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: 852

SHOW TRANSCRIPT: The Cloudcast #852 Transcript

SHOW VIDEO: https://youtube.com/@TheCloudcastNET

CLOUD NEWS OF THE WEEK: http://bit.ly/cloudcast-cnotw

CHECK 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 Infrastructure

SHOW NOTES:

• What is Retrieval Augmented Generation (RAG)?
• Fine-Tuning vs. RAG
• Predictive AI vs. Generative AI
• Andrew Ng (always worth a watch IMO) https://youtu.be/sal78ACtGTc?si=dCoKXb5o4KB2XSer
• Harrison Chase (LangChain) https://youtu.be/pBBe1pk8hf4?si=lAit69_pDeRKcBGq
• https://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-IYzyi86yY
• https://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 decisions
• How often do you update models with new data?

HOW DO WE BRING OUR COMPANY DATA / KNOWLEDGE TO OUR AI MODELS?

• Large Static Models - Predictive AI
• LLMs + Slow-Changing Data - Align the Model
• LLMs + Fast-Changing Data - RAG
• LLMs + Agent-Learned Data - Agentic AI

FEEDBACK?

• Email: show at the cloudcast dot net
• Twitter: @cloudcastpod
• Instagram: @cloudcastpod
• TikTok: @cloudcastpod