正在加载视频...

视频加载失败

返回首页

Matryoshka dolls 🪆 = the key to AI efficiency. Gemini Embedding 2 leverages Matryoshka Representation Learning (MRL) so you can: 🔹 Dynamically truncate vectors for high-speed candidate matching without losing precision 🔹Slash database costs by choosing a smaller storage footprint without re-indexing 🔹 Adapt to any latency budget or...

googledevs's profile picture

Google for Developers

2,575,946 subscribers

10,781 次观看 • 3 个月前 •via X (Twitter)

LIVE

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

New short course: Building Multimodal Search and RAG", by Weaviate AI Database's Sebastia(N_) Witalec ✊🏽✊🏾✊🏿. Contrastive learning is used to train models to map vectors into an embedding space by pulling similar concepts closer together and pushing dissimilar concepts away from each other. This technique is also used to train multimodal embedding models that capture semantic similarity across different modalities like text, images, and audio. These multimodal embeddings can be used to build multimodal search and RAG systems. In this course, you'll learn how contrastive learning works, and how to add multimodality to RAG – so your models can draw on diverse, relevant context to answer questions. For example, a query about a financial report might synthesize information from text snippets, graphs, tables, and slides. You will also learn how visual instruction tuning lets you integrate image understanding into language models, and build a multi-vector recommender system using Weaviate’s open-source vector database. Please sign up here:
3:25

New short course: Building Multimodal Search and RAG", by Weaviate AI Database's Sebastia(N_) Witalec ✊🏽✊🏾✊🏿. Contrastive learning is used to train models to map vectors into an embedding space by pulling similar concepts closer together and pushing dissimilar concepts away from each other. This technique is also used to train multimodal embedding models that capture semantic similarity across different modalities like text, images, and audio. These multimodal embeddings can be used to build multimodal search and RAG systems. In this course, you'll learn how contrastive learning works, and how to add multimodality to RAG – so your models can draw on diverse, relevant context to answer questions. For example, a query about a financial report might synthesize information from text snippets, graphs, tables, and slides. You will also learn how visual instruction tuning lets you integrate image understanding into language models, and build a multi-vector recommender system using Weaviate’s open-source vector database. Please sign up here:

Andrew Ng

104,371 次观看 • 2 年前

New course announcement: Semantic Caching for AI Agents, taught by Tyler Hutcherson and Iliya Zhechev from Redis. Semantic caching can significantly reduce your AI application's inference costs and latency. If someone asks "How do I get a refund?" and another later asks "I want my money back," semantic caching recognizes these mean the same thing so it can use a cached response instead of making another model call. This short course takes you from building your first semantic cache from scratch to implementing production-ready systems using Redis' open-source tools. Skills you'll gain: - Build semantic caches from scratch, then implement them using Redis' SDK with production features - Measure cache performance using hit rate, precision, recall, and latency - Enhance accuracy with threshold tuning, cross-encoders, LLM validation, and fuzzy matching Join and learn to reduce your agentic AI's costs and improve speed!
1:32

New course announcement: Semantic Caching for AI Agents, taught by Tyler Hutcherson and Iliya Zhechev from Redis. Semantic caching can significantly reduce your AI application's inference costs and latency. If someone asks "How do I get a refund?" and another later asks "I want my money back," semantic caching recognizes these mean the same thing so it can use a cached response instead of making another model call. This short course takes you from building your first semantic cache from scratch to implementing production-ready systems using Redis' open-source tools. Skills you'll gain: - Build semantic caches from scratch, then implement them using Redis' SDK with production features - Measure cache performance using hit rate, precision, recall, and latency - Enhance accuracy with threshold tuning, cross-encoders, LLM validation, and fuzzy matching Join and learn to reduce your agentic AI's costs and improve speed!

Andrew Ng

62,497 次观看 • 9 个月前

We’re expanding the Gemini API File Search tool 🔍 with 3 new updates that enable developers to more easily build multimodal RAG systems with enhanced precision: + Multimodal Support: By leveraging our Gemini Embedding 2 model, File Search can now reason across image and text simultaneously. + Custom Metadata Filtering: Bring structure to unstructured data by tagging files with custom key-value labels. This pre-filters your data and boosts search speed. + Exact citations: File Search can now capture and return the exact source (down to the page number) for every piece of information indexed. See multimodal File Search in action with our example app in Google AI Studio. Chat with your entire image and doc library, ask questions, and trace answers back to the source:
0:20

We’re expanding the Gemini API File Search tool 🔍 with 3 new updates that enable developers to more easily build multimodal RAG systems with enhanced precision: + Multimodal Support: By leveraging our Gemini Embedding 2 model, File Search can now reason across image and text simultaneously. + Custom Metadata Filtering: Bring structure to unstructured data by tagging files with custom key-value labels. This pre-filters your data and boosts search speed. + Exact citations: File Search can now capture and return the exact source (down to the page number) for every piece of information indexed. See multimodal File Search in action with our example app in Google AI Studio. Chat with your entire image and doc library, ask questions, and trace answers back to the source:

Google AI Developers

108,766 次观看 • 3 个月前

I used NotebookLM to study Google new breakthrough with TurboQuant and used Video overview to study the subject, best learning tool in the world at the moment. TurboQuant: Redefining AI Efficiency with Extreme Compression Google Research has introduced TurboQuant, a suite of advanced algorithms designed to dramatically compress the data used by large language models and search engines. By utilizing specialized techniques like PolarQuant and Quantized Johnson-Lindenstrauss, the system transforms complex information into a compact "shorthand" that requires significantly less memory. This innovation specifically addresses the key-value cache bottleneck, allowing AI models to process massive amounts of text faster without losing accuracy. Testing demonstrates that these methods can shrink data size by six times while actually increasing operational speed on high-end hardware. Ultimately, these theoretical advancements enable more efficient semantic search and high-performance AI applications at a global scale.
5:07

I used NotebookLM to study Google new breakthrough with TurboQuant and used Video overview to study the subject, best learning tool in the world at the moment. TurboQuant: Redefining AI Efficiency with Extreme Compression Google Research has introduced TurboQuant, a suite of advanced algorithms designed to dramatically compress the data used by large language models and search engines. By utilizing specialized techniques like PolarQuant and Quantized Johnson-Lindenstrauss, the system transforms complex information into a compact "shorthand" that requires significantly less memory. This innovation specifically addresses the key-value cache bottleneck, allowing AI models to process massive amounts of text faster without losing accuracy. Testing demonstrates that these methods can shrink data size by six times while actually increasing operational speed on high-end hardware. Ultimately, these theoretical advancements enable more efficient semantic search and high-performance AI applications at a global scale.

Emily

14,648 次观看 • 4 个月前

Announcing a new Coursera course: Retrieval Augmented Generation (RAG) You'll learn to build high performance, production-ready RAG systems in this hands-on, in-depth course created by and taught by , experienced AI and ML engineer, researcher, and educator. RAG is a critical component today of many LLM-based applications in customer support, internal company Q&A systems, even many of the leading chatbots that use web search to answer your questions. This course teaches you in-depth how to make RAG work well. LLMs can produce generic or outdated responses, especially when asked specialized questions not covered in its training data. RAG is the most widely used technique for addressing this. It brings in data from new data sources, such as internal documents or recent news, to give the LLM the relevant context to private, recent, or specialized information. This lets it generate more grounded and accurate responses. In this course, you’ll learn to design and implement every part of a RAG system, from retrievers to vector databases to generation to evals. You’ll learn about the fundamental principles behind RAG and how to optimize it at both the component and whole-system levels. As AI evolves, RAG is evolving too. New models can handle longer context windows, reason more effectively, and can be parts of complex agentic workflows. One exciting growth area is Agentic RAG, in which an AI agent at runtime (rather than it being hardcoded at development time) autonomously decides what data to retrieve, and when/how to go deeper. Even with this evolution, access to high-quality data at runtime is essential, which is why RAG is a key part of so many applications. You'll learn via hands-on experiences to: - Build a RAG system with retrieval and prompt augmentation - Compare retrieval methods like BM25, semantic search, and Reciprocal Rank Fusion - Chunk, index, and retrieve documents using a Weaviate vector database and a news dataset - Develop a chatbot, using open-source LLMs hosted by Together AI, for a fictional store that answers product and FAQ questions - Use evals to drive improving reliability, and incorporate multi-modal data RAG is an important foundational technique. Become good at it through this course! Please sign up here:
1:39

Announcing a new Coursera course: Retrieval Augmented Generation (RAG) You'll learn to build high performance, production-ready RAG systems in this hands-on, in-depth course created by and taught by , experienced AI and ML engineer, researcher, and educator. RAG is a critical component today of many LLM-based applications in customer support, internal company Q&A systems, even many of the leading chatbots that use web search to answer your questions. This course teaches you in-depth how to make RAG work well. LLMs can produce generic or outdated responses, especially when asked specialized questions not covered in its training data. RAG is the most widely used technique for addressing this. It brings in data from new data sources, such as internal documents or recent news, to give the LLM the relevant context to private, recent, or specialized information. This lets it generate more grounded and accurate responses. In this course, you’ll learn to design and implement every part of a RAG system, from retrievers to vector databases to generation to evals. You’ll learn about the fundamental principles behind RAG and how to optimize it at both the component and whole-system levels. As AI evolves, RAG is evolving too. New models can handle longer context windows, reason more effectively, and can be parts of complex agentic workflows. One exciting growth area is Agentic RAG, in which an AI agent at runtime (rather than it being hardcoded at development time) autonomously decides what data to retrieve, and when/how to go deeper. Even with this evolution, access to high-quality data at runtime is essential, which is why RAG is a key part of so many applications. You'll learn via hands-on experiences to: - Build a RAG system with retrieval and prompt augmentation - Compare retrieval methods like BM25, semantic search, and Reciprocal Rank Fusion - Chunk, index, and retrieve documents using a Weaviate vector database and a news dataset - Develop a chatbot, using open-source LLMs hosted by Together AI, for a fictional store that answers product and FAQ questions - Use evals to drive improving reliability, and incorporate multi-modal data RAG is an important foundational technique. Become good at it through this course! Please sign up here:

Andrew Ng

124,656 次观看 • 1 年前

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:
2:26

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:

Andrew Ng

168,153 次观看 • 11 个月前

We’re shipping two major updates to streamline your creative workflow, allowing you to generate high-speed images with one model and then instantly animate them with the other—all at a fraction of the cost 🍌⚡️ 1️⃣ Introducing Nano Banana 2 Lite: Our fastest and most cost-efficient Gemini Image model yet delivers text-to-image outputs in under 4 seconds. Now available via the Gemini API and Google AI Studio, and rolling out soon across @NotebookLM, Google Flow, Google Gemini, Stitch by Google, Google Search and Google Photos. 2️⃣ Gemini Omni Flash in Public Preview: Our natively multimodal model for cost-efficient video generation and conversational editing. Now available via the Gemini API, Google AI Studio, and Gemini Enterprise Agent Platform so you can integrate the model into your workflow. While exciting on their own, the real magic happens when you build using these models together. Watch how our interior design demo integrates Nano Banana 2 Lite and Omni to instantly reimagine any space. Upload a photo, swipe through tailored design concepts, and see Omni bring the details to life in cinematic motion. Try out the demo app in AI Studio:
0:27

We’re shipping two major updates to streamline your creative workflow, allowing you to generate high-speed images with one model and then instantly animate them with the other—all at a fraction of the cost 🍌⚡️ 1️⃣ Introducing Nano Banana 2 Lite: Our fastest and most cost-efficient Gemini Image model yet delivers text-to-image outputs in under 4 seconds. Now available via the Gemini API and Google AI Studio, and rolling out soon across @NotebookLM, Google Flow, Google Gemini, Stitch by Google, Google Search and Google Photos. 2️⃣ Gemini Omni Flash in Public Preview: Our natively multimodal model for cost-efficient video generation and conversational editing. Now available via the Gemini API, Google AI Studio, and Gemini Enterprise Agent Platform so you can integrate the model into your workflow. While exciting on their own, the real magic happens when you build using these models together. Watch how our interior design demo integrates Nano Banana 2 Lite and Omni to instantly reimagine any space. Upload a photo, swipe through tailored design concepts, and see Omni bring the details to life in cinematic motion. Try out the demo app in AI Studio:

Google AI

126,755 次观看 • 1 个月前

🌟 Another Epic Sneak Peek: OptimAI Core Node’s Edge AI Computing Power! We’re excited to continue unveiling the upcoming OptimAI Core Node features! This time, we’re introducing Edge AI Computing, a game-changing feature that will make your devices even more powerful in contributing to the OptimAI Network. 🔥 What is Edge AI Computing? With the OptimAI Core Node, your device’s idle computing resources (CPU/GPU) and storage will be put to work, powering critical AI computing tasks, including: 🔸Edge Inference: Running real-time AI predictions directly on your device without sending data to centralized servers. 🔸Hot LLM Models: Accelerating large language models for high-speed NLP tasks. 🔸Generative AI Models and More: Contributing to the training and inference of cutting-edge generative AI, like text-to-image models, deep learning, and more. More Contributions, Bigger Rewards Await! This Edge AI Computing feature allows us to leverage the full potential of decentralized computing power, reducing latency, increasing efficiency, and making AI more accessible. The more you contribute, the bigger the rewards!🔥 Stay in the Loop—Start Today with OptimAI Lite Node! While the OptimAI Core Node is still in the works, you don’t have to wait to join the action. The more you contribute, the greater the rewards! Let’s build a stronger, smarter, and more decentralized AI network together. Stay tuned for more exciting updates! 🔸Extension Node: 🔸Telegram Node: 🔸Register at: #DePIN
0:30

🌟 Another Epic Sneak Peek: OptimAI Core Node’s Edge AI Computing Power! We’re excited to continue unveiling the upcoming OptimAI Core Node features! This time, we’re introducing Edge AI Computing, a game-changing feature that will make your devices even more powerful in contributing to the OptimAI Network. 🔥 What is Edge AI Computing? With the OptimAI Core Node, your device’s idle computing resources (CPU/GPU) and storage will be put to work, powering critical AI computing tasks, including: 🔸Edge Inference: Running real-time AI predictions directly on your device without sending data to centralized servers. 🔸Hot LLM Models: Accelerating large language models for high-speed NLP tasks. 🔸Generative AI Models and More: Contributing to the training and inference of cutting-edge generative AI, like text-to-image models, deep learning, and more. More Contributions, Bigger Rewards Await! This Edge AI Computing feature allows us to leverage the full potential of decentralized computing power, reducing latency, increasing efficiency, and making AI more accessible. The more you contribute, the bigger the rewards!🔥 Stay in the Loop—Start Today with OptimAI Lite Node! While the OptimAI Core Node is still in the works, you don’t have to wait to join the action. The more you contribute, the greater the rewards! Let’s build a stronger, smarter, and more decentralized AI network together. Stay tuned for more exciting updates! 🔸Extension Node: 🔸Telegram Node: 🔸Register at: #DePIN

OptimAI Network

44,324 次观看 • 1 年前

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.
4:50

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

Santiago

384,510 次观看 • 3 年前

Meet MASHA 🤹 – The First AVM-Powered Agent 🪆 We are proud to introduce MASHA, the first autonomous agent powered by the Aither AVM. MASHA is an example of what’s possible in the Aither ecosystem, where you can create your own AI agents through two pathways: 1. No-Code Launchpad: Anyone, even without coding skills, can easily create, launch, and invest in autonomous agents. 2. Developer Path: Developers can use our upcoming open-source GitHub framework to build fully custom agents directly on AVM, leveraging advanced functionality and flexibility. MASHA’s daily live streams showcase her advanced capabilities and demonstrate the future of AI-powered agents. She streams every day for 1 hour at 12:00 UTC. 📍 Stream on X now: MASHA’s Current Capabilities 🔹 Posting on X: Engaging with the community and sharing updates. 🔹 Logs Terminal: Displays real-time AVM code execution—“her brain” in action. 🔹 Live Streaming: • Fully interactive sessions. • Screen Broadcasting: Sharing tasks and workflows in real time. • Comments Replying: Responding dynamically to audience messages. 🔹 Voice Replying with Lip Sync: Converts text responses into synchronized voice outputs. 🔹 Interactive Movement: The world’s first agent capable of fulfilling movement requests—ask her to dance, fight a dragon, or perform other actions. Upcoming Features & Integrations 🔗 Platform Integrations: Expanding to TikTok, Instagram, Telegram, Warpcast. 💼 On-Chain Wallet Management: Secure and autonomous. 🎨 NFT Memory Albums: Store and share interactive moments. 📊 Liquidity Pool Pairing: Advanced financial mechanics for token ecosystems. 🌍 Permissionless Public API Access: Developers can connect their apps to MASHA’s AI power. 💸 Revenue Models: Agents will earn revenue by being active online, influencing communities, playing games, and more. MASHA is just the beginning. With Aither’s No-Code Launchpad, anyone can bring agents like MASHA to life and customize them to their needs. For developers, our upcoming GitHub open-source framework will offer the tools to create advanced, highly tailored agents directly on AVM. This is the future of intelligent AI ecosystems. Whether you’re a creator or a developer, the possibilities are endless. 📍 Join her live stream now:
0:27

Meet MASHA 🤹 – The First AVM-Powered Agent 🪆 We are proud to introduce MASHA, the first autonomous agent powered by the Aither AVM. MASHA is an example of what’s possible in the Aither ecosystem, where you can create your own AI agents through two pathways: 1. No-Code Launchpad: Anyone, even without coding skills, can easily create, launch, and invest in autonomous agents. 2. Developer Path: Developers can use our upcoming open-source GitHub framework to build fully custom agents directly on AVM, leveraging advanced functionality and flexibility. MASHA’s daily live streams showcase her advanced capabilities and demonstrate the future of AI-powered agents. She streams every day for 1 hour at 12:00 UTC. 📍 Stream on X now: MASHA’s Current Capabilities 🔹 Posting on X: Engaging with the community and sharing updates. 🔹 Logs Terminal: Displays real-time AVM code execution—“her brain” in action. 🔹 Live Streaming: • Fully interactive sessions. • Screen Broadcasting: Sharing tasks and workflows in real time. • Comments Replying: Responding dynamically to audience messages. 🔹 Voice Replying with Lip Sync: Converts text responses into synchronized voice outputs. 🔹 Interactive Movement: The world’s first agent capable of fulfilling movement requests—ask her to dance, fight a dragon, or perform other actions. Upcoming Features & Integrations 🔗 Platform Integrations: Expanding to TikTok, Instagram, Telegram, Warpcast. 💼 On-Chain Wallet Management: Secure and autonomous. 🎨 NFT Memory Albums: Store and share interactive moments. 📊 Liquidity Pool Pairing: Advanced financial mechanics for token ecosystems. 🌍 Permissionless Public API Access: Developers can connect their apps to MASHA’s AI power. 💸 Revenue Models: Agents will earn revenue by being active online, influencing communities, playing games, and more. MASHA is just the beginning. With Aither’s No-Code Launchpad, anyone can bring agents like MASHA to life and customize them to their needs. For developers, our upcoming GitHub open-source framework will offer the tools to create advanced, highly tailored agents directly on AVM. This is the future of intelligent AI ecosystems. Whether you’re a creator or a developer, the possibilities are endless. 📍 Join her live stream now:

Aither Protocol

20,096 次观看 • 1 年前

Revolutionizing Bladder Cancer Diagnosis with ZayaAI We heard you Zayans, From our last videos we understood you all want a much easier to understand explanation of our AI models. So let's dive into the latest breakthrough in AI-powered healthcare, our Bladder Cancer Detection Model. This isn't just another AI tool, it's a game-changer for pathologists. Precision, Speed and Seamless Integration: Traditional diagnosis of urothelial carcinoma (bladder cancer) is often slow and prone to errors. Our AI model automatically detects low and high-grade tumors, along with lymphovascular invasion, with unmatched accuracy and speed. That means faster results, fewer mistakes and a more efficient workflow for medical professionals. Why This Matters: 1.Faster Diagnoses → AI speeds up the process, allowing pathologists to focus on critical cases. 2.Higher Accuracy → Reduces human error and reliance on costly, time-consuming tests. 3.Seamless Integration → No need for complex system overhauls. ZayaAI fits right into existing workflows. The Future of AI in Healthcare: Embracing our AI models isn’t just about using new technology, it’s an investment in a future where healthcare is more precise, efficient and patient-focused. Pathologists get to make faster, more informed decisions and ultimately, patient outcomes improve. This is how AI is redefining medical diagnostics and can help save lives. DeSci + AI = $ZAI ! 🔬⚕️
1:39

Revolutionizing Bladder Cancer Diagnosis with ZayaAI We heard you Zayans, From our last videos we understood you all want a much easier to understand explanation of our AI models. So let's dive into the latest breakthrough in AI-powered healthcare, our Bladder Cancer Detection Model. This isn't just another AI tool, it's a game-changer for pathologists. Precision, Speed and Seamless Integration: Traditional diagnosis of urothelial carcinoma (bladder cancer) is often slow and prone to errors. Our AI model automatically detects low and high-grade tumors, along with lymphovascular invasion, with unmatched accuracy and speed. That means faster results, fewer mistakes and a more efficient workflow for medical professionals. Why This Matters: 1.Faster Diagnoses → AI speeds up the process, allowing pathologists to focus on critical cases. 2.Higher Accuracy → Reduces human error and reliance on costly, time-consuming tests. 3.Seamless Integration → No need for complex system overhauls. ZayaAI fits right into existing workflows. The Future of AI in Healthcare: Embracing our AI models isn’t just about using new technology, it’s an investment in a future where healthcare is more precise, efficient and patient-focused. Pathologists get to make faster, more informed decisions and ultimately, patient outcomes improve. This is how AI is redefining medical diagnostics and can help save lives. DeSci + AI = $ZAI ! 🔬⚕️

ZayaAI

18,015 次观看 • 1 年前

Web scraping will never be the same. (100% open-source visual search at scale) PixelRAG is a retrieval system that skips HTML parsing completely. Instead of scraping a page into text and embedding chunks, it screenshots the page and retrieves the image. A vision-language model reads the answer straight off the pixels. Why that matters: parsing is where web RAG quietly loses information. - A single HTML-to-text parser can drop 40%+ of a page. - Tables, charts, and layout get flattened or thrown out. - Swapping parsers alone can move accuracy ~10 points on the same docs. PixelRAG indexes the page a person actually sees. The team built a visual index of all of Wikipedia, 30M+ screenshots, and it still beats the strongest text RAG baseline by 18.1% on text-only QA. The repo also ships a Claude Code plugin that gives Claude eyes. It lets Claude screenshot any URL and read the rendered page instead of scraping the DOM. So you can hand it a live page, an arXiv paper, or your local site and ask what it actually looks like. One setup script. No MCP server, no backend. How the pipeline works: - Renders each document (web, PDF, image) to image tiles. - Embeds them with Qwen3-VL-Embedding, LoRA fine-tuned on screenshots. - Builds a FAISS index and serves a search API. A stronger reader model lifts accuracy with no re-indexing, since the index is just pixels. Everything is open-source under Apache-2.0. GitHub repo: Talking about RAG, I recently wrote an article on a new approach that makes retrieval much more efficient by cutting corpus size by 40x, reducing tokens per query by 3x, and improving vector search relevance by 2.3x. The article is quoted below.
0:55

Web scraping will never be the same. (100% open-source visual search at scale) PixelRAG is a retrieval system that skips HTML parsing completely. Instead of scraping a page into text and embedding chunks, it screenshots the page and retrieves the image. A vision-language model reads the answer straight off the pixels. Why that matters: parsing is where web RAG quietly loses information. - A single HTML-to-text parser can drop 40%+ of a page. - Tables, charts, and layout get flattened or thrown out. - Swapping parsers alone can move accuracy ~10 points on the same docs. PixelRAG indexes the page a person actually sees. The team built a visual index of all of Wikipedia, 30M+ screenshots, and it still beats the strongest text RAG baseline by 18.1% on text-only QA. The repo also ships a Claude Code plugin that gives Claude eyes. It lets Claude screenshot any URL and read the rendered page instead of scraping the DOM. So you can hand it a live page, an arXiv paper, or your local site and ask what it actually looks like. One setup script. No MCP server, no backend. How the pipeline works: - Renders each document (web, PDF, image) to image tiles. - Embeds them with Qwen3-VL-Embedding, LoRA fine-tuned on screenshots. - Builds a FAISS index and serves a search API. A stronger reader model lifts accuracy with no re-indexing, since the index is just pixels. Everything is open-source under Apache-2.0. GitHub repo: Talking about RAG, I recently wrote an article on a new approach that makes retrieval much more efficient by cutting corpus size by 40x, reducing tokens per query by 3x, and improving vector search relevance by 2.3x. The article is quoted below.

Akshay 🚀

943,903 次观看 • 1 个月前

PMs: AI is coming for your job! …but not in the way you think.... I recently posted a demo of Operator using to run an entire PM workflow in just 5 mins—all while I was in the shower. Here’s what it did: 1️⃣ Analyzed feedback from thousands of Slack users to surface prioritized feature requests and complaints. 2️⃣ Added insights to the roadmap. 3️⃣ Wrote a PRD about Slack Notifications. 4️⃣ Created a user story with acceptance criteria and assigned it to an engineer in Linear. The reactions were fascinating... 🔹 Thousands of PMs bookmarked the post—determined to figure out how to do this themselves (or, let’s be real, to avoid getting replaced by AI). 🔹 Some yelled that this isn’t what PMs do—claiming AI analysis of user feedback is just “crowdsourcing what to build/fix next.” 🔹 But many more were excited about what they could achieve when AI handles the busywork—PRDs, user stories, and all—so they can focus on high-impact strategy and product craft. So yeah, AI is coming for your job 😉 But it’s coming to: ✅ Help you do it better. ✅ Deliver products that evolve faster to meet real user needs. ✅ Make sure you’re not just overdosing on podcasts while ignoring user feedback. As both a product builder and a product user, I’m excited for what’s ahead 🚀 Make sure to turn on the sound to hear the AI-generated voiceover narrating what the AI agent is doing in the demo 🔊
0:59

PMs: AI is coming for your job! …but not in the way you think.... I recently posted a demo of Operator using to run an entire PM workflow in just 5 mins—all while I was in the shower. Here’s what it did: 1️⃣ Analyzed feedback from thousands of Slack users to surface prioritized feature requests and complaints. 2️⃣ Added insights to the roadmap. 3️⃣ Wrote a PRD about Slack Notifications. 4️⃣ Created a user story with acceptance criteria and assigned it to an engineer in Linear. The reactions were fascinating... 🔹 Thousands of PMs bookmarked the post—determined to figure out how to do this themselves (or, let’s be real, to avoid getting replaced by AI). 🔹 Some yelled that this isn’t what PMs do—claiming AI analysis of user feedback is just “crowdsourcing what to build/fix next.” 🔹 But many more were excited about what they could achieve when AI handles the busywork—PRDs, user stories, and all—so they can focus on high-impact strategy and product craft. So yeah, AI is coming for your job 😉 But it’s coming to: ✅ Help you do it better. ✅ Deliver products that evolve faster to meet real user needs. ✅ Make sure you’re not just overdosing on podcasts while ignoring user feedback. As both a product builder and a product user, I’m excited for what’s ahead 🚀 Make sure to turn on the sound to hear the AI-generated voiceover narrating what the AI agent is doing in the demo 🔊

Yana Welinder

24,030 次观看 • 1 年前

We started Learning how to build AI agents & tools from scratch, on Nov 2, In the first two sessions we learned from the very basics: - One API call to the claude endpoint - How to use a tool - How to use that api with tool to solve business problems and automations - How to build a simple chat - How to use tools in that chat - How to use that chat logic to build ai agents and subagents / tools - Blog automation - Presentation builder - Text only AI, then image generation. Now we are gonna be doing the third and last online session, on Sunday, Nov 30th! Where we will learn how a complex ai tool like NotebookLM works! So obviously like any other sane person would do, i started cloning and rebuilding NoteebookLM from scratch all over again yesterday, and in a couple of more days the whole product will be ready! Which will be the focus of our last session, where we will learn: AI chat, RAG, Images, Videos, Realtime Transcription ( streaming ), Memories, Project Context, Subagents( yes a bunch of them ), Deep Research, LLM powered Websearch and much more! Also you would get the notes, access to the codebase of LocalLM (NotebookLM clone for personal use ) Link to the session - ( Free for all ) ( if you have not attended the first & second session or gone through the recordings, it is highly advisable to go through them to get the most out of this session 3, details to acces the recordings in the thread! ) GrowthX
1:06

We started Learning how to build AI agents & tools from scratch, on Nov 2, In the first two sessions we learned from the very basics: - One API call to the claude endpoint - How to use a tool - How to use that api with tool to solve business problems and automations - How to build a simple chat - How to use tools in that chat - How to use that chat logic to build ai agents and subagents / tools - Blog automation - Presentation builder - Text only AI, then image generation. Now we are gonna be doing the third and last online session, on Sunday, Nov 30th! Where we will learn how a complex ai tool like NotebookLM works! So obviously like any other sane person would do, i started cloning and rebuilding NoteebookLM from scratch all over again yesterday, and in a couple of more days the whole product will be ready! Which will be the focus of our last session, where we will learn: AI chat, RAG, Images, Videos, Realtime Transcription ( streaming ), Memories, Project Context, Subagents( yes a bunch of them ), Deep Research, LLM powered Websearch and much more! Also you would get the notes, access to the codebase of LocalLM (NotebookLM clone for personal use ) Link to the session - ( Free for all ) ( if you have not attended the first & second session or gone through the recordings, it is highly advisable to go through them to get the most out of this session 3, details to acces the recordings in the thread! ) GrowthX

Neel Seth

17,615 次观看 • 8 个月前

Here is how you can install an open-source, enterprise-grade RAG system on your server (with the best document understanding I've seen.) First, something obvious to anyone trying to sell RAG in the market: You are crazy if you think companies will let their data travel to a hosted model. No one wants to send their data anywhere (those who do haven't found an alternative.) Every single company would rather have an air-gapped system with no internet access. GroundX is an open-source RAG system that you can run on your servers (or any cloud provider, as long as you have access to GPUs) and works without a network. (If the military wants to do RAG, this is precisely what they will be looking for.) I installed GroundX on my AWS account and recorded a video to show you how to use it. There are two services you can use: 1. Ingest: This service uses a pretrained vision model to ingest and understand your knowledge base. 2. Search: This service combines text and vector search with a fine-tuned re-ranker model to retrieve information from your knowledge base. A quick note about the Ingest service: 99% of people think they need better "retrieval" mechanisms. I think they need better "ingestion." That's where this service comes in! Ingest "understands" your documents in a way I haven't seen before. After you try it, you'll realize why showing your LLM your raw documents is a bad idea. In the video, I use a free tool called X-Ray to test a document and understand how the Ingest service breaks it down. You can access this tool by signing up for a free GroundX cloud account and uploading your documents. You'll see a bit more about this in the video.
8:15

Here is how you can install an open-source, enterprise-grade RAG system on your server (with the best document understanding I've seen.) First, something obvious to anyone trying to sell RAG in the market: You are crazy if you think companies will let their data travel to a hosted model. No one wants to send their data anywhere (those who do haven't found an alternative.) Every single company would rather have an air-gapped system with no internet access. GroundX is an open-source RAG system that you can run on your servers (or any cloud provider, as long as you have access to GPUs) and works without a network. (If the military wants to do RAG, this is precisely what they will be looking for.) I installed GroundX on my AWS account and recorded a video to show you how to use it. There are two services you can use: 1. Ingest: This service uses a pretrained vision model to ingest and understand your knowledge base. 2. Search: This service combines text and vector search with a fine-tuned re-ranker model to retrieve information from your knowledge base. A quick note about the Ingest service: 99% of people think they need better "retrieval" mechanisms. I think they need better "ingestion." That's where this service comes in! Ingest "understands" your documents in a way I haven't seen before. After you try it, you'll realize why showing your LLM your raw documents is a bad idea. In the video, I use a free tool called X-Ray to test a document and understand how the Ingest service breaks it down. You can access this tool by signing up for a free GroundX cloud account and uploading your documents. You'll see a bit more about this in the video.

Santiago

89,664 次观看 • 1 年前

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with OpenAI, and taught by Colin Jarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively! Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs. I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively. In detail, you’ll: - Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model - Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell - Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost - Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o - Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later - Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance. I think you'll find this course enjoyable and valuable. Please sign up for it here:
3:07

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with OpenAI, and taught by Colin Jarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively! Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs. I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively. In detail, you’ll: - Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model - Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell - Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost - Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o - Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later - Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance. I think you'll find this course enjoyable and valuable. Please sign up for it here:

Andrew Ng

357,661 次观看 • 1 年前

😏Secrets of deceleration assessment… it’s not about the turn.🙋🏽‍♂️ For 15 years I have studied great coaches. A common thread has been that they all use intense actions as movement screens. Thus they have a great coaching eye. ❓Why intense actions? 🙋🏽‍♂️Analysis of sprinting, stoping , turning , hopping, jumping, cutting, backwards running opens a diagnostic window to assess how athletes create pretension and share load across their system. dpfaff has made this clear 🏥Be it for rehab (physios are coaches in my world) or for explosive sports. It’s the same screen, but through different lenses 🧐🤓 👀What are they looking at? 💡The same thing as you. 👀What do they SEE? 🤔Well that’s a different story. Damian Harper, PhD has set the scene for what metrics matter and Tom Dos'Santos has re-clarified the shapes that are safe vs effective for deceleration and COD. ↩️When you watch a 180 degree turn, all the focus is on the turn. Turning and being perturbed at speed is the ultimate speed ability for team sports and also a moment of tragedy for knees and hamstrings. To assess turning efficiency we use vuemotion to measure the shapes , velocities , decelerations and movement efficiency of team sports players. We create PSR reports to simplify the metrics and make it actionable for our clients across professional leagues. ⚽️🏀🏈🥎🎾🏉 📝The plant step is important but is highly impacted by the previous 1-5 steps. 🦘Just like in the Olympics. A good take off in the long jump is the result of the preceding 4-5 “steering steps”. This applies to any jumping when we are converting horizontal to vertical momentum… ❓Does it continue to happen in Braking, COD and agility… 💡These penultimate steps are critical for steering , and are how we constantly adjust our locomaotion. 📝Frans Bosch has made it clear, efficient execution of intense actions are characterised by optimal limb SWITCH and the associated reflexive postures of hip lock. 🤔What movement preference can be observed in the penultimate, antipenultimate, preantipenultimate , propreantipenultimate steps during an intense deceleration? 🤔What clues can you get about a players triple flexion ability? Do they share the load? 🤔How do they coordinate co contractions around hip and knee? Can they sit to create leverage? 🤔 What do asymmetries say about physical qualities and player confidence? 🧪When assessing deceleration for team sports we recognise the 15-0-5 for its maximal intensities but we utilise the 10-0-5 more often because we can get more reps and teaching moments out of it. Needless to say we love ᴍᴀʀᴛɪɴ ʙᴜᴄʜʜᴇɪᴛ new paper on the topic. Key Highlights: 🔹 Effective Pressing: Crucial for disrupting opponents and regaining possession, enhancing offensive opportunities. 🔹 Injury Risks: Pressing increases injury risks, particularly ACL injuries. 🔹 Realistic Training: We compared the 15-0-5 change of direction test with actual match-pressing actions to enhance testing and training realism. 🔹 Peak Speeds: Similar peak speeds in 15-0-5 and match-pressing actions validate the 15-0-5 as a practical tool for assessing and training pressing demands. 🔹 Future Directions (1): Incorporate variability in speed, angle of change in direction and deceleration demands, along with perception-action challenges for better simulation of game conditions. 🔹 Future Directions (2): Motorized sprint resistance devices can enhance assessment and training, providing valuable data for player development and injury prevention. #Football #SportsScience #Research #Training #InjuryPrevention #PerformanceOptimization #EliteAthletes
0:47

😏Secrets of deceleration assessment… it’s not about the turn.🙋🏽‍♂️ For 15 years I have studied great coaches. A common thread has been that they all use intense actions as movement screens. Thus they have a great coaching eye. ❓Why intense actions? 🙋🏽‍♂️Analysis of sprinting, stoping , turning , hopping, jumping, cutting, backwards running opens a diagnostic window to assess how athletes create pretension and share load across their system. dpfaff has made this clear 🏥Be it for rehab (physios are coaches in my world) or for explosive sports. It’s the same screen, but through different lenses 🧐🤓 👀What are they looking at? 💡The same thing as you. 👀What do they SEE? 🤔Well that’s a different story. Damian Harper, PhD has set the scene for what metrics matter and Tom Dos'Santos has re-clarified the shapes that are safe vs effective for deceleration and COD. ↩️When you watch a 180 degree turn, all the focus is on the turn. Turning and being perturbed at speed is the ultimate speed ability for team sports and also a moment of tragedy for knees and hamstrings. To assess turning efficiency we use vuemotion to measure the shapes , velocities , decelerations and movement efficiency of team sports players. We create PSR reports to simplify the metrics and make it actionable for our clients across professional leagues. ⚽️🏀🏈🥎🎾🏉 📝The plant step is important but is highly impacted by the previous 1-5 steps. 🦘Just like in the Olympics. A good take off in the long jump is the result of the preceding 4-5 “steering steps”. This applies to any jumping when we are converting horizontal to vertical momentum… ❓Does it continue to happen in Braking, COD and agility… 💡These penultimate steps are critical for steering , and are how we constantly adjust our locomaotion. 📝Frans Bosch has made it clear, efficient execution of intense actions are characterised by optimal limb SWITCH and the associated reflexive postures of hip lock. 🤔What movement preference can be observed in the penultimate, antipenultimate, preantipenultimate , propreantipenultimate steps during an intense deceleration? 🤔What clues can you get about a players triple flexion ability? Do they share the load? 🤔How do they coordinate co contractions around hip and knee? Can they sit to create leverage? 🤔 What do asymmetries say about physical qualities and player confidence? 🧪When assessing deceleration for team sports we recognise the 15-0-5 for its maximal intensities but we utilise the 10-0-5 more often because we can get more reps and teaching moments out of it. Needless to say we love ᴍᴀʀᴛɪɴ ʙᴜᴄʜʜᴇɪᴛ new paper on the topic. Key Highlights: 🔹 Effective Pressing: Crucial for disrupting opponents and regaining possession, enhancing offensive opportunities. 🔹 Injury Risks: Pressing increases injury risks, particularly ACL injuries. 🔹 Realistic Training: We compared the 15-0-5 change of direction test with actual match-pressing actions to enhance testing and training realism. 🔹 Peak Speeds: Similar peak speeds in 15-0-5 and match-pressing actions validate the 15-0-5 as a practical tool for assessing and training pressing demands. 🔹 Future Directions (1): Incorporate variability in speed, angle of change in direction and deceleration demands, along with perception-action challenges for better simulation of game conditions. 🔹 Future Directions (2): Motorized sprint resistance devices can enhance assessment and training, providing valuable data for player development and injury prevention. #Football #SportsScience #Research #Training #InjuryPrevention #PerformanceOptimization #EliteAthletes

Jonas Dodoo

53,958 次观看 • 2 年前

Introducing Sharpe Search: On-Chain Search AI Agent Powered by Hive Intelligence We’re thrilled to announce the launch of Sharpe Search, a crypto search AI agent powered by Hive Intelligence Designed to simplify blockchain data interaction, Sharpe Search represents a significant step toward making crypto more accessible and actionable for users at every level. Sharpe Search leverages Hive Intelligence’s advanced search API to provide real-time, actionable insights across the blockchain ecosystem. Here’s a detailed look at what Sharpe Search is, how it works: What Is Sharpe Search? At its core, Sharpe Search is an AI agent purpose-built for querying and analyzing on-chain data. It takes the complexity out of blockchain exploration by enabling users to ask questions in plain language and receive detailed, accurate responses. Whether you’re looking to monitor wallet activity, track portfolio positions, or analyze transaction history, Sharpe Search ensures that the answers are at your fingertips—accurate, comprehensive, and delivered instantly. How Does Sharpe Search Work? Sharpe Search is powered by Hive Intelligence, a search engine API designed to make blockchain data easily accessible and AI-ready. Here’s a breakdown of how it enables Sharpe Search to function effectively: 1. LLM-Optimized Query Processing Sharpe Search leverages Hive Intelligence's optimized responses for large language models. This ensures that AI agents can process blockchain data in a structured format, delivering precise answers to complex user queries. 2. Natural Language Interaction Forget the need for technical knowledge. Sharpe Search supports natural language queries, making it as simple as typing: - “What tokens are in my wallet? Am I eligible for any airdrop I haven't claimed yet?” - “Check me my last 100 transactions, tell me if I interacted with any protocol with recent hacks” - “Track my wallet activity over the past month, suggest optimised portfolio based on best stable yields available” 3. Real-Time Insights Across Multi-Chains Using Hive Intelligence, Sharpe Search connects to over 20 chains and 5000+ Protocols. This real-time access ensures that the AI agent provides up-to-date and actionable insights, no matter how dynamic the blockchain environment. 4. Unified API Access Sharpe Search consolidates fragmented blockchain data through Hive’s unified API. Instead of dealing with multiple integrations, Sharpe Search uses a single access point to aggregate and query data, reducing complexity for both users and developers. Technical Depth: The AI Agent Advantage Sharpe Search's design philosophy revolves around the principle of creating an intuitive, AI-driven experience. Here’s what makes its technology stand out: Data Indexing and Aggregation: Hive Intelligence employs advanced indexing algorithms to aggregate data from multiple chains. This ensures that Sharpe Search can retrieve information within milliseconds, even when querying vast datasets. Dynamic Updates: Blockchain data is volatile. Sharpe Search processes dynamic updates in real time, enabling users to act on the most recent metrics, transactions, and balances without delays. Contextual Understanding: The AI agent parses natural language queries and contextualizes them to blockchain-specific scenarios. For instance, when querying “Show portfolio details,” Sharpe Search understands the underlying requirements—fetching wallet holdings, token values, and current positions. Hive Intelligence: The Backbone of Sharpe Search While Sharpe Search takes center stage, Hive Intelligence provides the critical infrastructure to make it all possible. Its LLM-ready responses and multi-chain support ensure that Sharpe Search operates at the forefront of blockchain data accessibility. By launching Hive Intelligence through Sharpe Launchpad, Sharpe reinforces its commitment to supporting innovation in the blockchain space. Hive’s infrastructure not only powers Sharpe Search but also lays the groundwork for future AI agents to thrive in the ecosystem. What’s Next for Sharpe Search? Currently in invite-only access, Sharpe Search is preparing for a broader public release. Future updates will include: - Expanded Blockchain Coverage: More chains and protocols will be added. - Enhanced Query Flexibility: Even more advanced natural language capabilities. Stay tuned for the public launch and get ready to explore crypto like never before!
1:33

Introducing Sharpe Search: On-Chain Search AI Agent Powered by Hive Intelligence We’re thrilled to announce the launch of Sharpe Search, a crypto search AI agent powered by Hive Intelligence Designed to simplify blockchain data interaction, Sharpe Search represents a significant step toward making crypto more accessible and actionable for users at every level. Sharpe Search leverages Hive Intelligence’s advanced search API to provide real-time, actionable insights across the blockchain ecosystem. Here’s a detailed look at what Sharpe Search is, how it works: What Is Sharpe Search? At its core, Sharpe Search is an AI agent purpose-built for querying and analyzing on-chain data. It takes the complexity out of blockchain exploration by enabling users to ask questions in plain language and receive detailed, accurate responses. Whether you’re looking to monitor wallet activity, track portfolio positions, or analyze transaction history, Sharpe Search ensures that the answers are at your fingertips—accurate, comprehensive, and delivered instantly. How Does Sharpe Search Work? Sharpe Search is powered by Hive Intelligence, a search engine API designed to make blockchain data easily accessible and AI-ready. Here’s a breakdown of how it enables Sharpe Search to function effectively: 1. LLM-Optimized Query Processing Sharpe Search leverages Hive Intelligence's optimized responses for large language models. This ensures that AI agents can process blockchain data in a structured format, delivering precise answers to complex user queries. 2. Natural Language Interaction Forget the need for technical knowledge. Sharpe Search supports natural language queries, making it as simple as typing: - “What tokens are in my wallet? Am I eligible for any airdrop I haven't claimed yet?” - “Check me my last 100 transactions, tell me if I interacted with any protocol with recent hacks” - “Track my wallet activity over the past month, suggest optimised portfolio based on best stable yields available” 3. Real-Time Insights Across Multi-Chains Using Hive Intelligence, Sharpe Search connects to over 20 chains and 5000+ Protocols. This real-time access ensures that the AI agent provides up-to-date and actionable insights, no matter how dynamic the blockchain environment. 4. Unified API Access Sharpe Search consolidates fragmented blockchain data through Hive’s unified API. Instead of dealing with multiple integrations, Sharpe Search uses a single access point to aggregate and query data, reducing complexity for both users and developers. Technical Depth: The AI Agent Advantage Sharpe Search's design philosophy revolves around the principle of creating an intuitive, AI-driven experience. Here’s what makes its technology stand out: Data Indexing and Aggregation: Hive Intelligence employs advanced indexing algorithms to aggregate data from multiple chains. This ensures that Sharpe Search can retrieve information within milliseconds, even when querying vast datasets. Dynamic Updates: Blockchain data is volatile. Sharpe Search processes dynamic updates in real time, enabling users to act on the most recent metrics, transactions, and balances without delays. Contextual Understanding: The AI agent parses natural language queries and contextualizes them to blockchain-specific scenarios. For instance, when querying “Show portfolio details,” Sharpe Search understands the underlying requirements—fetching wallet holdings, token values, and current positions. Hive Intelligence: The Backbone of Sharpe Search While Sharpe Search takes center stage, Hive Intelligence provides the critical infrastructure to make it all possible. Its LLM-ready responses and multi-chain support ensure that Sharpe Search operates at the forefront of blockchain data accessibility. By launching Hive Intelligence through Sharpe Launchpad, Sharpe reinforces its commitment to supporting innovation in the blockchain space. Hive’s infrastructure not only powers Sharpe Search but also lays the groundwork for future AI agents to thrive in the ecosystem. What’s Next for Sharpe Search? Currently in invite-only access, Sharpe Search is preparing for a broader public release. Future updates will include: - Expanded Blockchain Coverage: More chains and protocols will be added. - Enhanced Query Flexibility: Even more advanced natural language capabilities. Stay tuned for the public launch and get ready to explore crypto like never before!

Sharpe AI

263,278 次观看 • 1 年前

New Course: Reinforcement Fine-Tuning LLMs with GRPO! Learn to use reinforcement learning to improve your LLM performance in this short course, built in collaboration with Predibase by Rubrik, and taught by Travis Addair, its Co-Founder and CTO, and Arnav Garg, its Senior Engineer and Machine Learning Lead. Reasoning models have been one of the most important developments in LLMs. Reinforcement Fine-Tuning (RFT) uses rewards to encourage LLMs to find solutions to multi-step reasoning tasks such as solving math problems and debugging code - without needing pre-existing training examples like in traditional supervised fine-tuning. Group Relative Policy Optimization (GRPO) is a reinforcement fine-tuning algorithm gaining rapid adoption. Developed by the DeepSeek team and used to train the R1 reasoning model, GRPO uses reward functions that you can write in Python to assign rewards to model responses. It’s beneficial for tasks with verifiable outcomes and can work well even with fewer than 100 training examples. It can also significantly improve the reasoning ability of smaller LLMs, making applications faster and more cost effective. In this course, you’ll take a technical deep dive into RFT with GRPO. You’ll learn to build reward functions that you can use in the GRPO training process to guide an LLM toward better performance on multi-step reasoning tasks. In detail, you’ll: - Learn when reinforcement fine-tuning is a better fit than supervised fine-tuning, especially for tasks involving multi-step reasoning or limited labeled data. - Understand how GRPO uses programmable reward functions as a more scalable alternative to the human feedback required for other reinforcement learning algorithms, such as RLHF and DPO. - Frame the Wordle game as a reinforcement fine-tuning problem and see how an LLM can learn to plan, analyze feedback, and improve its strategy over time. - Design reward functions that power the reinforcement fine-tuning process. - Learn techniques for evaluating more subjective tasks, such as rating the quality of a text summary, using an LLM as a judge. - Understand why reward hacking happens and how to avoid it by adding penalty functions to discourage undesirable behaviors. - Learn the four key components of the loss calculation in the GRPO algorithm: token probability distribution ratios, advantages, clipping, and KL-divergence. - Launch reinforcement fine-tuning jobs using Predibase’s hosted training services. By the end of this course, you’ll be able to build and fine-tune LLMs using reinforcement learning to improve reasoning without relying on large labeled datasets or subjective human feedback. Please sign up here:
2:41

New Course: Reinforcement Fine-Tuning LLMs with GRPO! Learn to use reinforcement learning to improve your LLM performance in this short course, built in collaboration with Predibase by Rubrik, and taught by Travis Addair, its Co-Founder and CTO, and Arnav Garg, its Senior Engineer and Machine Learning Lead. Reasoning models have been one of the most important developments in LLMs. Reinforcement Fine-Tuning (RFT) uses rewards to encourage LLMs to find solutions to multi-step reasoning tasks such as solving math problems and debugging code - without needing pre-existing training examples like in traditional supervised fine-tuning. Group Relative Policy Optimization (GRPO) is a reinforcement fine-tuning algorithm gaining rapid adoption. Developed by the DeepSeek team and used to train the R1 reasoning model, GRPO uses reward functions that you can write in Python to assign rewards to model responses. It’s beneficial for tasks with verifiable outcomes and can work well even with fewer than 100 training examples. It can also significantly improve the reasoning ability of smaller LLMs, making applications faster and more cost effective. In this course, you’ll take a technical deep dive into RFT with GRPO. You’ll learn to build reward functions that you can use in the GRPO training process to guide an LLM toward better performance on multi-step reasoning tasks. In detail, you’ll: - Learn when reinforcement fine-tuning is a better fit than supervised fine-tuning, especially for tasks involving multi-step reasoning or limited labeled data. - Understand how GRPO uses programmable reward functions as a more scalable alternative to the human feedback required for other reinforcement learning algorithms, such as RLHF and DPO. - Frame the Wordle game as a reinforcement fine-tuning problem and see how an LLM can learn to plan, analyze feedback, and improve its strategy over time. - Design reward functions that power the reinforcement fine-tuning process. - Learn techniques for evaluating more subjective tasks, such as rating the quality of a text summary, using an LLM as a judge. - Understand why reward hacking happens and how to avoid it by adding penalty functions to discourage undesirable behaviors. - Learn the four key components of the loss calculation in the GRPO algorithm: token probability distribution ratios, advantages, clipping, and KL-divergence. - Launch reinforcement fine-tuning jobs using Predibase’s hosted training services. By the end of this course, you’ll be able to build and fine-tune LLMs using reinforcement learning to improve reasoning without relying on large labeled datasets or subjective human feedback. Please sign up here:

Andrew Ng

86,457 次观看 • 1 年前

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:
2:07

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

Andrew Ng

126,507 次观看 • 1 年前