⏪ Making LLMs Backwards Compatible with Jason Liu from The MLOps Podcast

⏪ Making LLMs Backwards Compatible with Jason Liu

53 minutes Posted Jan 15, 2024 at 2:15 pm.

Introduction

Excitement about Machine Learning and AI

Using LLMs as Backend Developers

Building Applications with LLMs

Building Instructor

Thinking in Logic and Design

Validating Data and Building Systems with Instructor

Thoughts About Product and UX in LLMs

Future of Instructor

Misconceptions and Unsolved Problems in LLMs

Improving LLM Applications

RAG as Recommendation Systems

Fine-tuning Embedding Models

Beyond Vector Similarity in RAG

Predictions for the Next Year in AI and ML

Measuring Impact on Business Outcomes

The Continuous Cycle of Machine Learning

Unlocking Economic Value through Structured Data Extraction

Questioning the Status Quo and Making an Impact

0:00

53:41

Download MP3

Share at current time

Show notes

In this episode, I had the pleasure of speaking with Jason Liu, an applied AI consultant and the creator of Instructor – an open-source tool for extracting structured data from LLM outputs. We chat about LLM applications, their challenges, and how to overcome them. We also dive into Instructor, making LLMs interact with existing systems and a bunch of other cool things.

Join our Discord community: https://discord.gg/tEYvqxwhah

➡️ Jason Liu on Twitter – https://twitter.com/jxnlco

🤖 Instructor Blog – https://jxnl.github.io/instructor/

🌐 Check Out Our Website! https://dagshub.com

Social Links:

➡️ LinkedIn: https://www.linkedin.com/company/dagshub

➡️ Twitter: https://twitter.com/TheRealDAGsHub

➡️ Dean Pleban: https://twitter.com/DeanPlbn

Timestamps:

← See all 35 episodes of The MLOps Podcast