Exercises: Decomposing Tasks for Better Supervision

Resources: Decomposing Tasks for Better Supervision

Exercises: Interpretability 9

Resources: Interpretability 9

Exercises: Track 1: Eliciting Latent Knowledge

Resources: Track 1: Eliciting Latent Knowledge

Exercises: Literature Review or Project Proposal

Resources: Literature Review or Project Proposal

Exercises: Track 3: Science and Deep Learning

Resources: Track 3: Science and Deep Learning

Exercises: Reasoning about Reasoning

Resources: Reasoning about Reasoning

Exercises: Further Understanding the Alignment Problem

Resources: Further Understanding the Alignment Problem

Exercises: Preventing Misgeneralization

Resources: Preventing Misgeneralization

Exercises: Track 2: Agent Foundations

Resources: Track 2: Agent Foundations

After doing a first-pass read of all of the core resources in this session (above), **pick whichever you find most interesting, and try to fully understand that.**
A good way to test understanding is to explain it to someone else. Can you write an explainer for the point you decide to deep-dive into?


Understanding deep-dive

This session digs deeper into understanding what is meant by agency, and implied problems for alignment of AI agents.


Alignment 201

Track 2: Agent Foundations

Further Understanding the Alignment Problem

Decomposing Tasks for Better Supervision

Preventing Misgeneralization

Interpretability (201)

Reasoning about Reasoning

Track 1: Eliciting Latent Knowledge

Track 3: Science and Deep Learning

Literature Review or Project Proposal