpay look like in the agentic era? We started with the basics at FTX’26. • onboarding handled by an AI agent (~3 mins) • integration created from a prompt (~2 mins) • d̶a̶s̶h̶b̶o̶a̶r̶d̶ just talk to an agent for everything The first agentic fintech platform. And we timed it live. Live Demo ↓ (More to come)

Harshil Mathur

82,010 次观看 • 5 个月前

When patients ask me "what does a stent look like?" I frequently say that it is similar to the spring found at the tip of a ball pen - just a bit more delicate. Usually works well as an explanation. #cardiotwitter European Society of Cardiology

When patients ask me "what does a stent look like?" I frequently say that it is similar to the spring found at the tip of a ball pen - just a bit more delicate. Usually works well as an explanation. #cardiotwitter European Society of Cardiology

Stephan Achenbach

33,460 次观看 • 1 年前

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.

Palantir

82,026 次观看 • 1 个月前

This is incredible I ask an AI agent to make me $10,000 It then did market research, built a business plan, and started executing on that plan Now ANYONE can use AI agents to build entire businesses for them autonomously (trust me, you want to bookmark this one)

This is incredible I ask an AI agent to make me $10,000 It then did market research, built a business plan, and started executing on that plan Now ANYONE can use AI agents to build entire businesses for them autonomously (trust me, you want to bookmark this one)

Alex Finn

135,437 次观看 • 1 年前

Today we introduced Gemini Enterprise, built with our most advanced Gemini models. It allows you to chat with your company’s documents, data and apps as well as build and deploy AI agents, all grounded in your information and context. Have a look at how it helps you build an agent for almost anything:

Today we introduced Gemini Enterprise, built with our most advanced Gemini models. It allows you to chat with your company’s documents, data and apps as well as build and deploy AI agents, all grounded in your information and context. Have a look at how it helps you build an agent for almost anything:

Sundar Pichai

1,105,854 次观看 • 10 个月前

Most people treat AI like Google: ask a question, get an answer. But what if AI could think *like/with you?* I reverse-engineer "Theory of Mind" to test if the model can form a "theory of my mind". Using AI as a mirror to understand myself by giving it personal context and seeing how well it can embody/reflect my expertise back to me helps me to evaluate the model's thinking. This is something like a single-user, multi-model human-AI synergy benchmark where the task is "strategic alignment with your own expertise." Here's my hypothesis: Does pre-loading context create emergent synergy and enhance collective intelligence? If the LLM has: - Your projects (what you've built) - Your career details (how you think about growth) - Your self-description (your values/philosophy) 1. Does this response sound like something I'd say? 2. Does it reveal blind spots I hadn't considered? 3. Does it reduce the "explanation tax" I pay in every conversation? Different models excel at different aspects of "me." Before you think I'm building a digital mirror to talk to myself: this isn't about AI companionship or AI psychosis. It's actually bout me understanding the model's reasoning so I can deploy the right model for the right task. I'm my own test subject because I have ground truth: I know what I actually think, what I'd actually decide, what I'd actually prioritize. Most benchmarks lack this. When a model says "Muratcan would choose X," I can immediately verify: "No, I'd choose Y because of Z." I think everyone should do this with their own domain expertise. - If you're a manager, load your case history and test which model best applies your reasoning. - If you're a creative, load your portfolio and test which model understands your aesthetic principles. - If you're a founder, load your strategy docs and test which model identifies blind spots in your go-to-market plan. AI should serve as an extension of your strategic thinking, a collaborative partner.

Most people treat AI like Google: ask a question, get an answer. But what if AI could think like/with you? I reverse-engineer "Theory of Mind" to test if the model can form a "theory of my mind". Using AI as a mirror to understand myself by giving it personal context and seeing how well it can embody/reflect my expertise back to me helps me to evaluate the model's thinking. This is something like a single-user, multi-model human-AI synergy benchmark where the task is "strategic alignment with your own expertise." Here's my hypothesis: Does pre-loading context create emergent synergy and enhance collective intelligence? If the LLM has: - Your projects (what you've built) - Your career details (how you think about growth) - Your self-description (your values/philosophy) 1. Does this response sound like something I'd say? 2. Does it reveal blind spots I hadn't considered? 3. Does it reduce the "explanation tax" I pay in every conversation? Different models excel at different aspects of "me." Before you think I'm building a digital mirror to talk to myself: this isn't about AI companionship or AI psychosis. It's actually bout me understanding the model's reasoning so I can deploy the right model for the right task. I'm my own test subject because I have ground truth: I know what I actually think, what I'd actually decide, what I'd actually prioritize. Most benchmarks lack this. When a model says "Muratcan would choose X," I can immediately verify: "No, I'd choose Y because of Z." I think everyone should do this with their own domain expertise. - If you're a manager, load your case history and test which model best applies your reasoning. - If you're a creative, load your portfolio and test which model understands your aesthetic principles. - If you're a founder, load your strategy docs and test which model identifies blind spots in your go-to-market plan. AI should serve as an extension of your strategic thinking, a collaborative partner.

Muratcan Koylan

24,128 次观看 • 8 个月前

You can now text an AI agent and it does the task inside the actual apps 🤯 It's called Airtap. No app to download. The conversation is the product. You can ask things like: - "Order an item from Amazon" - "See if Orangetheory has a 6am slot tomorrow" - "Post this photo to TikTok" Setup is one message. No download, no signup form. You can try Airtap Ai here:

You can now text an AI agent and it does the task inside the actual apps 🤯 It's called Airtap. No app to download. The conversation is the product. You can ask things like: - "Order an item from Amazon" - "See if Orangetheory has a 6am slot tomorrow" - "Post this photo to TikTok" Setup is one message. No download, no signup form. You can try Airtap Ai here:

Alvaro Cintas

99,458 次观看 • 1 个月前

“Why does Rome still matter for today? Well, I think when you look at it, as I said earlier, history doesn't repeat, but it does rhyme in a lot of ways. And I think if you understand patterns that happen in history, you can understand a lot of what's happening in your world today. Because I think we look at modern politics and we see the things that are happening, and we try to say, okay, well, if we just make this solution now, will it solve it? Centralization of power. Emergency authority becomes permanent. Rome had an oral constitution, and when a crisis arose, they would alter it to handle the crisis. But the problem is, once you do that, you don't go back.” Jeremy Ryan Slate

“Why does Rome still matter for today? Well, I think when you look at it, as I said earlier, history doesn't repeat, but it does rhyme in a lot of ways. And I think if you understand patterns that happen in history, you can understand a lot of what's happening in your world today. Because I think we look at modern politics and we see the things that are happening, and we try to say, okay, well, if we just make this solution now, will it solve it? Centralization of power. Emergency authority becomes permanent. Rome had an oral constitution, and when a crisis arose, they would alter it to handle the crisis. But the problem is, once you do that, you don't go back.” Jeremy Ryan Slate

Shawn Ryan

180,348 次观看 • 6 个月前

We ran an SLM fully on an Apple Watch! (the first watch app ever to ship intelligence built into it) My team is obsessed with the question "how small can models go and still be useful?" So Shahir trained a custom model which takes advantage of Apple's Neural Engine hidden inside every Apple Watch. Full autoregressive decoding, close to 30 TPS, ON YOUR WRIST (Series 9)!! 75MB package = 70M param model. Use-Cases? purposefully fine tuning this model to get personal context, health data, run a tiny agent agent for some automation etc. This is exactly what will we be doing next! "Watch out" :P (Also sabesh 📟 exploring alt career options as a hand model)

We ran an SLM fully on an Apple Watch! (the first watch app ever to ship intelligence built into it) My team is obsessed with the question "how small can models go and still be useful?" So Shahir trained a custom model which takes advantage of Apple's Neural Engine hidden inside every Apple Watch. Full autoregressive decoding, close to 30 TPS, ON YOUR WRIST (Series 9)!! 75MB package = 70M param model. Use-Cases? purposefully fine tuning this model to get personal context, health data, run a tiny agent agent for some automation etc. This is exactly what will we be doing next! "Watch out" :P (Also sabesh 📟 exploring alt career options as a hand model)

Kautuk | Conscious Engines

43,522 次观看 • 16 天前

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

Andrew Ng

105,343 次观看 • 1 年前

This Snow Isn’t Acting Normal. Watch Closely. ❄️👀 I recorded this video because it caught my attention. This is snow that is behaving differently than what most of us are used to seeing. I’m not here to jump to conclusions. I’m not here to tell you what to think. I am here to show you what I’m seeing and ask a simple question. Why does this look different than normal snow? That’s it. Sometimes the most important thing you can do is slow down and observe. Not argue. Not assume. Not let someone else tell you what you’re seeing. Just look. Ask questions. And think for yourself. Too many people rush to label curiosity as ignorance. Curiosity is how you learn. Critical thinking is how you stay grounded. If there’s a normal explanation, I’m open to it. If there isn’t, people should still be allowed to ask questions. That used to be normal. Watch the video. Draw your own conclusions. And don’t let anyone shame you for paying attention. 🫡🇺🇸 If you’ve seen something similar, comment and share your experience.

This Snow Isn’t Acting Normal. Watch Closely. ❄️👀 I recorded this video because it caught my attention. This is snow that is behaving differently than what most of us are used to seeing. I’m not here to jump to conclusions. I’m not here to tell you what to think. I am here to show you what I’m seeing and ask a simple question. Why does this look different than normal snow? That’s it. Sometimes the most important thing you can do is slow down and observe. Not argue. Not assume. Not let someone else tell you what you’re seeing. Just look. Ask questions. And think for yourself. Too many people rush to label curiosity as ignorance. Curiosity is how you learn. Critical thinking is how you stay grounded. If there’s a normal explanation, I’m open to it. If there isn’t, people should still be allowed to ask questions. That used to be normal. Watch the video. Draw your own conclusions. And don’t let anyone shame you for paying attention. 🫡🇺🇸 If you’ve seen something similar, comment and share your experience.

Ryan Nichols Sr.

577,054 次观看 • 7 个月前

IPO, IPO, IPO… yeah, it’s a big word at eToro right now! But what does it actually mean? Depends who you ask 👀 Here’s how our team defined it. Drop your own definition in the comments ⬇️ #eToroIPO #NasdaqListed ⚠️ This shall not constitute an offer, or the solicitation of an offer, to buy or sell these securities. Your capital is at risk.

IPO, IPO, IPO… yeah, it’s a big word at eToro right now! But what does it actually mean? Depends who you ask 👀 Here’s how our team defined it. Drop your own definition in the comments ⬇️ #eToroIPO #NasdaqListed ⚠️ This shall not constitute an offer, or the solicitation of an offer, to buy or sell these securities. Your capital is at risk.

eToro

1,726,184 次观看 • 1 年前

Most AI products added voice by wrapping a chatbot in speech-to-text. Vellum built a real-time voice loop on top of a full agent. It browses the web, reads your files, runs code, and sends messages while you’re still talking. This is voice as a real surface for an agent. Not a voice chatbot.

Most AI products added voice by wrapping a chatbot in speech-to-text. Vellum built a real-time voice loop on top of a full agent. It browses the web, reads your files, runs code, and sends messages while you’re still talking. This is voice as a real surface for an agent. Not a voice chatbot.

Kyronis

112,849 次观看 • 1 个月前

AAAAAAA This does an amazing job at showing how coyotes actually manipulate their voices to make the impression that there are more individuals than there actually are. The different pitches and sounds are impossible for most to distinguish from a distance as being 1 individual.

AAAAAAA This does an amazing job at showing how coyotes actually manipulate their voices to make the impression that there are more individuals than there actually are. The different pitches and sounds are impossible for most to distinguish from a distance as being 1 individual.

OnlyYotes

34,218 次观看 • 2 年前