Crazy Wisdom
Episode #395: How to Teach an AI to Think: A Conversation About Knowledge and Intelligence
- AI & Agents
- Knowledge graphs
- AI architecture
- machine learning
- language models
- BERT
- foundational models
- retrieval-augmented generation (RAG)
- data engineering
This video isn't available here. Try YouTube, or listen to the audio below.
Watch on YouTubeAbout this episode
Timestamps
Key Insights
- The evolution of AI models: Ian Mason discusses how foundational models like BERT have been overtaken by newer, more capable language models, which can perform tasks that once required multiple models. He highlights that while earlier models like BERT still have their uses, foundational models have simplified and expanded AI’s capabilities.
- The role of knowledge graphs: Knowledge graphs provide structured, deterministic ways of handling data, which can complement language models. Ian explains that while LLMs are great for articulating responses based on large datasets, they lack the ability to handle logical and architectural connections between pieces of information, which knowledge graphs can provide.
- RAG (Retrieval-Augmented Generation) systems: Ian delves into how RAG systems help refine AI output by feeding language models relevant data from a pre-searched database, reducing hallucinations. By narrowing down the possible answers and focusing the LLM on high-quality data, RAG ensures more accurate and contextually appropriate responses.
- Limitations of language models: While LLMs can generate plausible-sounding responses, they lack deep architectural understanding and can easily hallucinate or provide inaccurate results without carefully curated input. Ian points out the importance of combining LLMs with structured data systems like knowledge graphs or vector databases to ground the output.
- Vector databases and embeddings: Ian explains how vector databases, which use embeddings and cosine similarity, are crucial for narrowing down the most relevant data in a RAG system. This modern approach outperforms traditional keyword searches by considering semantic meaning rather than just text similarity.
- AI’s impact on business solutions: The conversation highlights how AI, particularly through tools like RAG and LLMs, can streamline business processes. For instance, Ian uses AI to automate customer service email drafting, breaking down complex customer queries and retrieving the most relevant answers, significantly improving operational efficiency.
- The future of AI in business: Ian believes AI’s real-world impact will come from its integration into larger systems rather than revolutionary standalone changes. While there is significant hype around AGI and other speculative technologies, the focus for the near future should be on practical applications like automating business workflows, where AI can create measurable value without over-promising its capabilities.
Episode transcript
Welcome to the Crazy Wisdom Podcast. This podcast is for you. If you have an insane drive to find the truth of things, it's not the good answers that we seek, but the good questions. I interview a range of different guests from many different fields, all with the intention to uncover the simple truths that are hidden in plain sight. Most people don't want to go there. I go there, my guests go there, and you benefit. Please let me know if you enjoy these episodes and as always, subscribe on itunes, Spotify or wherever you listen to the podcasts.
Welcome to the Crazy Wisdom Podcast. My guest today is Ian Mason. He does architecture and delivery of AI and ML, including LLMs and RAG. Most of my listeners are probably familiar with all of those terms. We got data analytics and data engineering, full stack solutions. So welcome to the show.
Yeah, long time mutual, very on Twitter and we're going to go deep dive into all the different stuff that you talk about. And we were just talking beforehand about how I want to create a knowledge graph and I've heard the term knowledge graph thrown around so many times and now with AI I'm able to go whenever somebody says something, able to go do the studying on it and get it really quick. And so now I think I've got what a knowledge graph is in my head. It's taken me six months to figure out what it even is. And, and at first ChatGPT said sent me down this total rabbit hole. I asked it, how do I make my podcast a a how do I make my podcast into a knowledge graph? And it started giving me the pre trained BERT models, all of which now seem to be totally obsolete because now we just have the foundational models which can do all of this different stuff. Is that an accurate representation of what's happened? Like would you still use the BERT model? Is that it's a transformer?
Your first full transcript is free. After that, an email opens every transcript in the index — a list of readers we can write to, not a guest book.