Vanishing Gradients

Episode 28: Beyond Supervised Learning: The Rise of In-Context Learning with LLMs

Jun 9, 2024

Alan Nichol, Co-founder and CTO of Rasa, shares insights on using LLMs in chatbots, the evolution of conversational AI, and the challenges of supervised learning. He emphasizes the importance of balancing traditional techniques with new advancements. The podcast also includes a live demo of Rasa's CALM system, showcasing the separation of business logic from language models for reliable conversational flow execution.

01:05:38

Creator website

Episode guests

Alan Nichol

AI Summary

AI Chapters

Episode notes

Podcast summary created with Snipd AI

Quick takeaways

Implementing LLMs in chatbots necessitates balancing autonomy with business logic for secure actions like money transfers.

Understanding the historical progression of conversational AI aids in effective LLM integration for future chatbot development.

Incorporating LLMs into chatbots should focus on interpreting context within predefined business logic to ensure reliable conversation outcomes.

Deep dives

Challenges of Using Large Language Models in Conversational AI

Incorporating LLMs into chatbots raises questions on whether to trust a single large LLM like GPT or secure its actions within distinct business logic. The episode explores how to effectively implement LLMs in chatbots for actions like secure money transfers.

Intro

4min

Evolution of Conversational AI and Chatbots

19min

The Impact of ChatGPT and the Surge in Chatbot Conversations

2min

Integration of Large Language Models in Conversational AI

13min

Exploring the Challenges and Failures of Supervised Learning

5min

Exploring the Shift to Data-Centric AI and Challenges of In-Context Learning vs. Supervised Learning

3min

Exploring Frustrations with GPT-4, Overrated and Underrated Aspects of LLMs

3min

Effective Integration of Language Models in Conversational AI

17min

Hugo speaks with Alan Nichol, co-founder and CTO of Rasa, where they build software to enable developers to create enterprise-grade conversational AI and chatbot systems across industries like telcos, healthcare, fintech, and government.

What's super cool is that Alan and the Rasa team have been doing this type of thing for over a decade, giving them a wealth of wisdom on how to effectively incorporate LLMs into chatbots - and how not to. For example, if you want a chatbot that takes specific and important actions like transferring money, do you want to fully entrust the conversation to one big LLM like ChatGPT, or secure what the LLMs can do inside key business logic?

In this episode, they also dive into the history of conversational AI and explore how the advent of LLMs is reshaping the field. Alan shares his perspective on how supervised learning has failed us in some ways and discusses what he sees as the most overrated and underrated aspects of LLMs.

Alan offers advice for those looking to work with LLMs and conversational AI, emphasizing the importance of not sleeping on proven techniques and looking beyond the latest hype. In a live demo, he showcases Rasa's Calm (Conversational AI with Language Models), which allows developers to define business logic declaratively and separate it from the LLM, enabling reliable execution of conversational flows.

LINKS

Upcoming Livestreams

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.

Vanishing Gradients

Episode 28: Beyond Supervised Learning: The Rise of In-Context Learning with LLMs

Episode guests

Podcast summary created with Snipd AI

Quick takeaways

Deep dives

Challenges of Using Large Language Models in Conversational AI

The Evolution of Chatbots and Conversational AI

Balancing Language Models with Business Logic in Conversational AI

Shift in Focus to Data for Improving ML Models

Importance of Business Logic and Flow Structure in LLM Development

Remember Everything You Learn from Podcasts