Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Everyone is building RAG applications, but nobody is talking about the data these systems use. You are delusional if you think clients will have their data sitting in a folder waiting for you to process it. Data is everywhere: in Google Drive, Dropbox, S3, Gmail, Slack, you name it.... And, of course, no sane developer wants to build connections to every one of these systems. This would be suicide. I'm working with Ragie, and they released Ragie Connect to solve this problem. First, their RAG system is top-notch (they have published how they do on several RAG benchmarks), and with Connect, they made it very simple to integrate client data without having to write any code. (Well, in reality, you still have to write a few lines, but it's minimal.) Instead of developing one-off integrations for Drive, Dropbox, etc, you can use Connect to integrate with all of them and let Ragie handle authentication, authorization, and automatic data synchronization. This is a huge time saver!show more

Santiago

452,346 subscribers

72,976 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & Teknoloji Eğitim

Anya Rossi• Live Now

Private livecam show

11 Yorum

Santiago profil fotoğrafı

Santiago1 yıl önce

Go to the link below to try Ragie Connect for free. It's as simple as making an API call and redirecting the user so they approve the integration.

Tembo - Multi-Workload Managed Postgres profil fotoğrafı

Tembo - Multi-Workload Managed Postgres2 yıl önce

The "data platform" status quo is vendor sprawl and data islands. Tembo Cloud can help you tame the sprawl and centralize your data using the full power of Postgres.

Petri Kuittinen profil fotoğrafı

Petri Kuittinen1 yıl önce

Obtaining the data is one thing, but curating and cleaning is another. A lot of companies and organizations have loads of legacy stuff, outdated documents, and lots of very similar or near identical data. Feeding all of that into a RAG system or LLM won't yield stellar results. Of course most AI "engineers" don't like the idea that they would need to do the dirty work to weed though this pile of half-rotten, partially contradicting and incorrect and outdated legacy data, but that is actually the hard part. Garbage In, Garbage Out (GIGO) is still true.

Santiago profil fotoğrafı

Santiago1 yıl önce

Yup, you are correct. I look at this in stages: First stage: let's use what you have. Usually, the results are better than nothing. This is a great starting point. Second stage: let's identify what data we need to improve to achieve better results. Third stage: let's do the improvements and iterate.

Albert Kozlowski profil fotoğrafı

Albert Kozlowski1 yıl önce

Thanks for the recommendation. I was looking for a solution that can connect with multiple data sources and auto-sync!

Santiago profil fotoğrafı

Santiago1 yıl önce

This should do it nicely.

Rodolpho Arruda profil fotoğrafı

Rodolpho Arruda1 yıl önce

Can I use it to connect to my Evernote account? I would like to ask questions to my entire document/notes inventory (~5000 items). For that, would I have to implement a web UI that connects to Ragie and allow me to pass queries?

Santiago profil fotoğrafı

Santiago1 yıl önce

I don't know if they support Evernote, but if you visit their home page, there's a list of every connector and a link to ask them for something specific. That might help.

Maria Khalusova profil fotoğrafı

Maria Khalusova1 yıl önce

No one? @UnstructuredIO has built 70+ connectors to data sources AND destinations, so you don't have to depend on RAG-in-a-box, but can use the data and build what YOU want.

CuratorX Anon profil fotoğrafı

CuratorX Anon1 yıl önce

Right! Thinking all data's in one folder is delusional . Integrating from Gmail, Dropbox, S3, etc., is vital for effective RAG apps. Streamlining this process is key.

Adam Small profil fotoğrafı

Adam Small1 yıl önce

Some customers prefer on premise. Does this do that?

Benzer Videolar

Web scraping is a critical skill, and yet nobody talks about it. How do you think companies are training their Large Language Models? Where do you think the data comes from? But web scraping goes beyond all of that. Imagine giving an AI agent access to any public online data in real time! I like to call this "web-scrapping on demand", and I'm pretty sure it's going to unlock unlimited power for AI applications. I recorded a quick video to show you how you can do this using Apify. I've talked about them before, and they are collaborating with me on this post. They have one of the best open-source web scraping and browser automation libraries out there: But it gets much better than this! You can use MCP to connect your AI Agents and applications to the Apify platform and use any specialized actor on demand to scrape and process online data. In the video, I used Cursor to scrape LinkedIn posts with the words "Machine Learning" in real time. Worked like a charm with no code needed! Here is a link to the platform: Think about this: You can now feed your AI applications with any public data on demand! We aren't ready for what's coming.

Web scraping is a critical skill, and yet nobody talks about it. How do you think companies are training their Large Language Models? Where do you think the data comes from? But web scraping goes beyond all of that. Imagine giving an AI agent access to any public online data in real time! I like to call this "web-scrapping on demand", and I'm pretty sure it's going to unlock unlimited power for AI applications. I recorded a quick video to show you how you can do this using Apify. I've talked about them before, and they are collaborating with me on this post. They have one of the best open-source web scraping and browser automation libraries out there: But it gets much better than this! You can use MCP to connect your AI Agents and applications to the Apify platform and use any specialized actor on demand to scrape and process online data. In the video, I used Cursor to scrape LinkedIn posts with the words "Machine Learning" in real time. Worked like a charm with no code needed! Here is a link to the platform: Think about this: You can now feed your AI applications with any public data on demand! We aren't ready for what's coming.

Santiago

101,473 görüntüleme • 1 yıl önce

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. 2. The connector ecosystem to load data from unstructured data sources is very immature. 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. The goal of a RAG Pipeline is to solve these problems. The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. At a high level, there are four different stages in the architecture of a RAG pipeline: 1. Ingestion: Here is where the pipeline loads the information from the data source. 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. 3. Transform: Where the pipeline chunks the data and generates document embeddings. 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. There are different rabbit holes at each one of these stages. Here are three of them: 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. If you have a few documents lying around, set up a free account and give it a try.

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. 2. The connector ecosystem to load data from unstructured data sources is very immature. 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. The goal of a RAG Pipeline is to solve these problems. The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. At a high level, there are four different stages in the architecture of a RAG pipeline: 1. Ingestion: Here is where the pipeline loads the information from the data source. 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. 3. Transform: Where the pipeline chunks the data and generates document embeddings. 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. There are different rabbit holes at each one of these stages. Here are three of them: 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. If you have a few documents lying around, set up a free account and give it a try.

Santiago

40,441 görüntüleme • 1 yıl önce

Why aren't more people talking about how difficult it is to turn documents into structured data? This is literally a problem that every single company I talk to is trying to solve. They have a buttload of documents with forms and tables, and they want to turn them into usable data. Let me show you how you can do this using Tensorlake. Probably the best parser I've found:

Why aren't more people talking about how difficult it is to turn documents into structured data? This is literally a problem that every single company I talk to is trying to solve. They have a buttload of documents with forms and tables, and they want to turn them into usable data. Let me show you how you can do this using Tensorlake. Probably the best parser I've found:

Santiago

46,413 görüntüleme • 1 yıl önce

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:

Santiago

125,928 görüntüleme • 9 ay önce

99% of AI applications are cool-looking demos. Impressive, but don't get fooled by the hype. It takes a lot to build enterprise-grade products that deliver real value. I have at least three weekly conversations with companies that want to use a Large Language Model with their data. The demand is huge! Here is one idea about what you can do to help. The use cases that most of these companies want to solve are similar: They have an extensive knowledge base and want to build a simple application that uses that information to answer questions. In other words, they need help building Retrieval Augmented Generation (RAG) applications they can use in many different scenarios: 1. To train new employees 2. To help their support team 3. To search old meetings and documents 4. To help with their research However, building these systems is not straightforward. Yes, there's a lot of information online, but there aren't enough people who know how to create solutions that work. Here is the idea: Today, you can build an enterprise-grade RAG application without writing code. A couple of MIT PhDs with 10+ years of experience building AI applications created . It's a no-code platform for building applications using Large Language Models. They are partnering with me on this post. You can use Stack AI to create, test, and deploy an end-to-end production-ready AI system. It's SOC-2, HIPAA, and GDPR compliant and offers SSO, role management, access control, and on-premise deployments. Of course, you can use the platform with any LLM on the market now. It's the whole nine yards for building AI applications. Check them out here: 2023 was about models. 2024 is about the tools using these models to build production-ready applications. That's where I'd start.

99% of AI applications are cool-looking demos. Impressive, but don't get fooled by the hype. It takes a lot to build enterprise-grade products that deliver real value. I have at least three weekly conversations with companies that want to use a Large Language Model with their data. The demand is huge! Here is one idea about what you can do to help. The use cases that most of these companies want to solve are similar: They have an extensive knowledge base and want to build a simple application that uses that information to answer questions. In other words, they need help building Retrieval Augmented Generation (RAG) applications they can use in many different scenarios: 1. To train new employees 2. To help their support team 3. To search old meetings and documents 4. To help with their research However, building these systems is not straightforward. Yes, there's a lot of information online, but there aren't enough people who know how to create solutions that work. Here is the idea: Today, you can build an enterprise-grade RAG application without writing code. A couple of MIT PhDs with 10+ years of experience building AI applications created . It's a no-code platform for building applications using Large Language Models. They are partnering with me on this post. You can use Stack AI to create, test, and deploy an end-to-end production-ready AI system. It's SOC-2, HIPAA, and GDPR compliant and offers SSO, role management, access control, and on-premise deployments. Of course, you can use the platform with any LLM on the market now. It's the whole nine yards for building AI applications. Check them out here: 2023 was about models. 2024 is about the tools using these models to build production-ready applications. That's where I'd start.

Santiago

197,675 görüntüleme • 2 yıl önce

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 Zain, 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:

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 Zain, 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

124,458 görüntüleme • 1 yıl önce

So here’s the deal, THE TREASURY DEPARTMENT DATA IS COMPROMISED. Actors without security clearance have been given access to scrape your data. Elon Musk now controls your data and it represents the same level of control exerted by the Chinese government’s social credit system. Musk is now able to profile every name on the treasury data systems. There is no way to sugar coat the fact that your data is no longer secure. It can now be used to target you and not for your benefit, be sure of that. Democrats and advocacy groups can take all the legal action they like, THE DATA IS COMPROMISED and you can’t put the genie back in the bottle. This data can now be used to literally social engineer services to target any perceived enemy of ‘the state’. Call me a conspiracy theorist if you like, but then sit back have a think if any of what I am suggesting is not possible. I analyse big data for a living and I have no solution to this problem and neither does any Democrat telling you it can be fixed.

𝔗𝔯𝔲𝔱𝔥 𝔐𝔞𝔱𝔱𝔢𝔯𝔰

16,366 görüntüleme • 1 yıl önce

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.

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

89,624 görüntüleme • 1 yıl önce

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!

Andrew Ng

244,284 görüntüleme • 2 yıl önce

I miss building simple, working software. At some point, we decided to complicate everything for no reason. Today, people can't build anything without using three frameworks, 17 libraries, and a swarm of microservices. And here is a funny paradox: To understand how these complex systems work, we've had to build systems and tools that generate data we can later analyze. But the more data we produce, the harder it is to process and make sense of it. We are in the middle of an observability crisis. The tools we have are inefficient, and we don't have enough people to keep systems running. A few weeks ago, I met the team Resolve AI, and they have built a fundamentally new approach to observability and incident management: Instead of depending on humans to run a system, Resolve built a Production Software Engineer who runs the system using AI while letting people supervise. And it's not only crazy, but I think this will fundamentally change how we monitor and maintain systems in production for years to come. I recorded a quick video to showcase a simple example of how Resolve works behind the scenes. There are two main things I'd like you to notice: 1. The tool can correlate data across logs, metrics, and traces coming from different systems. You don't have to do any work to get the information that matters right in front of you. 2. (This is the big one!) The tool can diagnose what's happening and give you instructions on how to solve it. It can produce causal relationships across the entire system stack. Resolve is backed by investors like Replit's founder Amjad Masad, Reid Hoffman, Jeff Dean, Fei Fei Li, Andy Price, among others. They are currently working with a select number of companies and want to onboard a few more. If you are interested in trying them out, go to this link: Honestly, this is one of the most impressive uses of AI I've seen.

I miss building simple, working software. At some point, we decided to complicate everything for no reason. Today, people can't build anything without using three frameworks, 17 libraries, and a swarm of microservices. And here is a funny paradox: To understand how these complex systems work, we've had to build systems and tools that generate data we can later analyze. But the more data we produce, the harder it is to process and make sense of it. We are in the middle of an observability crisis. The tools we have are inefficient, and we don't have enough people to keep systems running. A few weeks ago, I met the team Resolve AI, and they have built a fundamentally new approach to observability and incident management: Instead of depending on humans to run a system, Resolve built a Production Software Engineer who runs the system using AI while letting people supervise. And it's not only crazy, but I think this will fundamentally change how we monitor and maintain systems in production for years to come. I recorded a quick video to showcase a simple example of how Resolve works behind the scenes. There are two main things I'd like you to notice: 1. The tool can correlate data across logs, metrics, and traces coming from different systems. You don't have to do any work to get the information that matters right in front of you. 2. (This is the big one!) The tool can diagnose what's happening and give you instructions on how to solve it. It can produce causal relationships across the entire system stack. Resolve is backed by investors like Replit's founder Amjad Masad, Reid Hoffman, Jeff Dean, Fei Fei Li, Andy Price, among others. They are currently working with a select number of companies and want to onboard a few more. If you are interested in trying them out, go to this link: Honestly, this is one of the most impressive uses of AI I've seen.

Santiago

82,074 görüntüleme • 1 yıl önce

This is Anagha Rajesh. And she is crazy. She wants to store data in bacterial DNA. Her startup is called BioCompute. And last year, they actually did it. They stored data in DNA and retrieved it in their tiny lab in Bengaluru. This is a huge moment. But why is she even doing it? Because DNA is the ultimate storage tool available to us. Just 1 gm of DNA can store about 215 petabytes of data - that's like storing over 2 million movies in 4K. On top of that - this data can last for literally 1000s of years. Right now, they still need to figure out a way to make the reading and writing process faster and cheaper. But if BioCompute solves this problem - we could theoretically store all the data created in the world every year in the palm of our hands. And that would be insane. P.S. Check out this video from vyom going to Anagha's lab and actually doing it.

This is Anagha Rajesh. And she is crazy. She wants to store data in bacterial DNA. Her startup is called BioCompute. And last year, they actually did it. They stored data in DNA and retrieved it in their tiny lab in Bengaluru. This is a huge moment. But why is she even doing it? Because DNA is the ultimate storage tool available to us. Just 1 gm of DNA can store about 215 petabytes of data - that's like storing over 2 million movies in 4K. On top of that - this data can last for literally 1000s of years. Right now, they still need to figure out a way to make the reading and writing process faster and cheaper. But if BioCompute solves this problem - we could theoretically store all the data created in the world every year in the palm of our hands. And that would be insane. P.S. Check out this video from vyom going to Anagha's lab and actually doing it.

Varun Guru

253,113 görüntüleme • 1 ay önce

Tune Studio is an end-to-end platform for developing applications using Large Language Models. So far, I haven't seen any other platform like this one. You can do everything here: 1. You can curate your data. 2. Use the playground to play with different models and try your ideas. 3. Fine-tune an open-source model on your data. 4. Deploy the model when you are done. This is awesome for anyone building generative AI applications. You can use Tune Studio to work with any of the open-source models out there. They were one of the few companies to host Llama 2 and Llama 3 before anyone else. Here is a link to check it out: One of their main selling points is that Tune Studio scales! You don't have to worry about serving your model to lots of users. They also have built-in user management, authentication, on-prem support, user context management, and pretty much everything you need to build generative AI applications. Thanks to the Tune team for collaborating with me on this post. We are living through the best years of development tools for AI developers. The field is unstoppable.

Tune Studio is an end-to-end platform for developing applications using Large Language Models. So far, I haven't seen any other platform like this one. You can do everything here: 1. You can curate your data. 2. Use the playground to play with different models and try your ideas. 3. Fine-tune an open-source model on your data. 4. Deploy the model when you are done. This is awesome for anyone building generative AI applications. You can use Tune Studio to work with any of the open-source models out there. They were one of the few companies to host Llama 2 and Llama 3 before anyone else. Here is a link to check it out: One of their main selling points is that Tune Studio scales! You don't have to worry about serving your model to lots of users. They also have built-in user management, authentication, on-prem support, user context management, and pretty much everything you need to build generative AI applications. Thanks to the Tune team for collaborating with me on this post. We are living through the best years of development tools for AI developers. The field is unstoppable.

Santiago

39,101 görüntüleme • 2 yıl önce

David Friedberg says Anthropic asked big pharma for their data and nearly everyone said no "There's been an effort by Anthropic to sign up life sciences companies to contribute to a new life sciences focused model. They're approaching these large companies with large proprietary data sets and saying, if you share your data, we will give you early access, some sort of proprietary value. Sign this NDA and you can participate with us." "I think nearly everyone I've spoken with has woken up to the fact that they are trying to commoditize everyone's business. If all of the tens of billions of dollars you have invested in experiments and product development, and you've generated all of this proprietary data along the way, that data is a true asset of your organization. It's an asset that you've spent billions of dollars developing." "And by handing it over to a model company to then combine with other people's data, you are commoditizing the one core differentiation that you have. And so everyone is largely saying no." "I think what everyone's realizing is they're better off developing their own weights and their own models using either an open source basis or there might be some intermediary business model that evolves."

David Friedberg says Anthropic asked big pharma for their data and nearly everyone said no "There's been an effort by Anthropic to sign up life sciences companies to contribute to a new life sciences focused model. They're approaching these large companies with large proprietary data sets and saying, if you share your data, we will give you early access, some sort of proprietary value. Sign this NDA and you can participate with us." "I think nearly everyone I've spoken with has woken up to the fact that they are trying to commoditize everyone's business. If all of the tens of billions of dollars you have invested in experiments and product development, and you've generated all of this proprietary data along the way, that data is a true asset of your organization. It's an asset that you've spent billions of dollars developing." "And by handing it over to a model company to then combine with other people's data, you are commoditizing the one core differentiation that you have. And so everyone is largely saying no." "I think what everyone's realizing is they're better off developing their own weights and their own models using either an open source basis or there might be some intermediary business model that evolves."

dnap

282,289 görüntüleme • 14 gün önce

David Friedberg: Michael Burry’s Datacenter Math is Wrong “I actually think Michael Burberry's got this wrong.” “What Michael Burry is saying is that all of these hyperscalers have extended their depreciation schedule or the useful life of their data centers by roughly 2x, which cuts the operating costs in half when they report it in earnings. And so it's making their earnings inflate.” “So he's claiming they're cooking the books. Google first made this change in Q1 of 2021, where they said the servers are now going from 3 to 4 years. Separately in 2021, Google took networking equipment from 3 to 5 years. And then in 2023, they took it from 5 to 6 years.” “And so this is a result of this effort where they went in and did an analysis. So what happened?” “What happened in the data centers is that the data centers transitioned from being primarily data storage and data transfer systems, where you would use hard drives and RAM and memory to store data and then transmit it back out, to being data processing centers because of the AI boom.” “So as AI became more important in the data center, more of the dollars that are going into data centers were allocated towards chips from data storage, which initially was hard drives.” “And then suddenly, when you put these processors in to process the data to do AI, the majority of the spend and the majority of the energy is going towards the processors.” “I made some calls and I checked around with some other friends, and everyone says the same thing: that these 7-8 year old TPUs and GPUs that are sitting in the data centers are still being used and they're being used at 100% utilization.” “So that actually justifies and validates the depreciation schedule being much longer versus shorter.”

David Friedberg: Michael Burry’s Datacenter Math is Wrong “I actually think Michael Burberry's got this wrong.” “What Michael Burry is saying is that all of these hyperscalers have extended their depreciation schedule or the useful life of their data centers by roughly 2x, which cuts the operating costs in half when they report it in earnings. And so it's making their earnings inflate.” “So he's claiming they're cooking the books. Google first made this change in Q1 of 2021, where they said the servers are now going from 3 to 4 years. Separately in 2021, Google took networking equipment from 3 to 5 years. And then in 2023, they took it from 5 to 6 years.” “And so this is a result of this effort where they went in and did an analysis. So what happened?” “What happened in the data centers is that the data centers transitioned from being primarily data storage and data transfer systems, where you would use hard drives and RAM and memory to store data and then transmit it back out, to being data processing centers because of the AI boom.” “So as AI became more important in the data center, more of the dollars that are going into data centers were allocated towards chips from data storage, which initially was hard drives.” “And then suddenly, when you put these processors in to process the data to do AI, the majority of the spend and the majority of the energy is going towards the processors.” “I made some calls and I checked around with some other friends, and everyone says the same thing: that these 7-8 year old TPUs and GPUs that are sitting in the data centers are still being used and they're being used at 100% utilization.” “So that actually justifies and validates the depreciation schedule being much longer versus shorter.”

The All-In Podcast

304,297 görüntüleme • 8 ay önce

Today we're launching Amplitude MCP MCP was made for data analytics. Ask a vague question and have an AI model iteratively query Amplitude to find you insights. Amplitude MCP exposes all of Amplitude's functionality so an agent can interact with it directly. It allows you to use Amplitude without having to know anything about Amplitude's user interface or your data taxonomy. It uses the intelligence of off the shelf AI agents, including Claude, Gemini, and Cursor, to query Amplitude data you already have to find answers. It leverages all of your existing Amplitude data and how it's used to navigate through large complex behavioral datasets. You can have conversations about your product data directly inside any AI model with MCP. It can create Amplitude dashboards and notebooks with what it finds and even make recommendations. This is the best MCP use case I've ever seen. Watching an AI agent think, reason, query Amplitude, and then repeat that process iteratively is magical. See it in action:

Today we're launching Amplitude MCP MCP was made for data analytics. Ask a vague question and have an AI model iteratively query Amplitude to find you insights. Amplitude MCP exposes all of Amplitude's functionality so an agent can interact with it directly. It allows you to use Amplitude without having to know anything about Amplitude's user interface or your data taxonomy. It uses the intelligence of off the shelf AI agents, including Claude, Gemini, and Cursor, to query Amplitude data you already have to find answers. It leverages all of your existing Amplitude data and how it's used to navigate through large complex behavioral datasets. You can have conversations about your product data directly inside any AI model with MCP. It can create Amplitude dashboards and notebooks with what it finds and even make recommendations. This is the best MCP use case I've ever seen. Watching an AI agent think, reason, query Amplitude, and then repeat that process iteratively is magical. See it in action:

Spenser Skates

32,315 görüntüleme • 9 ay önce

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.

Aaron Levie

17,543 görüntüleme • 3 ay önce

Sen. Josh Hawley at NatCon 5 on AI and copyright theft: Americans should have the ability to defend their human data and their rights to that data against what is amounting to the largest copyright threat in the world. Many of you have online profiles and writings and creative productions that you care deeply about. It's your work, belongs to you. But get this: LLMs have already trained on enough copyrighted works to fill the Library of Congress 22 times over. As I look out across the room and see many authors, all of your works have already been taken. Did they consult you? I doubt it. Did they compensate you? Of course not. This is wrong. This is dangerous. We should empower human beings to protect the very human data that they create. -Assign property rights to specific forms of data. -Create legal liability for the companies who use that data. -Fully repeal Second 230. Open the courtroom doors. Allow people who have their rights taken away to sue, including suing companies and actors and individuals who use AI.

Sen. Josh Hawley at NatCon 5 on AI and copyright theft: Americans should have the ability to defend their human data and their rights to that data against what is amounting to the largest copyright threat in the world. Many of you have online profiles and writings and creative productions that you care deeply about. It's your work, belongs to you. But get this: LLMs have already trained on enough copyrighted works to fill the Library of Congress 22 times over. As I look out across the room and see many authors, all of your works have already been taken. Did they consult you? I doubt it. Did they compensate you? Of course not. This is wrong. This is dangerous. We should empower human beings to protect the very human data that they create. -Assign property rights to specific forms of data. -Create legal liability for the companies who use that data. -Fully repeal Second 230. Open the courtroom doors. Allow people who have their rights taken away to sue, including suing companies and actors and individuals who use AI.

National Conservatism

26,004 görüntüleme • 10 ay önce

The OFFICIAL preview with Erin Brockovich “Some data centers can use up to 30 million gallons of water a day. They’re utilizing water from aquifers and municipal waters, and people with their own wells are reporting that their wells are running dry. They’re having to dig deeper because of these mass amounts of water that these data centers require to stay cool. Communities can handle the truth. They will ask questions, they will sit at the table, and they will work with you. But they can never, ever handle the lie. There was no community input on this. You slid it under the table. You did it in the dark of the night. We didn’t even have a chance. We didn’t even have a voice.”

The OFFICIAL preview with Erin Brockovich “Some data centers can use up to 30 million gallons of water a day. They’re utilizing water from aquifers and municipal waters, and people with their own wells are reporting that their wells are running dry. They’re having to dig deeper because of these mass amounts of water that these data centers require to stay cool. Communities can handle the truth. They will ask questions, they will sit at the table, and they will work with you. But they can never, ever handle the lie. There was no community input on this. You slid it under the table. You did it in the dark of the night. We didn’t even have a chance. We didn’t even have a voice.”

Shawn Ryan

407,105 görüntüleme • 6 gün önce

Data preprocessing is critical for building effective RAG systems. Our new short course, Preprocessing Unstructured Data for LLM Applications, taught by Matt Robinson of Unstructured, demonstrates important but sometimes overlooked aspects of RAG systems: - How to extract and normalize content from diverse formats like PDF, Powerpoint, and HTML to expand your LLM's knowledge - Enriching data with metadata to enable more powerful retrieval and reasoning - Applying document layout analysis and vision transforms to process embedded images and tables Then you’ll use all these skills and build a RAG bot that draws from a corpus that includes PDF, PowerPoint, and Markdown documents. Please sign up here:

Data preprocessing is critical for building effective RAG systems. Our new short course, Preprocessing Unstructured Data for LLM Applications, taught by Matt Robinson of Unstructured, demonstrates important but sometimes overlooked aspects of RAG systems: - How to extract and normalize content from diverse formats like PDF, Powerpoint, and HTML to expand your LLM's knowledge - Enriching data with metadata to enable more powerful retrieval and reasoning - Applying document layout analysis and vision transforms to process embedded images and tables Then you’ll use all these skills and build a RAG bot that draws from a corpus that includes PDF, PowerPoint, and Markdown documents. Please sign up here:

Andrew Ng

150,317 görüntüleme • 2 yıl önce