Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

2nd Place - Pravah 🥈 Electrical grids are overwhelmed with data needed to manage complex operations. Pravah developed an agentic grid orchestration framework to intake multimodal data, analyze it, and coordinate response actions Mohak Mangal

OpenAI Developers

388,247 subscribers

128,599 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

FASHN AI parsa Eyal Shechtman Aleph @manim_community Surya 6/ Pravah Agentic grid orchestration for electric utilities Chat with grid data Mohak Mangal

FASHN AI parsa Eyal Shechtman Aleph @manim_community Surya 6/ Pravah Agentic grid orchestration for electric utilities Chat with grid data Mohak Mangal

Alex Reibman 🖇️

26,374 views • 1 year ago

I am excited to introduce OpenGeoAgent, a powerful open-source multimodal AI agent for automated geospatial analysis and visualization! It supports QGIS, Jupyter notebook, and Python scripting. In this tutorial, you’ll learn how to automate GIS workflows using natural language, generate maps, analyze satellite data, and even run complex hydrological models. You can even interact with the agent using voice commands (no typing needed). Video: GitHub: QGIS Plugin: #geospatial #GeoAgent #OpenSource #AI

I am excited to introduce OpenGeoAgent, a powerful open-source multimodal AI agent for automated geospatial analysis and visualization! It supports QGIS, Jupyter notebook, and Python scripting. In this tutorial, you’ll learn how to automate GIS workflows using natural language, generate maps, analyze satellite data, and even run complex hydrological models. You can even interact with the agent using voice commands (no typing needed). Video: GitHub: QGIS Plugin: #geospatial #GeoAgent #OpenSource #AI

Qiusheng Wu

62,401 views • 3 months ago

Every other chat I do now in cursor is to use an MCP to analyze my usage data. And it all started after I recorded this episode. This week on How I AI, Tim & Alexa at Faire show us how they analyze everything from experiment results to weird data anomalies with Cursor + various MCPs. We'll walk through - investigating a mysterious conversion rate drop across various data sources, including PRDs in Notion and code - programmatically creating Mode Analytics data visualizations via chat - defining agents to do repetitive tasks like writing eppo experiment reports After this ep, I realized I was massively underutilizing data MCPs and I hope you do, too. As always, a big thanks to our amazing sponsors! ⚡️ Zapier - the most connected AI orchestration platform (with a killer MCP I must add) 🤑 Brex - the intelligent finance platform built for founders

Every other chat I do now in cursor is to use an MCP to analyze my usage data. And it all started after I recorded this episode. This week on How I AI, Tim & Alexa at Faire show us how they analyze everything from experiment results to weird data anomalies with Cursor + various MCPs. We'll walk through - investigating a mysterious conversion rate drop across various data sources, including PRDs in Notion and code - programmatically creating Mode Analytics data visualizations via chat - defining agents to do repetitive tasks like writing eppo experiment reports After this ep, I realized I was massively underutilizing data MCPs and I hope you do, too. As always, a big thanks to our amazing sponsors! ⚡️ Zapier - the most connected AI orchestration platform (with a killer MCP I must add) 🤑 Brex - the intelligent finance platform built for founders

claire vo 🖤

22,942 views • 9 months ago

Scale alone is not enough for AI data. Quality and complexity are equally critical. Excited to support all of these for LLM developers with Snorkel AI Data-as-a-Service, and to share our new leaderboard! — Our decade-plus of research and work in AI data has a simple point: scale alone is not enough. AI success is all about the quality, complexity, and distribution of data—in addition to volume. We’re excited to be powering leading LLM developers with Snorkel AI Expert Data-as-a-Service, our white glove service for custom, expert-level AI datasets—and to now preview some of what we’re building via our new Expert Data Leaderboard (🔗 in 🧵) + upcoming OSS dataset releases! Snorkel Expert Data-as-a-Service is built to meet the rapidly evolving data needs of the agentic AI world—where success is built on the quality, complexity, and distribution of datasets, in addition to size and scale. This kind of high-quality, frontier AI data can only come from a union of technology and human expertise. With Snorkel Expert Data-as-a-Service, we’re powering frontier LLM developers across agentic, expert knowledge, reasoning, coding, multi-modal, and other task types via the combination of these two key components: - (1) The Snorkel Expert Network: A global team of subject matter experts focused wholly on specialized knowledge–spanning thousands of topics in STEM/academic, vertical/professional, and consumer/lifestyle domains. - (2) Snorkel AI Data Development Platform: Our unique programmatic data curation and quality control platform, accelerating and improving expert authoring and review through principled techniques developed over the last decade of R&D. Now: we’re incredibly excited to showcase some of the power of Snorkel Expert Data-as-a-Service via the new Snorkel Leaderboard—putting frontier models to the test in complex, agentic, and reasoning settings inspired by real industry scenarios (not esoteric puzzles)! We’ll be releasing new leaderboards and accompanying expert-verified open source datasets (coming soon!) regularly. To start, we’re sharing three initial ones in preview: - SnorkelFinance: Q&A over financial documents requiring agentic tool-calling and reasoning - SnorkelUnderwrite: Agentic insurance tasks requiring industry-specific reasoning and tool use - SnorkelSequences: Mathematical tasks requiring compositional multi-step reasoning

Scale alone is not enough for AI data. Quality and complexity are equally critical. Excited to support all of these for LLM developers with Snorkel AI Data-as-a-Service, and to share our new leaderboard! — Our decade-plus of research and work in AI data has a simple point: scale alone is not enough. AI success is all about the quality, complexity, and distribution of data—in addition to volume. We’re excited to be powering leading LLM developers with Snorkel AI Expert Data-as-a-Service, our white glove service for custom, expert-level AI datasets—and to now preview some of what we’re building via our new Expert Data Leaderboard (🔗 in 🧵) + upcoming OSS dataset releases! Snorkel Expert Data-as-a-Service is built to meet the rapidly evolving data needs of the agentic AI world—where success is built on the quality, complexity, and distribution of datasets, in addition to size and scale. This kind of high-quality, frontier AI data can only come from a union of technology and human expertise. With Snorkel Expert Data-as-a-Service, we’re powering frontier LLM developers across agentic, expert knowledge, reasoning, coding, multi-modal, and other task types via the combination of these two key components: - (1) The Snorkel Expert Network: A global team of subject matter experts focused wholly on specialized knowledge–spanning thousands of topics in STEM/academic, vertical/professional, and consumer/lifestyle domains. - (2) Snorkel AI Data Development Platform: Our unique programmatic data curation and quality control platform, accelerating and improving expert authoring and review through principled techniques developed over the last decade of R&D. Now: we’re incredibly excited to showcase some of the power of Snorkel Expert Data-as-a-Service via the new Snorkel Leaderboard—putting frontier models to the test in complex, agentic, and reasoning settings inspired by real industry scenarios (not esoteric puzzles)! We’ll be releasing new leaderboards and accompanying expert-verified open source datasets (coming soon!) regularly. To start, we’re sharing three initial ones in preview: - SnorkelFinance: Q&A over financial documents requiring agentic tool-calling and reasoning - SnorkelUnderwrite: Agentic insurance tasks requiring industry-specific reasoning and tool use - SnorkelSequences: Mathematical tasks requiring compositional multi-step reasoning

Alex Ratner

495,851 views • 1 year ago

‘pip install elysia’ and ‘elysia start’ That’s literally all it takes to get the most advanced open source agentic RAG app running on your data. We just released 𝗘𝗹𝘆𝘀𝗶𝗮, our open source, agentic RAG framework and an app so cool needed a cool video to go with it. Watch the full video: In the video, we go through these components of Elysia: 1️⃣ 𝗗𝗲𝗰𝗶𝘀𝗶𝗼𝗻 𝗧𝗿𝗲𝗲 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲: Instead of giving agents access to all tools at once, Elysia uses a pre-defined web of nodes with corresponding actions. Each decision agent has global context awareness. 2️⃣ 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗗𝗮𝘁𝗮 𝗗𝗶𝘀𝗽𝗹𝗮𝘆𝘀: Seven different data display formats including tables, e-commerce product cards, GitHub tickets, and charts. The system automatically choses the best display format. 3️⃣ 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗰 𝗗𝗮𝘁𝗮 𝗘𝘅𝗽𝗲𝗿𝘁𝗶𝘀𝗲: Unlike naive RAG systems that perform blind vector searches, Elysia analyzes your collections to understand data structure and meaning before performing queries. 𝗢𝘁𝗵𝗲𝗿 𝗖𝗼𝗼𝗹 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀: • 𝗙𝗲𝗲𝗱𝗯𝗮𝗰𝗸 𝗦𝘆𝘀𝘁𝗲𝗺: Uses positive examples as few-shot demonstrations for smaller, faster models • 𝗖𝗵𝘂𝗻𝗸-𝗢𝗻-𝗗𝗲𝗺𝗮𝗻𝗱: Dynamically chunks documents at query time instead of pre-chunking • 𝗠𝘂𝗹𝘁𝗶-𝗠𝗼𝗱𝗲𝗹 𝗦𝘁𝗿𝗮𝘁𝗲𝗴𝘆: Routes different tasks to appropriate model sizes based on complexity …And also how to get started with your own data! The entire project is open source and designed with customization in mind. You can use it as-is for effective data searching, or install the Python package to create custom tools for whatever agentic AI purposes you need. Big kudos to Edward for the vision, filming, and editing this masterpiece

‘pip install elysia’ and ‘elysia start’ That’s literally all it takes to get the most advanced open source agentic RAG app running on your data. We just released 𝗘𝗹𝘆𝘀𝗶𝗮, our open source, agentic RAG framework and an app so cool needed a cool video to go with it. Watch the full video: In the video, we go through these components of Elysia: 1️⃣ 𝗗𝗲𝗰𝗶𝘀𝗶𝗼𝗻 𝗧𝗿𝗲𝗲 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲: Instead of giving agents access to all tools at once, Elysia uses a pre-defined web of nodes with corresponding actions. Each decision agent has global context awareness. 2️⃣ 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗗𝗮𝘁𝗮 𝗗𝗶𝘀𝗽𝗹𝗮𝘆𝘀: Seven different data display formats including tables, e-commerce product cards, GitHub tickets, and charts. The system automatically choses the best display format. 3️⃣ 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗰 𝗗𝗮𝘁𝗮 𝗘𝘅𝗽𝗲𝗿𝘁𝗶𝘀𝗲: Unlike naive RAG systems that perform blind vector searches, Elysia analyzes your collections to understand data structure and meaning before performing queries. 𝗢𝘁𝗵𝗲𝗿 𝗖𝗼𝗼𝗹 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀: • 𝗙𝗲𝗲𝗱𝗯𝗮𝗰𝗸 𝗦𝘆𝘀𝘁𝗲𝗺: Uses positive examples as few-shot demonstrations for smaller, faster models • 𝗖𝗵𝘂𝗻𝗸-𝗢𝗻-𝗗𝗲𝗺𝗮𝗻𝗱: Dynamically chunks documents at query time instead of pre-chunking • 𝗠𝘂𝗹𝘁𝗶-𝗠𝗼𝗱𝗲𝗹 𝗦𝘁𝗿𝗮𝘁𝗲𝗴𝘆: Routes different tasks to appropriate model sizes based on complexity …And also how to get started with your own data! The entire project is open source and designed with customization in mind. You can use it as-is for effective data searching, or install the Python package to create custom tools for whatever agentic AI purposes you need. Big kudos to Edward for the vision, filming, and editing this masterpiece

Victoria Slocum

45,497 views • 11 months ago

Crazy... I just found a super cheap way to code with AI Tried GLM 4.5 on Claude Code and I’m really impressed! Prompt: “create an interactive python app where users can track, manage or analyze data” And, It came up with: • Dashboard - a clean interface to see all your data at a glance • Datasets - manage multiple collections of data easily • Data entries - add, edit, and organize your records without hassle • Analysis - get insights and summaries directly from your data What I observed: Everything worked smoothly, GLM 4.5 is definitely one of the best open-source models for coding, I’ll keep using it. Check it out now: And the best part: super affordable coding plans! • Lite - $3/month (promo). ~120 prompts every 5 hours. Works with Claude Code, Roo Code, Cline, Kilo Code, and more. • Pro - $15/month (promo). 5× more usage than Lite. Faster. Includes image/video tools and web search. • Max - $30/month (promo). 4× more usage than Pro. Guaranteed performance. Early access to new features. Bonus - Use my referral link to get an extra 10% off on top of these promo prices! Video demo 👇

Crazy... I just found a super cheap way to code with AI Tried GLM 4.5 on Claude Code and I’m really impressed! Prompt: “create an interactive python app where users can track, manage or analyze data” And, It came up with: • Dashboard - a clean interface to see all your data at a glance • Datasets - manage multiple collections of data easily • Data entries - add, edit, and organize your records without hassle • Analysis - get insights and summaries directly from your data What I observed: Everything worked smoothly, GLM 4.5 is definitely one of the best open-source models for coding, I’ll keep using it. Check it out now: And the best part: super affordable coding plans! • Lite - $3/month (promo). ~120 prompts every 5 hours. Works with Claude Code, Roo Code, Cline, Kilo Code, and more. • Pro - $15/month (promo). 5× more usage than Lite. Faster. Includes image/video tools and web search. • Max - $30/month (promo). 4× more usage than Pro. Guaranteed performance. Early access to new features. Bonus - Use my referral link to get an extra 10% off on top of these promo prices! Video demo 👇

Chidanand Tripathi

83,854 views • 10 months ago

Strategy CEO: How Do We Decide to Sell Bitcoin? Not an Impulsive Decision On June 19, 2026, Strategy CEO Phong Le Phong Le detailed the internal decision-making process behind selling 32 Bitcoins in an interview with Coinage. He stated that as a NASDAQ-listed company, their actions are never impulsive. The team maps out capital optionality quarterly, runs sophisticated financial models monthly to analyze equity and credit quality, and coordinates daily operations with Michael Saylor and the trading team. Furthermore, they use tools like Grok sentiment analysis on X to ensure every financial move is backed by rigorous data analytics.

Strategy CEO: How Do We Decide to Sell Bitcoin? Not an Impulsive Decision On June 19, 2026, Strategy CEO Phong Le Phong Le detailed the internal decision-making process behind selling 32 Bitcoins in an interview with Coinage. He stated that as a NASDAQ-listed company, their actions are never impulsive. The team maps out capital optionality quarterly, runs sophisticated financial models monthly to analyze equity and credit quality, and coordinates daily operations with Michael Saylor and the trading team. Furthermore, they use tools like Grok sentiment analysis on X to ensure every financial move is backed by rigorous data analytics.

Wu Blockchain

19,951 views • 1 month ago

This week, ML Scientist @dimid_ml shares an exciting update on the Theoriq Protocol. ⚡️ As MCP gains momentum in connecting AI models with external tools and data, our team has moved fast to integrate an MCP server directly into Theoriq’s SDK. This upgrade makes it easy for agents to register, manage, and update other agents on the protocol, laying the foundation for a more flexible and adaptable agentic ecosystem. More below.

This week, ML Scientist @dimid_ml shares an exciting update on the Theoriq Protocol. ⚡️ As MCP gains momentum in connecting AI models with external tools and data, our team has moved fast to integrate an MCP server directly into Theoriq’s SDK. This upgrade makes it easy for agents to register, manage, and update other agents on the protocol, laying the foundation for a more flexible and adaptable agentic ecosystem. More below.

Theoriq

82,463 views • 1 year ago

The next evolution of the OptimAI Core Node is coming, and it’s bringing one of our most powerful innovations yet: The Data Mining Agent. Become an OptimAI Node: 🔍 What is the Data Mining Agent? A fully autonomous agent running on your Core Node that: + Scans, retrieves, and indexes real-time public web data + Transforms raw information into actionable intelligence + Powers faster, smarter, adaptive Persona AI systems 💡 Why It Matters: Agentic AI is only as strong as the data it can access. Centralized APIs are slow, expensive, and limited. With the Core Node + Data Mining Agent, every contributor turns their desktop into a data supernode, accelerating AI evolution and giving our community a massive edge. ⚡ We’re not just building tools - we’re architecting the global backbone of Agentic AI, powered by you. Stay tuned for teasers, and get ready to upgrade your node. The future is decentralized. The future is agentic. And you are a key part of it. 💪 The more you contribute, the more you earn. Let’s BUIDL the future of AI together.

The next evolution of the OptimAI Core Node is coming, and it’s bringing one of our most powerful innovations yet: The Data Mining Agent. Become an OptimAI Node: 🔍 What is the Data Mining Agent? A fully autonomous agent running on your Core Node that: + Scans, retrieves, and indexes real-time public web data + Transforms raw information into actionable intelligence + Powers faster, smarter, adaptive Persona AI systems 💡 Why It Matters: Agentic AI is only as strong as the data it can access. Centralized APIs are slow, expensive, and limited. With the Core Node + Data Mining Agent, every contributor turns their desktop into a data supernode, accelerating AI evolution and giving our community a massive edge. ⚡ We’re not just building tools - we’re architecting the global backbone of Agentic AI, powered by you. Stay tuned for teasers, and get ready to upgrade your node. The future is decentralized. The future is agentic. And you are a key part of it. 💪 The more you contribute, the more you earn. Let’s BUIDL the future of AI together.

OptimAI Network

50,452 views • 11 months ago

Solidus Ai Tech Presents Agent Forge: Transforming AI Technology! Agent Forge is more than a platform—it's a revolution in how users interact with AI agents. Accessible to everyone, from seasoned professionals to newcomers, it empowers users to: 🔹Create Autonomous AI Agents: Automate processes, execute strategies, and stay ahead 24/7. 🔹 Gain Real-Time Insights: Stay informed with market updates via leading data platforms like CoinGecko and CoinMarketCap. 🔹 Simplify Complex Systems: Build automated workflows and manage digital strategies effortlessly, with no coding required. 🔹 Optimize Financial Management: Track data, optimize resources, and manage workflows with ease. 🔹 Breaking Barriers in AI Automation: Agent Forge makes advanced AI accessible to all, eliminating traditional technical challenges. 💡 Powered by AITECH HPC Data Center, Agent Forge ensures speed, security, and eco-friendly operations. 🗓 Coming Soon Agent Forge isn’t just a launch—it’s a leap forward.

Solidus Ai Tech Presents Agent Forge: Transforming AI Technology! Agent Forge is more than a platform—it's a revolution in how users interact with AI agents. Accessible to everyone, from seasoned professionals to newcomers, it empowers users to: 🔹Create Autonomous AI Agents: Automate processes, execute strategies, and stay ahead 24/7. 🔹 Gain Real-Time Insights: Stay informed with market updates via leading data platforms like CoinGecko and CoinMarketCap. 🔹 Simplify Complex Systems: Build automated workflows and manage digital strategies effortlessly, with no coding required. 🔹 Optimize Financial Management: Track data, optimize resources, and manage workflows with ease. 🔹 Breaking Barriers in AI Automation: Agent Forge makes advanced AI accessible to all, eliminating traditional technical challenges. 💡 Powered by AITECH HPC Data Center, Agent Forge ensures speed, security, and eco-friendly operations. 🗓 Coming Soon Agent Forge isn’t just a launch—it’s a leap forward.

AITECH CLOUD NETWORK

171,755 views • 1 year ago

We’ve partnered with OpenAI to release Sweetspot (YC S23) directly within ChatGPT. Any ChatGPT user can now search over federal contract data - no paid tools required and no Sweetspot subscription needed. We built this on ChatGPT because access to basic federal data shouldn't cost thousands of dollars a year. is public information, and using AI to find the right opportunities shouldn't be a privilege. For Sweetspot customers, it gets even better. You can pull opportunity data straight from ChatGPT and start up your full workflow (qualification, analysis, proposal response) inside Sweetspot. Even if you’re not in government contracting, check it out and share it with your colleagues who are. It’s completely free! Link below.

We’ve partnered with OpenAI to release Sweetspot (YC S23) directly within ChatGPT. Any ChatGPT user can now search over federal contract data - no paid tools required and no Sweetspot subscription needed. We built this on ChatGPT because access to basic federal data shouldn't cost thousands of dollars a year. is public information, and using AI to find the right opportunities shouldn't be a privilege. For Sweetspot customers, it gets even better. You can pull opportunity data straight from ChatGPT and start up your full workflow (qualification, analysis, proposal response) inside Sweetspot. Even if you’re not in government contracting, check it out and share it with your colleagues who are. It’s completely free! Link below.

sachin

38,465 views • 4 months ago

Crypto markets are stronger in numbers. This week, 717ai Terminal upgrade will include: - Profile creation, social links, and UX journey👤 - Leaderboards & community database📊 - Engagement metrics and rewards framework🏆 - Live Social Feed📺 - Prompt Interactions🔁 - Search Capabilities🔍 - Community Alpha Notifications📳 ALL of these upgrades make up a unique SocialFi framework. Enabling other AI Agents & builders to benefit from an easy plug-and-play model. - User data aggregation📊 - Mempool database and support; - Rewards framework for other communities; - Potential ad/partnership revenue (banner notifications); - Response Feedback; ALL of these framework benefits were designed to improve 717ai’s language model and refine social capabilities as Alpha subagents are developed. All while providing a fun and engaging way of rewarding $WIRE holders! Stay tuned👀

717ai

20,709 views • 1 year ago

For years, green groups have hailed electrification as a core climate solution. And now that we’re suddenly in the middle of historic load growth, they’re largely unprepared to meet the moment with big ideas. “We should all be embarrassed,” says Jane Flegal on this week's Open Circuit episode. For a long time, the climate community talked about aggressive electrification and the need to expand and modernize the grid. But now that future is arriving, the response has been fragmented or defensive. Some groups have leaned into affordability. Others are debating who should pay. And there are increasing calls for data center moratoriums. But there’s been very little thinking about how to plan and build at the scale this moment actually requires. "There's kind of like a rude awakening happening now, where everyone's like, ‘what was our plan to actually build?' she says. Jane has an idea. She proposes a new kind of grid infrastructure fund to bring hyperscalers, utilities, and policymakers into tighter coordination and to use demand as leverage to invest in the grid in a way that actually serves the public. Jigar Shah and I dug into the idea with her. We are mired in debates about grid-connected vs off-grid data centers, gas vs renewables, and who should pay for it all. But those debates are downstream of a bigger issue: we don’t have a system that can plan, coordinate, and build the grid for this era.

For years, green groups have hailed electrification as a core climate solution. And now that we’re suddenly in the middle of historic load growth, they’re largely unprepared to meet the moment with big ideas. “We should all be embarrassed,” says Jane Flegal on this week's Open Circuit episode. For a long time, the climate community talked about aggressive electrification and the need to expand and modernize the grid. But now that future is arriving, the response has been fragmented or defensive. Some groups have leaned into affordability. Others are debating who should pay. And there are increasing calls for data center moratoriums. But there’s been very little thinking about how to plan and build at the scale this moment actually requires. "There's kind of like a rude awakening happening now, where everyone's like, ‘what was our plan to actually build?' she says. Jane has an idea. She proposes a new kind of grid infrastructure fund to bring hyperscalers, utilities, and policymakers into tighter coordination and to use demand as leverage to invest in the grid in a way that actually serves the public. Jigar Shah and I dug into the idea with her. We are mired in debates about grid-connected vs off-grid data centers, gas vs renewables, and who should pay for it all. But those debates are downstream of a bigger issue: we don’t have a system that can plan, coordinate, and build the grid for this era.

Stephen Lacey

90,569 views • 4 months ago

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

The Humanoid Hub

11,575 views • 5 months ago

The future of automation at the Department of War 🇺🇸 has arrived. We are excited to announce the launch of Agent Designer, now available in first AI instance, Google Google Gemini. All 3 million Department of War personnel now have the power to create their own custom AI assistants to automate tasks and streamline complex workflows, with absolutely no coding experience needed. These custom agents can perform multi-step tasks, ingest various data sources, and be shared with teams for immediate deployment. Now, operators can automatically generate after-action reports, analysts can synthesize CUI images into memos, and comptrollers can build apps to analyze financial data. From logistics to strategy, Agent Designer empowers you to build the tools needed for increased efficiency. Several pre-built agents are already available in Gemini to address common workflows. An “AI-first” Department of War empowers the warfighter to address bigger problems, rather than being burdened by tedious tasks.

The future of automation at the Department of War 🇺🇸 has arrived. We are excited to announce the launch of Agent Designer, now available in first AI instance, Google Google Gemini. All 3 million Department of War personnel now have the power to create their own custom AI assistants to automate tasks and streamline complex workflows, with absolutely no coding experience needed. These custom agents can perform multi-step tasks, ingest various data sources, and be shared with teams for immediate deployment. Now, operators can automatically generate after-action reports, analysts can synthesize CUI images into memos, and comptrollers can build apps to analyze financial data. From logistics to strategy, Agent Designer empowers you to build the tools needed for increased efficiency. Several pre-built agents are already available in Gemini to address common workflows. An “AI-first” Department of War empowers the warfighter to address bigger problems, rather than being burdened by tedious tasks.

Department of War CTO

14,523 views • 5 months ago

How to setup a multi agent system? Bookmark it 📂 "The Trading Floor" Multi-Agent Market Analysis Council to analyze a stock ticker Z.ai GLM-4.7 🤝 OpenCode Agent framework: CrewAI How it works? 1. User enters a stock ticker to analyze 2. 5 AI agents wake up, each with distinct expertise: - Quant Analyst — technical indicators & price patterns - Sentiment Scout — market mood & crowd psychology - Macro Strategist — sector dynamics & economic context - Risk Manager — volatility, drawdowns & position sizing - Portfolio Chief — synthesizes all perspectives 3. Agents analyze independently using real market data 4. They debate, challenge assumptions, and identify disagreements 5. Portfolio Chief resolves conflicts and delivers a consensus recommendation 6. Final output: buy/hold/sell rating with confidence level, position size, and key risks How to built The Trading Floor? 1. Chose CrewAI as the agent framework — handles multi-agent orchestration out of the box 2. Defined 5 agents with distinct roles, goals, and backstories in Python 3. Built custom tools wrapping yfinance for real market data (prices, indicators, volatility) 4. Configured sequential workflow — specialists analyze first, Portfolio Chief synthesizes last 5. Set up FastAPI backend with SSE to stream agent thoughts in real-time 6. Built Next.js frontend to visualize the "board of directors" deliberating live 7. One environment variable (MODEL=openai/gpt-5.2) powers all agents 8. Generated unique agent icons with AI image tools Total cost: $0 for the framework, pay only for LLM API calls Tech stack: - GLM-4.7 with opencode to build the app - CrewAI (open source) for agent orchestration - GPT-5.2 powering each agent - FastAPI + SSE for real-time streaming - Next.js frontend showing live agent deliberations

How to setup a multi agent system? Bookmark it 📂 "The Trading Floor" Multi-Agent Market Analysis Council to analyze a stock ticker Z.ai GLM-4.7 🤝 OpenCode Agent framework: CrewAI How it works? 1. User enters a stock ticker to analyze 2. 5 AI agents wake up, each with distinct expertise: - Quant Analyst — technical indicators & price patterns - Sentiment Scout — market mood & crowd psychology - Macro Strategist — sector dynamics & economic context - Risk Manager — volatility, drawdowns & position sizing - Portfolio Chief — synthesizes all perspectives 3. Agents analyze independently using real market data 4. They debate, challenge assumptions, and identify disagreements 5. Portfolio Chief resolves conflicts and delivers a consensus recommendation 6. Final output: buy/hold/sell rating with confidence level, position size, and key risks How to built The Trading Floor? 1. Chose CrewAI as the agent framework — handles multi-agent orchestration out of the box 2. Defined 5 agents with distinct roles, goals, and backstories in Python 3. Built custom tools wrapping yfinance for real market data (prices, indicators, volatility) 4. Configured sequential workflow — specialists analyze first, Portfolio Chief synthesizes last 5. Set up FastAPI backend with SSE to stream agent thoughts in real-time 6. Built Next.js frontend to visualize the "board of directors" deliberating live 7. One environment variable (MODEL=openai/gpt-5.2) powers all agents 8. Generated unique agent icons with AI image tools Total cost: $0 for the framework, pay only for LLM API calls Tech stack: - GLM-4.7 with opencode to build the app - CrewAI (open source) for agent orchestration - GPT-5.2 powering each agent - FastAPI + SSE for real-time streaming - Next.js frontend showing live agent deliberations

CloudAI-X

58,189 views • 7 months ago

"President Bola Ahmed Tinubu's administration is implementing Nigeria's first comprehensive, data-driven national electrification plan, designed to provide electricity access to 17.5 million Nigerians through renewable energy solutions under the Distributed Access through Renewable Energy Scale-up (DARES) programme." - REA Boss, Abba Aliyu Update: - The Tinubu administration is implementing the Distributed Access through Renewable Energy Scale-up (DARES) programme, Nigeria's first structured nationwide electrification initiative targeting underserved communities. - The programme aims to provide electricity access to 17.5 million Nigerians through renewable energy solutions. - The initiative includes the deployment of 1,350 solar mini-grids, including 250 interconnected mini-grids. - Nigeria has now deployed over 1,000 mini-grids nationwide, marking the largest rollout of renewable energy mini-grids in the country's history. - Mini-grid projects are currently being implemented across multiple states, including Plateau, Adamawa, Kano, Anambra, the FCT, Kogi, Oyo, Lagos, Ondo, Bayelsa, Ebonyi, Yobe, and others. - In Plateau State, the REA recently performed the groundbreaking for 1.5 megawatts of mini-grid projects. - In Adamawa State, three interconnected mini-grids are being deployed to serve communities including Pufore and Saminaka. - In Anambra State, the REA is developing an 8.5-megawatt interconnected mini-grid for Oko Community. - In Kano State, the agency is deploying 10 megawatts of interconnected mini-grids across Bichi, Tarauni Civic Centre, Singer Market, and Dawakin Kudu. - In the Federal Capital Territory, close to 30 megawatts of interconnected mini-grids are being developed to serve Gwagwa I, Gwagwa II, Pegi, Dei-Dei, and Orozo. - Additional interconnected mini-grid projects are ongoing in Dekina, Anyigba I, Anyigba II, and Olamaboro in Kogi State, as well as communities in Oyo State. - The DARES programme is expected to be completed by the end of 2027, ahead of its original implementation timeline. - As part of implementation planning, the REA has digitally mapped more than 700,000 communities across Nigeria.

"President Bola Ahmed Tinubu's administration is implementing Nigeria's first comprehensive, data-driven national electrification plan, designed to provide electricity access to 17.5 million Nigerians through renewable energy solutions under the Distributed Access through Renewable Energy Scale-up (DARES) programme." - REA Boss, Abba Aliyu Update: - The Tinubu administration is implementing the Distributed Access through Renewable Energy Scale-up (DARES) programme, Nigeria's first structured nationwide electrification initiative targeting underserved communities. - The programme aims to provide electricity access to 17.5 million Nigerians through renewable energy solutions. - The initiative includes the deployment of 1,350 solar mini-grids, including 250 interconnected mini-grids. - Nigeria has now deployed over 1,000 mini-grids nationwide, marking the largest rollout of renewable energy mini-grids in the country's history. - Mini-grid projects are currently being implemented across multiple states, including Plateau, Adamawa, Kano, Anambra, the FCT, Kogi, Oyo, Lagos, Ondo, Bayelsa, Ebonyi, Yobe, and others. - In Plateau State, the REA recently performed the groundbreaking for 1.5 megawatts of mini-grid projects. - In Adamawa State, three interconnected mini-grids are being deployed to serve communities including Pufore and Saminaka. - In Anambra State, the REA is developing an 8.5-megawatt interconnected mini-grid for Oko Community. - In Kano State, the agency is deploying 10 megawatts of interconnected mini-grids across Bichi, Tarauni Civic Centre, Singer Market, and Dawakin Kudu. - In the Federal Capital Territory, close to 30 megawatts of interconnected mini-grids are being developed to serve Gwagwa I, Gwagwa II, Pegi, Dei-Dei, and Orozo. - Additional interconnected mini-grid projects are ongoing in Dekina, Anyigba I, Anyigba II, and Olamaboro in Kogi State, as well as communities in Oyo State. - The DARES programme is expected to be completed by the end of 2027, ahead of its original implementation timeline. - As part of implementation planning, the REA has digitally mapped more than 700,000 communities across Nigeria.

Daddy D.O🇳🇬

25,545 views • 18 days ago

⚡️We are excited to announce that our new no-code Enterprise Platform is NOW available in private beta! As RAG apps advance from prototype to production we’ve been overwhelmed by requests for an enterprise grade solution to provide these applications with the data they need. Designed to make it easy to get your data #RAGready, our Platform can preprocess more than 25 file types and soon will be fully #multimodal, also able to ingest audio, video and image files. We ship with a baseline suite of source connectors, including Amazon Web Services S3, Microsoft Azure Blob Storage, OneDrive, SFTP, Databricks Delta Table, Google Drive, Salesforce, Elastic, OpenSearch, and Google Cloud storage with many more fast following. Platform transforms your documents into a standardized JSON schema, broken down into semantically coherent elements allowing you to reconstruct your document in the manner most useful to you. Want only the narrative text but not the headers and footers? This is entirely configurable through the UI. Additionally, we generate more than 30 types of metadata for each element to make it easy to curate the data being written downstream and to support metadata filtering during retrieval. Smart chunking and the ability to choose from a range of embedding models are in from launch, delivering a turnkey solution for chunk and embedding experimentation. As for destination connectors, we've got that covered too, with Amazon Web Services S3, Pinecone, Chroma , Weaviate AI Database, Google Cloud storage, MongoDB, Microsoft Azure cognitive search, PostgreSQL, Elastic, OpenSearch, and Databricks Delta Table. And of course, all of this can be scheduled to keep your data continuously hydrated. The private-beta is live today! Sign-up to get access and come build the future of LLM data foundations with us: 🚀 #ETLforLLMs #AI #DataPreprocessing #DataScience #DataTransformation #LLMs #ETL #ML #PreppingData #MachineLearning #RAG #Engineer #Unstructured #Unstructuredio #RetrievalAugmentedGeneration #multimodal #AIJobs

⚡️We are excited to announce that our new no-code Enterprise Platform is NOW available in private beta! As RAG apps advance from prototype to production we’ve been overwhelmed by requests for an enterprise grade solution to provide these applications with the data they need. Designed to make it easy to get your data #RAGready, our Platform can preprocess more than 25 file types and soon will be fully #multimodal, also able to ingest audio, video and image files. We ship with a baseline suite of source connectors, including Amazon Web Services S3, Microsoft Azure Blob Storage, OneDrive, SFTP, Databricks Delta Table, Google Drive, Salesforce, Elastic, OpenSearch, and Google Cloud storage with many more fast following. Platform transforms your documents into a standardized JSON schema, broken down into semantically coherent elements allowing you to reconstruct your document in the manner most useful to you. Want only the narrative text but not the headers and footers? This is entirely configurable through the UI. Additionally, we generate more than 30 types of metadata for each element to make it easy to curate the data being written downstream and to support metadata filtering during retrieval. Smart chunking and the ability to choose from a range of embedding models are in from launch, delivering a turnkey solution for chunk and embedding experimentation. As for destination connectors, we've got that covered too, with Amazon Web Services S3, Pinecone, Chroma , Weaviate AI Database, Google Cloud storage, MongoDB, Microsoft Azure cognitive search, PostgreSQL, Elastic, OpenSearch, and Databricks Delta Table. And of course, all of this can be scheduled to keep your data continuously hydrated. The private-beta is live today! Sign-up to get access and come build the future of LLM data foundations with us: 🚀 #ETLforLLMs #AI #DataPreprocessing #DataScience #DataTransformation #LLMs #ETL #ML #PreppingData #MachineLearning #RAG #Engineer #Unstructured #Unstructuredio #RetrievalAugmentedGeneration #multimodal #AIJobs

Unstructured

21,874 views • 2 years ago

New course: Gemini CLI: Code & Create with an Open-Source Agent, built with Google Cloud Tech/Gemini CLI and taught by Jack Wotherspoon. Agentic coding assistants like Gemini CLI are transforming how developers work. This short course teaches you to use Google's open-source agent to coordinate local tools and cloud services for coding and non-coding workflows. Gemini CLI works from your terminal, so it works with your local files and development tools. You can also connect it to services through MCP. Then provide high-level instructions, and it autonomously plans and executes complex workflows. Skills you'll gain: - Build website features and automate code reviews with GitHub ActionsCreate data dashboards that combine local files with cloud data sources - Use MCP servers and extensions to orchestrate workflows across GitHub, Canva, and Google Workspace - Generate social media content from multimedia files like conference recordings I particularly appreciate that Gemini CLI is open-source. You can see exactly how it works, read the prompts it uses, and understand its architecture. The community has contributed thousands of pull requests. Since Gemini 3’s release I've found Gemini CLI highly capable - this is a tool worth having in your toolbox! Whether you're prototyping applications, automating workflows, or working with multimedia content, join to learn to delegate complex tasks and build faster:

New course: Gemini CLI: Code & Create with an Open-Source Agent, built with Google Cloud Tech/Gemini CLI and taught by Jack Wotherspoon. Agentic coding assistants like Gemini CLI are transforming how developers work. This short course teaches you to use Google's open-source agent to coordinate local tools and cloud services for coding and non-coding workflows. Gemini CLI works from your terminal, so it works with your local files and development tools. You can also connect it to services through MCP. Then provide high-level instructions, and it autonomously plans and executes complex workflows. Skills you'll gain: - Build website features and automate code reviews with GitHub ActionsCreate data dashboards that combine local files with cloud data sources - Use MCP servers and extensions to orchestrate workflows across GitHub, Canva, and Google Workspace - Generate social media content from multimedia files like conference recordings I particularly appreciate that Gemini CLI is open-source. You can see exactly how it works, read the prompts it uses, and understand its architecture. The community has contributed thousands of pull requests. Since Gemini 3’s release I've found Gemini CLI highly capable - this is a tool worth having in your toolbox! Whether you're prototyping applications, automating workflows, or working with multimedia content, join to learn to delegate complex tasks and build faster:

Andrew Ng

125,385 views • 6 months ago

To investigate further, we downloaded data showing confirmed smart city locations in the United States from the Global Covenant of Mayors and overlaid it with Erin Brockovich’s confirmed and community-reported data center locations. Texas was the first state we examined. And we superimposed aquifer maps onto the Texas data. What we found was revealing. Hyperscale data centers appear to be concentrated in areas with healthier aquifers, while areas with struggling aquifers show little to no smart city or data center activity. She then examined Georgia and Virginia and identified what appeared to be clusters or triangulations of data centers surrounding smart city locations. Texas displayed the same pattern. Major hyperscale data centers are being developed in places such as Odessa, the Panhandle, and Wichita Falls, locations that are outside major smart city zones. She emphasizes that hyperscale facilities also exist near smart cities, but argues that the pattern of placing many of them in already resource-strained rural regions suggests there may be another purpose behind their location. This leads to Maria’s theory: She argues that hyperscale data centers are being built in rural areas outside planned smart cities, even though smart cities appear to have their own clustered data infrastructure. These rural facilities consume water, increase electricity costs, create light and noise pollution, and gradually make rural communities less livable. As resources become scarcer, residents may be pushed toward urban areas where those resources are prioritized. We then turned our attention to the triangulation pattern seen around smart cities. To explain it, Maria introduces the concept of edge data centers. Edge data centers are smaller facilities located at the edge of a network. They often handle simple processing tasks while larger hyperscale facilities handle more complex workloads. Maria thinks it’s not a stretch to assume that these edge facilities may be operating alongside hyperscale facilities outside smart city networks.

To investigate further, we downloaded data showing confirmed smart city locations in the United States from the Global Covenant of Mayors and overlaid it with Erin Brockovich’s confirmed and community-reported data center locations. Texas was the first state we examined. And we superimposed aquifer maps onto the Texas data. What we found was revealing. Hyperscale data centers appear to be concentrated in areas with healthier aquifers, while areas with struggling aquifers show little to no smart city or data center activity. She then examined Georgia and Virginia and identified what appeared to be clusters or triangulations of data centers surrounding smart city locations. Texas displayed the same pattern. Major hyperscale data centers are being developed in places such as Odessa, the Panhandle, and Wichita Falls, locations that are outside major smart city zones. She emphasizes that hyperscale facilities also exist near smart cities, but argues that the pattern of placing many of them in already resource-strained rural regions suggests there may be another purpose behind their location. This leads to Maria’s theory: She argues that hyperscale data centers are being built in rural areas outside planned smart cities, even though smart cities appear to have their own clustered data infrastructure. These rural facilities consume water, increase electricity costs, create light and noise pollution, and gradually make rural communities less livable. As resources become scarcer, residents may be pushed toward urban areas where those resources are prioritized. We then turned our attention to the triangulation pattern seen around smart cities. To explain it, Maria introduces the concept of edge data centers. Edge data centers are smaller facilities located at the edge of a network. They often handle simple processing tasks while larger hyperscale facilities handle more complex workloads. Maria thinks it’s not a stretch to assume that these edge facilities may be operating alongside hyperscale facilities outside smart city networks.

The Vigilant Fox 🦊

16,783 views • 2 months ago