205: How to make LLMs Boring (Predictable, Reliable, and Safe), Featuring Nicolay Gerold

Sep 4, 2024

Nicolay Gerold, an expert in artificial intelligence, shares his journey in developing large language models (LLMs) while discussing the challenges of generating reliable outputs. He emphasizes the importance of data quality over model adjustments, addressing the barriers to effective LLM use. The conversation also highlights the need for human oversight in AI applications, especially regarding security and customer interactions. Nicolay delves into monitoring, testing challenges, and the evolving landscape of AI startups, offering insights into making LLMs more predictable and reliable.

Ask episode

Chapters

Transcript

Episode notes

Intro

00:00 • 2min

Navigating the Evolution of AI and LLMs

01:40 • 13min

Harnessing Large Language Models: Pros and Cons

14:50 • 17min

Empowering Non-Technical Users with AI Tools

31:59 • 2min

Monitoring and Testing in AI

33:56 • 4min

Navigating AI and Software Development

38:20 • 8min

Sustainability and Challenges in the LLM Landscape

46:49 • 2min