logo
episode-header-image
Dec 2024
35m 12s

How LLMs Actually Work

Knownwell
About this episode

Ever wondered what really powers LLMs like ChatGPT, Claude, or Gemini?

In this episode, Courtney Baker, David DeWolf, and Mohan Rao are joined by John Fowler (Knownwell's Chief Science Officer) and Ramsri Goutham Golla (Lead Data Scientist) to break down the mechanics of large language models (LLMs) in ways that are accessible and relevant for all professionals, not just data scientists.

John and Ramsri help explain how LLMs predict the next word in a sentence, what makes them so powerful, and the role of neural networks and attention mechanisms. They also dive into real-world applications, such as retrieval-augmented generation (RAG), and how it’s replacing fine-tuning for more efficient and reliable AI performance.

Ready to harness AI for your business? Learn how Knownwell’s AI-powered platform can empower you to stay ahead at Knownwell.com.

Watch this episode on YouTube: https://youtu.be/l1S3GGyo_o8 

 

Up next
Oct 6
Commercial Intelligence in Action: A Deep Dive into the Knownwell Platform
What if the biggest threat to next year’s revenue isn’t churn—but the quiet erosion of loyalty you never saw coming? With 85% of professional services revenue riding on existing clients, old tools like NPS and gut instinct just won’t cut it anymore. In this special edition, we’re ... Show More
32m 39s
Sep 29
From Curiosity to Core Strategy: Looking Back on Two Years of AI in Business
We’re celebrating 100 episodes of AI Knowhow and asking: what have the last two years of AI actually taught us? Courtney, David, and Mohan rewind the tape to trace how far AI and executive thinking have come since episode 1 of the show all the way back in September 2023. What beg ... Show More
22m 56s
Sep 22
Finding the Next Advantage When Everyone Has AI
AI is fast becoming a utility—accessible to everyone, everywhere. But if the tools are the same, where does competitive advantage come from? Courtney Baker, David DeWolf, and Mohan Rao explore the new sources of differentiation when AI is no longer scarce: proprietary data, clean ... Show More
37m 43s
Recommended Episodes
Sep 18
How People Actually Use ChatGPT
This episode of AI Daily Brief dives into two important reports on how people are really using AI tools like ChatGPT and Claude. OpenAI’s massive study with Harvard and NBER reveals consumer patterns across 1.5 million conversations, while Anthropic’s Economic Index tracks broade ... Show More
27m 39s
Dec 2024
841: Andrew Ng on AI Vision, Agents and Business Value
In this special episode recorded live at ScaleUp:AI in New York, Jon Krohn speaks to Andrew Ng in response to his conference talk on smart agentic AI workflows. Jon follows up with Andrew about smart agentic workflows and when to use them, how businesses should direct their effor ... Show More
26m 21s
Apr 2025
2027 Intelligence Explosion: Month-by-Month Model — Scott Alexander & Daniel Kokotajlo
Scott and Daniel break down every month from now until the 2027 intelligence explosion.Scott Alexander is author of the highly influential blogs Slate Star Codex and Astral Codex Ten. Daniel Kokotajlo resigned from OpenAI in 2024, rejecting a non-disparagement clause and risking ... Show More
3h 4m
Feb 2025
Is Deepseek Worth the Hype?
Episode 44: How impactful is the debut of China's AI model, DeepSeek, on the global tech landscape? Matt Wolfe (https://x.com/mreflow) and Nathan Lands (https://x.com/NathanLands) unravel everything you need to know about DeepSeek R1 in this episode, where they also dive deep on ... Show More
42m 24s
Sep 23
How Microsoft is Fixing the Biggest AI Agent Problem
Want the guide to create AI Agents? get it here: https://clickhubspot.com/fhc Episode 77: Are we nearing a future where AI agents can autonomously tackle our biggest challenges—while remaining efficient, safe, and truly aligned with human goals? Matt Wolfe (https://x.com/mreflow) ... Show More
30m 8s
Oct 2
When Will AI Make Scientific Discoveries?
Today’s AI Daily Brief asks when artificial intelligence will begin making real scientific discoveries. We look at Periodic Labs, which just raised more than $300 million to build AI scientists and autonomous labs for physics and chemistry, and Thinking Machines, which is creatin ... Show More
24m 25s
Dec 2024
How Diamond Cooling Could Power the Future of AI, with Akash Systems
In this episode of No Priors, Sarah sits down with Felix Ejeckam and Ty Mitchell, founders of Akash Systems, a company pioneering diamond-based cooling technology for semiconductors used in space applications and large-scale AI data centers. Felix and Ty discuss how their backgro ... Show More
42m 21s
Apr 2025
AI Agents: The Truth Behind the Hype
Nicolas de Bellefonds, BCG’s global AI leader, unpacks the myths, challenges, and real potential of AI agents. They can transform how work gets done if companies stop chasing shortcuts, rethink outdated processes, and prepare for the costs and complexity that come with real chang ... Show More
19m 7s
Sep 16
The State of AI Agents in 2025 & How to Use Them
Want our guide to master AI Agents? Get it here: https://clickhubspot.com/bka Episode 76: What actually makes something a real "AI Agent"—and how close are we to AI handling complex work entirely on its own? Matt Wolfe (https://x.com/mreflow) is joined by Deepak Singh (https://x. ... Show More
51m 26s
Sep 18
From RAG to Relational: How Agentic Patterns Are Reshaping Data Architecture
SummaryIn this episode of the AI Engineering Podcast Mark Brooker, VP and Distinguished Engineer at AWS, talks about how agentic workflows are transforming database usage and infrastructure design. He discusses the evolving role of data in AI systems, from traditional models to m ... Show More
52m 58s