AF - The Hubinger lectures on AGI safety: an introductory lecture series by Evan Hubinger

<a href="https://www.alignmentforum.org/posts/jotZXEixzToEHnrfr/the-hubinger-lectures-on-agi-safety-an-introductory-lecture">Link to original article</a><br/><br/>Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: The Hubinger lectures on AGI safety: an introductory lecture series, published by Evan Hubinger on June 22, 2023 on The AI Alignment Forum. In early 2023, I (Evan Hubinger) gave a series of recorded lectures to SERI MATS fellows with the goal of building up a series of lectures that could serve as foundational introductory material to a variety of topics in AGI safety. Those lectures have now been edited and are available on YouTube for anyone who would like to watch them. The basic goal of this lecture series is to serve as longform, in-depth video content for people who are new to AGI safety, but interested enough to be willing to spend a great deal of time engaging with longform content, and who prefer video content to written content. Though we already have good introductory shortform video content and good introductory longform written content, the idea of this lecture series is to bridge the gap between those two. Note that the topics I chose to include are highly opinionated: though this is introductory material, it is not intended to introduce the listener to every topic in AI safety—rather, it is focused on the topics that I personally think are most important to understand. This is intentional: in my opinion, I think it is far more valuable to have some specific gears-level model of how to think about AI safety, rather than a shallow overview of many different possible ways of thinking about AI safety. The former allows you to actually start operationalizing that model to work on interventions that would be valuable under it, something the latter doesn't do. The lecture series is composed of six lectures, each around 2 hours long, covering the topics: Machine learning + instrumental convergence Risks from learned optimization Deceptive alignment How to evaluate alignment proposals LLMs + predictive models Overview of alignment proposals Each lecture features a good deal of audience questions both in the middle and at the end, the idea being to hopefully pre-empt any questions or confusions the listener might have. The full slide deck for all the talks is available here. Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org.

First published

06/22/2023

Genres:

education

Listen to this episode

0:00 / 0:00

Summary

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: The Hubinger lectures on AGI safety: an introductory lecture series, published by Evan Hubinger on June 22, 2023 on The AI Alignment Forum. In early 2023, I (Evan Hubinger) gave a series of recorded lectures to SERI MATS fellows with the goal of building up a series of lectures that could serve as foundational introductory material to a variety of topics in AGI safety. Those lectures have now been edited and are available on YouTube for anyone who would like to watch them. The basic goal of this lecture series is to serve as longform, in-depth video content for people who are new to AGI safety, but interested enough to be willing to spend a great deal of time engaging with longform content, and who prefer video content to written content. Though we already have good introductory shortform video content and good introductory longform written content, the idea of this lecture series is to bridge the gap between those two. Note that the topics I chose to include are highly opinionated: though this is introductory material, it is not intended to introduce the listener to every topic in AI safety—rather, it is focused on the topics that I personally think are most important to understand. This is intentional: in my opinion, I think it is far more valuable to have some specific gears-level model of how to think about AI safety, rather than a shallow overview of many different possible ways of thinking about AI safety. The former allows you to actually start operationalizing that model to work on interventions that would be valuable under it, something the latter doesn't do. The lecture series is composed of six lectures, each around 2 hours long, covering the topics: Machine learning + instrumental convergence Risks from learned optimization Deceptive alignment How to evaluate alignment proposals LLMs + predictive models Overview of alignment proposals Each lecture features a good deal of audience questions both in the middle and at the end, the idea being to hopefully pre-empt any questions or confusions the listener might have. The full slide deck for all the talks is available here. Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org.

Duration

2 hours and 7 minutes

Parent Podcast

The Nonlinear Library: Alignment Forum Weekly

View Podcast

Share this episode

Similar Episodes

AMA: Paul Christiano, alignment researcher by Paul Christiano

Release Date: 12/06/2021

Description: Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: AMA: Paul Christiano, alignment researcher, published by Paul Christiano on the AI Alignment Forum. I'll be running an Ask Me Anything on this post from Friday (April 30) to Saturday (May 1). If you want to ask something just post a top-level comment; I'll spend at least a day answering questions. You can find some background about me here. Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org.

Explicit: No

Details

What is the alternative to intent alignment called? Q by Richard Ngo

Release Date: 11/17/2021

Description: Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: What is the alternative to intent alignment called? Q, published by Richard Ngo on the AI Alignment Forum. Paul defines intent alignment of an AI A to a human H as the criterion that A is trying to do what H wants it to do. What term do people use for the definition of alignment in which A is trying to achieve H's goals (whether or not H intends for A to achieve H's goals)? Secondly, this seems to basically map on to the distinction between an aligned genie and an aligned sovereign. Is this a fair characterisation? (Intent alignment definition from) Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org.

Explicit: No

Details

AI alignment landscape by Paul Christiano

Release Date: 11/19/2021

Description: Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: AI alignment landscape, published byPaul Christiano on the AI Alignment Forum. Here (link) is a talk I gave at EA Global 2019, where I describe how intent alignment fits into the broader landscape of “making AI go well,” and how my work fits into intent alignment. This is particularly helpful if you want to understand what I’m doing, but may also be useful more broadly. I often find myself wishing people were clearer about some of these distinctions. Here is the main overview slide from the talk: The highlighted boxes are where I spend most of my time. Here are the full slides from the talk. Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org.

Explicit: No

Details

Would an option to publish to AF users only be a useful feature?Q by Richard Ngo

Release Date: 11/17/2021

Description: Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Would an option to publish to AF users only be a useful feature?Q , published by Richard Ngo on the AI Alignment Forum. Right now there are quite a few private safety docs floating around. There's evidently demand for a privacy setting lower than "only people I personally approve", but higher than "anyone on the internet gets to see it". But this means that safety researchers might not see relevant arguments and information. And as the field grows, passing on access to such documents on a personal basis will become even less efficient. My guess is that in most cases, the authors of these documents don't have a problem with other safety researchers seeing them, as long as everyone agrees not to distribute them more widely. One solution could be to have a checkbox for new posts which makes them only visible to verified Alignment Forum users. Would people use this? Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org.

Explicit: No

Details