Clearer Thinking with Spencer Greenberg

Taking pleasure in being wrong (with Buck Shlegeris)

Jun 8, 2022

Buck Shlegeris, CTO of Redwood Research, shares insights on the complexities of forming true beliefs and embracing the joy of being wrong. He discusses how we should approach certainty in our claims and the value of engaging in rigorous debates to refine our understanding. The conversation delves into effective learning strategies, particularly the benefits of small-scale practice in machine learning. Shlegeris also highlights the challenges in AI alignment, emphasizing the critical need to align AI systems with human values for future safety.

01:16:10

Creator website

Episode guests

Buck Shlegeris

Highlights

AI Chapters

Episode notes

How to Get Fast at Small Skills

01:20

The Core Problem With Machine Learning

01:20

Intro

2min

Navigating Beliefs and Misconceptions

18min

The Power of Case Studies in Management Learning

4min

Accelerating Learning Through Small-Scale Practice

4min

Understanding Machine Learning Through Simplified Questions

2min

Exploring Complexity in Scientific Understanding

13min

Navigating AI Alignment Challenges

9min

Evolving Perspectives on Machine Learning Challenges

3min

Navigating Machine Learning Challenges

17min

10.

Balancing Research and Intuition

3min

Read the full transcript here.

How hard is it to arrive at true beliefs about the world? How can you find enjoyment in being wrong? When presenting claims that will be scrutinized by others, is it better to hedge and pad the claims in lots of caveats and uncertainty, or to strive for a tone that matches (or perhaps even exaggerates) the intensity with which you hold your beliefs? Why should you maybe focus on drilling small skills when learning a new skill set? What counts as a "simple" question? How can you tell when you actually understand something and when you don't? What is "cargo culting"? Which features of AI are likely in the future to become existential threats? What are the hardest parts of AI research? What skills will we probably really wish we had on the eve of deploying superintelligent AIs?

Buck Shlegeris is the CTO of Redwood Research, an independent AI alignment research organization. He currently leads their interpretability research. He previously worked on research and outreach at the Machine Intelligence Research Institute. His website is shlegeris.com.

Staff

Spencer Greenberg — Host / Director
Josh Castle — Producer
Ryan Kessler — Audio Engineer
Uri Bram — Factotum
Janaisa Baril — Transcriptionist

Music

Affiliates

[Read more]

Remember Everything You Learn from Podcasts

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

Get the app