Slow Data, Fast Data and Adapting AI models for your business
Slow Data, Fast Data and Adapting AI models for your business  
Podcast: The Reasoning Show
Published On: Sun Sep 01 2024
Description: With so much rapid change happening around AI models, is there a framework for when to build models, train models, fine-tune models, use RAG or something else? Let’s explore…SHOW: 852SHOW TRANSCRIPT: The Cloudcast #852 TranscriptSHOW VIDEO: https://youtube.com/@TheCloudcastNET CLOUD NEWS OF THE WEEK:  http://bit.ly/cloudcast-cnotwCHECK OUT OUR NEW PODCAST:  "CLOUDCAST BASICS"SHOW SPONSOR:Access Gartner cloud research come to life with the “The Future of Cloud in 2028: From Technology to Business Necessity,” webinar.Secure your seat for Gartner IT Infrastructure, Operations & Cloud Strategies Conference 2024 with our early bird savings of $400 off standard rates now.  Upgrade to the next generation of the cloud.  Oracle Cloud InfrastructureSHOW NOTES:What is Retrieval Augmented Generation (RAG)?Fine-Tuning vs. RAGPredictive AI vs. Generative AIAndrew Ng (always worth a watch IMO) https://youtu.be/sal78ACtGTc?si=dCoKXb5o4KB2XSerHarrison Chase (LangChain) https://youtu.be/pBBe1pk8hf4?si=lAit69_pDeRKcBGqhttps://blog.langchain.dev/what-is-a-cognitive-architecture/https://thenewstack.io/lets-get-agentic-langchain-and-llamaindex-talk-ai-agents/https://www.youtube.com/watch?v=N-IYzyi86yYhttps://blog.langchain.dev/what-is-an-agent/https://www.microsoft.com/en-us/research/project/autogen/https://www.crewai.com/ HOW SHOULD WE DECIDE WHICH AI MODEL TO USE FOR OUR APPLICATION?Build, buy, use open source, augment with your own data - so many decisionsHow often do you update models with new data? HOW DO WE BRING OUR COMPANY DATA / KNOWLEDGE TO OUR AI MODELS?Large Static Models - Predictive AILLMs + Slow-Changing Data - Align the ModelLLMs + Fast-Changing Data - RAGLLMs + Agent-Learned Data - Agentic AIFEEDBFEEDBACK?Email: show @ reasoning dot showBluesky: @reasoningshow.bsky.socialTwitter/X: @ReasoningShowInstagram: @reasoningshowTikTok: @reasoningshow