AI Safety Fundamentals: Alignment 201
By BlueDot Impact
Listen to a podcast, please open Podcast Republic app. Available on Google Play Store and Apple App Store.
Image by BlueDot Impact
Category: Technology
Open in Apple Podcasts
Open RSS feed
Open Website
Rate for this podcast
Subscribers: 0
Reviews: 0
Episodes: 15
Description
Listen to resources from the AI Safety Fundamentals: Alignment 201 course!
https://course.aisafetyfundamentals.com/alignment-201
| Episode | Date |
|---|---|
|
Empirical Findings Generalize Surprisingly Far
|
May 13, 2023 |
|
Worst-Case Thinking in AI Alignment
|
May 13, 2023 |
|
Two-Turn Debate Doesn’t Help Humans Answer Hard Reading Comprehension Questions
|
May 13, 2023 |
|
Least-To-Most Prompting Enables Complex Reasoning in Large Language Models
|
May 13, 2023 |
|
Low-Stakes Alignment
|
May 13, 2023 |
|
ABS: Scanning Neural Networks for Back-Doors by Artificial Brain Stimulation
|
May 13, 2023 |
|
Imitative Generalisation (AKA ‘Learning the Prior’)
|
May 13, 2023 |
|
Discovering Latent Knowledge in Language Models Without Supervision
|
May 13, 2023 |
|
Toy Models of Superposition
|
May 13, 2023 |
|
An Investigation of Model-Free Planning
|
May 13, 2023 |
|
Gradient Hacking: Definitions and Examples
|
May 13, 2023 |
|
Intro to Brain-Like-AGI Safety
|
May 13, 2023 |
|
Deep double descent
|
May 13, 2023 |
|
Eliciting Latent Knowledge
|
May 13, 2023 |
|
Chinchilla’s wild implications
|
May 13, 2023 |