Chapters
Transcript
Episode notes
1 2 3 4 5 6 7 8 9 10 11
Introduction
00:00 • 4min
Is It a I Line or a Terminator?
04:04 • 2min
The Probability of Death From a I Is More Than a Small Number
05:54 • 4min
How to Build Really Powerful Systems That Don't Kill You?
09:25 • 2min
Train a Machine Learning System to Do Really Well According to a Lost Function
11:34 • 4min
The Long Term Deployment Only Failures Problem
15:15 • 2min
Machine Learning and Mechanistic Interpretability
17:36 • 3min
How Successful Has It Been?
20:31 • 2min
Is There a Problem With Automated Classifiers?
22:29 • 2min
Is There a Difference Between Interpretability and Other Places?
24:06 • 2min
Applying Lima Research
26:19 • 3min