Global Challenges Project - Library

EA Student Groups Handbook

AI Alignment

ℹ️

This is based on the 2023 AGI Safety Fundamentals curriculum

Start here

Topics

Introduction to Machine Learning

Introduction to Machine Learning

Introduction to Machine Learning

Next in the Sequence

Topics

Artificial general intelligence

Artificial general intelligence

Artificial general intelligence

Reward misspecification and instrumental convergence

Reward misspecification and instrumental convergence

Reward misspecification and instrumental convergence

Goal misgeneralization

Goal misgeneralization

Goal misgeneralization

Task decomposition for scalable oversight

Task decomposition for scalable oversight

Task decomposition for scalable oversight

Adversarial techniques for scalable oversight

Adversarial techniques for scalable oversight

Adversarial techniques for scalable oversight

Interpretability

Interpretability

Interpretability

Interpretability, and MIRI's research agenda

Agent foundations or AI governance, and careers in alignment

Agent foundations or AI governance, and careers in alignment

Agent foundations or AI governance, and careers in alignment