Resources: Adversarial techniques for scalable oversight

Exercises: Adversarial techniques for scalable oversight

Resources: Reward misspecification and instrumental convergence

Exercises: Reward misspecification and instrumental convergence

Resources: Governance (Alignment 23)

Exercises: Governance (Alignment 23)

Resources: Task decomposition for scalable oversight

Exercises: Task decomposition for scalable oversight

Resources: Careers and Projects

Exercises: Careers and Projects

Resources: Interpretability

Exercises: Interpretability

Resources: Agent foundations

Exercises: Agent foundations

Resources: Artificial General Intelligence

Exercises: Artificial General Intelligence

Resources: Introduction to Machine Learning (23)

Exercises: Introduction to Machine Learning (23)

Resources: Goal misgeneralisation

Exercises: Goal misgeneralisation

Scaling up neural networks predictably leads to more powerful and general capabilities, and we're not far away from being able to train networks with sizes comparable to human brains.
Artificial general intelligence (AGI) is the key concept underpinning this course, so it's important to start by exploring what we mean by AGI and examine the reasons for thinking that the field of machine learning is heading towards it.
First, we will examine the current state of machine learning and then consider what AGI is. These two topics will help you form your views on whether modern machine learning is heading towards the development of AGI.
Second, we will consider how these capabilities might develop over time. We'll cover a report that measures how long it'll take to afford the necessary compute to train a human-equivalent intelligence and arguments that scaling current techniques leads to higher - and potentially more general - capabilities.
Finally, we'll examine texts that speculate the potential step changes in ML capabilities still to come.

By the end of the unit, you should be able to:
\- Define what 'foundation models' are and understand how they are trained.
\- Describe the current state of the art in machine learning, and summarise the rate of progress.
\- Propose the capability requirements for an AI system to be defined as AGI.
\- Contrast modern machine learning with your blueprint for AGI, and evaluate if/when AGI could be developed.


AI Alignment (2023)

Exercises: Artificial General Intelligence