- Видео 362
- Просмотров 1 269 278
Gradient Flow
США
Добавлен 3 май 2020
Gradient Flow presents a rich array of high quality content on data, technology and business, with a focus on machine learning and AI. Named by Coursera as one of the Top 10 Sites for Data Scientists, Gradient Flow helps you stay ahead on the latest technology trends and tools with in-depth coverage, analysis and insights.
Learn the latest trends and best practices in data, technology and business, with a focus on machine learning and AI.
gradientflow.com/subscribe/
Learn the latest trends and best practices in data, technology and business, with a focus on machine learning and AI.
gradientflow.com/subscribe/
Data Exchange Podcast (Episode 256): Vaibhav Gupta of Boundary and BAML
Episode Notes: thedataexchange.media/baml/
Vaibhav Gupta is the CEO and co-founder of Boundary and co-creator of BAML.
**Sections**
Extracting Structured Data from LLMs - 00:01:24
Pivot from RAG to BAML for Better Data Results - 00:03:22
Challenges in RAG Pipelines and BAML’s High-Quality Data Approach - 00:04:08
Overview of BAML’s Information Extraction Capabilities - 00:05:07
Reducing Token Usage and Switching to Smaller Models - 00:06:37
BAML’s Role in Information Transformation - 00:09:58
Structured Text with OpenAI and BAML’s Error Handling - 00:12:38
Entity Extraction and Data Transformation Use Cases - 00:13:54
Case Study: Fortune 50 Company Using BAML for Cost Optimization - 00:16:19
Prevent...
Vaibhav Gupta is the CEO and co-founder of Boundary and co-creator of BAML.
**Sections**
Extracting Structured Data from LLMs - 00:01:24
Pivot from RAG to BAML for Better Data Results - 00:03:22
Challenges in RAG Pipelines and BAML’s High-Quality Data Approach - 00:04:08
Overview of BAML’s Information Extraction Capabilities - 00:05:07
Reducing Token Usage and Switching to Smaller Models - 00:06:37
BAML’s Role in Information Transformation - 00:09:58
Structured Text with OpenAI and BAML’s Error Handling - 00:12:38
Entity Extraction and Data Transformation Use Cases - 00:13:54
Case Study: Fortune 50 Company Using BAML for Cost Optimization - 00:16:19
Prevent...
Просмотров: 309
Видео
Data Exchange Podcast (Episode 255): Tim Persons of PwC
Просмотров 92819 часов назад
Episode Notes: thedataexchange.media/tim-persons-2024-07/ In this conversation with Tim Persons, AI Leader at PwC, we explore the current landscape of generative AI adoption, examining how enterprises are navigating budget trends, moving from experimentation to full-scale deployment, and addressing cultural challenges along the way. Sections Overview: Adoption of Generative AI in Enterprises - ...
Data Exchange Podcast (Episode 254): Monthly Roundup with Ben Lorica & Paco Nathan
Просмотров 1 тыс.14 дней назад
Episode Notes: thedataexchange.media/roundup-2024-10/ Sections Ray Compiled Graphs - 00:00:43 SB 1047 Is Vetoed, what next? - 00:07:57 Structure Is All You Need: enhancing RAG with structured & contextual information - 00:13:41 Llama 3.2 & the state of frontier model developers - 00:27:40 vLLM and Ray Data: status reports - 00:39:04 The Bigger-is-Better Paradigm in AI - 00:44:35 Recommendations...
Data Exchange Podcast (Episode 254): Matt Welsh of Aryn AI
Просмотров 1,3 тыс.21 день назад
Episode Notes: thedataexchange.media/matt-welsh-2024-09/ Matt Welsh is a technical leader at Aryn AI, an AI-powered ETL system for RAG frameworks, LLM-based applications, and vector databases. Sections The Changing Nature of Programming - 00:02:24 Trusting AI to Build Pipelines - 00:04:29 The Democratization of Programming - 00:07:04 The Role of LLMs in Programming - 00:10:42 Challenges in Inte...
Data Exchange Podcast (Episode 253): Mars Lan of Metaphor
Просмотров 1,8 тыс.28 дней назад
Episode Notes: thedataexchange.media/the-security-debate-how-safe-is-open-source-software/ Mars Lan, Co-Founder & CTO at Metaphor1 an AI-powered social platform that enhances data governance by empowering all employees, not just data teams, to easily collaborate, search, and share insights through an intuitive, AI-driven interface. Sections Security and Vulnerabilities in Open Source Software -...
Data Exchange Podcast (Episode 252): Yishay Carmiel of Meaning.team
Просмотров 2,4 тыс.Месяц назад
Episode Notes: thedataexchange.media/generative-ai-in-voice-technology/ Yishay Carmiel is the CEO of Meaning, a startup building real-time generative AI systems focused on voice applications. Sections Demo of real-time speech synthesis - 00:02:48 Speech Technologies: From Analysis to Synthesis - 00:05:54 Future Scenarios for Speech-Based Interfaces - 00:07:58 Voice Agents and the Role of Genera...
Data Exchange Podcast (Episode 251): Aurimas Griciūnas of Neptune.ai
Просмотров 3,3 тыс.Месяц назад
Episode Notes: Aurimas Griciūnas is the Chief Product Officer of Neptune.AI, a startup building experiment tracking tools for foundation model training. Sections Overview of LLM Ops and Experiment Tracking - 00:01:42 Challenges of Scaling LLMs: From ML to LLM Ops - 00:02:14 Scale and Complexity of LLM Clusters and Training - 00:06:58 Frontier Models and Training Cycles - 00:09:25 Enterprise Les...
Data Exchange Podcast (Episode 250): Monthly Roundup with Paco Nathan
Просмотров 1,1 тыс.Месяц назад
Episode Notes: thedataexchange.media/roundup-2024-09/ Key Sections The Case Against SB 1047 - 00:00:55 Generate a Health Insurance Appeal with Generative AI - 00:18:16 Cerebras Inference - 00:22:10 Roles and Implications of AI in the Russian-Ukrainian Conflict - 00:33:08 2024 Ray Summit - 00:42:30 Mamba for Tabular Data Generative AI for Analysts - 00:44:10 The arrest of Telegram’s CEO - 00:46:...
Data Exchange Podcast (Episode 249): Petros Zerfos and Hima Patel of IBM Research and Data Prep Kit
Просмотров 1,3 тыс.Месяц назад
Episode Notes: thedataexchange.media/ibm-data-prep-kit/ Petros Zerfos and Hima Patel of IBM Research are part of the team behind Data Prep Kit, an open-source toolkit that helps process and prepare raw text and code data at scale for use in large language model applications. Sections High-Level Basics of Data Preparation - 00:00:27 Core Functions of Data Prep Kit for Structured Data - 00:01:45 ...
Data Exchange Podcast (Episode 248): Andrew Ng
Просмотров 1,2 тыс.2 месяца назад
Episode Notes: thedataexchange.media/andrew-ng-2024-05/ Dr. Andrew Ng is a globally recognized AI leader, founder of DeepLearning.AI and Landing AI, General Partner at AI Fund, Chairman and Co-Founder of Coursera, and Adjunct Professor at Stanford University. Sections Scaling Up Deep Learning Algorithms - 00:00:00 GPUs and the Importance of Inference - 00:01:58 Data-Centric AI - 00:03:27 AI Age...
Data Exchange Podcast (Episode 247): Jay Dawani, CEO and founder of Lemurian Labs
Просмотров 4,6 тыс.2 месяца назад
Episode Notes: thedataexchange.media/lemurian-labs/ Sections ↓ Lemurian Labs - their origin story - 00:00:40 Scaling Laws and the Evolution of AI Models - 00:04:14 Challenges and Opportunities in Using Multiple AI Models - 00:07:29 Industry Trends and the Role of Software in AI Hardware - 00:14:00 Optimizing Foundation Models: A Deep Dive into PyTorch and Beyond - 00:16:53 Building Developer-Fr...
Data Exchange Podcast (Episode 246): Monthly Roundup with Paco Nathan
Просмотров 1,7 тыс.2 месяца назад
Episode Notes: thedataexchange.media/roundup-2024-08/ Sections ↓ Foundation Models and the AI Arms Race: Winners, Losers, and Strategic Pivots - 00:00:28 Neural Networks and Partial Differential Equations - 00:21:30 Why Digital-First Companies Are Building Their Own AI Platforms - 00:27:05 Vulnerabilities in LangChain Gen AI - 00:35:47 2024 AI Conference :: a preview - 00:43:09 relik: A blazing...
Data Exchange Podcast (Episode 245): Evangelos Simoudis of Synapse Partners
Просмотров 2,5 тыс.2 месяца назад
Episode Notes: thedataexchange.media/current-state-of-enterprise-generative-ai-adoption/ Evangelos Simoudis is Managing Director at Synapse Partners, a firm that assists corporations in implementing AI solutions, and invests in startups developing applications that exploit data using AI. Sections Adoption of Enterprise Generative AI - 00:01:36 Investment Trends in Generative AI - 00:03:08 Chall...
Data Exchange Podcast (Episode 244): Shuveb Hussain of Unstract
Просмотров 2,3 тыс.3 месяца назад
Episode Notes: thedataexchange.media/unstract-zipstack/ Shuveb Hussain is co-founder of Unstract, a no-code platform that uses large language models to extract structured data from unstructured documents, allowing users to build API endpoints and ETL pipelines to automate document processing workflows. Sections Inspiration for Unstract - 00:00:45 Emerging Role of Prompt Engineers - 00:02:04 Rei...
Data Exchange Podcast (Episode 243): Alfred Spector of M.I.T.
Просмотров 1,9 тыс.3 месяца назад
Episode Notes: thedataexchange.media/generative-ai-in-context/ Alfred Spector’s distinguished career includes groundbreaking work in networked computing systems and leadership roles in research at IBM, Google, and Two Sigma Investments. He is currently a visiting scholar at MIT. Sections Roles at MIT and Blackstone - 00:00:25 Discussion on the Book "Data Science and Context" - 00:02:13 Importan...
Data Exchange Podcast (Episode 242): Monthly Roundup with Paco Nathan
Просмотров 1,6 тыс.3 месяца назад
Data Exchange Podcast (Episode 242): Monthly Roundup with Paco Nathan
Data Exchange Podcast (Episode 241): Andrew Burt of Luminos.Law and Luminos.ai
Просмотров 3 тыс.3 месяца назад
Data Exchange Podcast (Episode 241): Andrew Burt of Luminos.Law and Luminos.ai
Data Exchange Podcast (Episode 240): Chang She of LanceDB
Просмотров 2 тыс.3 месяца назад
Data Exchange Podcast (Episode 240): Chang She of LanceDB
Data Exchange Podcast (Episode 239): Ajay Kulkarni and Mike Freedman of Timescale, on vector search
Просмотров 1 тыс.4 месяца назад
Data Exchange Podcast (Episode 239): Ajay Kulkarni and Mike Freedman of Timescale, on vector search
Data Exchange Podcast (Episode 238): Philip Rathle of Neo4j
Просмотров 4,5 тыс.4 месяца назад
Data Exchange Podcast (Episode 238): Philip Rathle of Neo4j
Data Exchange Podcast (Episode 237): monthly roundup with Ben Lorica and Paco Nathan
Просмотров 8374 месяца назад
Data Exchange Podcast (Episode 237): monthly roundup with Ben Lorica and Paco Nathan
Data Exchange Podcast (Episode 236): Jiwoo Hong and Noah Lee of KAIST AI
Просмотров 1,3 тыс.4 месяца назад
Data Exchange Podcast (Episode 236): Jiwoo Hong and Noah Lee of KAIST AI
Data Exchange Podcast (Episode 235): Pete Warden of Useful Sensors
Просмотров 2 тыс.5 месяцев назад
Data Exchange Podcast (Episode 235): Pete Warden of Useful Sensors
Data Exchange Podcast (Episode 234): Ken Liu of Stanford
Просмотров 2,4 тыс.5 месяцев назад
Data Exchange Podcast (Episode 234): Ken Liu of Stanford
Data Exchange Podcast (Episode 233): Joao Moura of crewAI
Просмотров 1,7 тыс.5 месяцев назад
Data Exchange Podcast (Episode 233): Joao Moura of crewAI
Data Exchange Podcast (Episode 232): Ben Lorica & Paco Nathan on Llama 3, Agents, Eval, and more
Просмотров 1,9 тыс.5 месяцев назад
Data Exchange Podcast (Episode 232): Ben Lorica & Paco Nathan on Llama 3, Agents, Eval, and more
Data Exchange Podcast (Episode 231): Gunther Hagleither of Waii
Просмотров 2,2 тыс.5 месяцев назад
Data Exchange Podcast (Episode 231): Gunther Hagleither of Waii
Data Exchange Podcast (Episode 230): Nestor Maslej, editor-in-chief of the 2024 AI Index Report
Просмотров 3,7 тыс.6 месяцев назад
Data Exchange Podcast (Episode 230): Nestor Maslej, editor-in-chief of the 2024 AI Index Report
Data Exchange Podcast (Episode 229): Hagay Lupesko of Databricks and the DBRX
Просмотров 3,1 тыс.6 месяцев назад
Data Exchange Podcast (Episode 229): Hagay Lupesko of Databricks and the DBRX
Data Exchange Podcast (Episode 228): Ben Lorica and Paco Nathan New LLMs, Insights from GTC 2024.
Просмотров 2,4 тыс.6 месяцев назад
Data Exchange Podcast (Episode 228): Ben Lorica and Paco Nathan New LLMs, Insights from GTC 2024.
I love how you made your mind map in this video! Could you share the tools or techniques you used to create it? I’d love to make mine look as professional as yours.
💐💐💐💐💐💐💐💐💐💐💐🇮🇳🇮🇳🇮🇳🙏🙏🙏🙏🙏❤❤❤
I think Paco makes a very interesting and crucial point at the 30:35 mark. These LLM-powered graph builders are creating graphs from unstructured data, but how much domain knowledge do they possess to build truly sensible and accurate graphs in specific areas? For example, if I work with medical record systems and want to enhance them with data from medical guidelines, how confident can I be that the LLM understands the proper relationships between diseases, symptoms, and medical encodings like ICD-10 to generate a sensible and accurate graph? I know that some SciSpacy models have been trained on biomedical data and could theoretically do a better job of extracting relevant medical entities and relationships. How can this be incorporated into current GraphRAG workflows? I was hoping Paco would discuss this more and possibly explain ways to improve the resultant knowledge graph, either using existing approaches (Microsoft GraphRAG or Neo4J Graph Builder) or other alternative methods.
insightful discussions!
That's a fantastic question from Ben: We can accomplish everything you've outlined using a straightforward software class, without the need for an agent.
its the same use case all over, but AI can take 'fuzzy' input! one simple example of superiority of agents even at current capability? web scraping
Great interview but man, you have to stop cutting your guest off mid sentence. It's rude and it hurts the flow.
Ao
0:25
😕 "promo sm"
Dvngeelrtt
Hello there! I recently stumbled upon your RUclips-recommended video discussing Data Exchange Podcast. I was thoroughly impressed by your presentation. Your focus on developing self-discipline, staying motivated, and being consistent deeply resonates with the topics I cover on my own channel. Like you, I'm dedicated to empowering and inspiring my audience with practical guidance. Your unique perspective and clear communication style have convinced me to hit that subscribe button. Keep up the great work-you're definitely making a positive difference!
I hope : in oxide or somebody else, ansure all compute, network and storage get its own purposed very specific functions , maybe integrated FPGA alike ??
Really enjoy listening when Dmitriy explains how A.I. is being applied at Ginkgo. He breaks it down into bite-sized pieces that I am able to understand.
"Nothing is better than showing". I could not agree more! I worked two months on an MVP just to be able to show my target audience what I wanted to sell them. I found out someone was already doing what my app did but better. Oh well.
Good quantization and c p.u etc
Jbbbb
it is bit annoying to see the host interrupting the guest so often 😊
Greats guest..
Great discussion.
Very good conversation. Like every other technology, AI requires efforts to make it work. One can’t simply assume that it is like flicking a switch. This realisation is important for us to begin to realise the value at scale. Else there will be disappointment.
Excellent discussion. Totally agree it’s a revolution in communication. Also creation.
I really like that Sudhir showed open-minded opinion about the market trends, not just pitching Neo4j - where in fact Neo4j can be very important player for this wave on AI revolution because of mixing graphs and VBD capabilities.
🎉
Would love more podcasts on navigating, defending against, and combatting next generation identity theft, social engineering, misinformation/disinformation, etc. That’s honestly what keeps me up most at night regarding these rapidly developing technologies.
Great discussion.
Nice
Fascinating. Great listen!
😊😊😊 😊
😊
😊
Really very useful tips,very well done,get going,best wishes
Fkdhttnk😢😢😢😢
Very excited to try this. Great discussion.
'Promo sm'
Awesome! Super excited to listen to this!
Really great interview!
great interview. thanks!
It looks Python, it runs like C.
Ok
Bought the book after just a few minutes, in the chat about statistics. Just great! I wish Chris had been my prof at uni! Thank you Ben. Adding real value.
Very informative and interesting podcast. Loved watching, Keep it up👏🙏🙏
AI innovation. Aleph Alpha leads the way. Such a great watch.
Excellent conversation. Much appreciated👍👍👏👏
Next-gen AI for healthcare and government sectors. Impressive!
Transforming AI with data integration. Great information!✌
Building responsible and impactful AI systems. Exciting future ahead!
Great video! I'll watch some other videos on this channel this weekend. Keep up the good work!
It's fascinating to see how tools like Dagster and Ray are being used to solve infrastructure issues and optimize workloads. Technology solutions were critical.😍
Important discussion on AI model interpretability and security. Thanks for sharing!
Love this conversation. Very informative and interesting!! Thanks for sharing👍👍