Introduction to AI Safety, Ethics, and Society
Course information
- Organized by: Prof. Joschka Boedecker, Shengchao Yan
- Course number on HISinOne: 11LES-510-32
- Location: SR-00-007 in building 106 (TF campus)
- Time: every Wednesday, 16:00 s.t. - 17:30
- Language: English
Overview
AI systems are rapidly developing and are increasingly transforming many areas of our economy and our society. In contrast to this, our understanding of these technologies and the consequences for their large-scale deployment often remains rather limited. In this seminar, we will look at the question of what is needed to ensure that these AI systems can be deployed in a safe, ethical and beneficial way for society. This is a highly interdisciplinary question which goes beyond mere technical problems. Accordingly, we will examine the question from many different viewpoints.
Format
The seminar will rely on in-person attendance. After a short ramp-up phase with an introductory lecture, a lecture on advice for giving scientific presentations, and some time for reading, we will start with presentations and discussions on chapters of the book "Introduction to AI Safety, Ethics, and Society" by Dr. Dan Hendrycks.
Important Note on Selection Criteria for the Seminar
More people seem to be interested in taking the seminar than we can accommodate, which forces us to make a selection. To increase your chances of being able to take part, make sure you select the seminar with priority 1 in HISinOne and potentially send an email to jboedeck@informatik.uni-freiburg.de in which you explain why a slot in the seminar is important to you. Please make sure to prefix the subject line of your email with [ai-safety-sem] so it does not get overlooked. We will consider emails which reach us by noon on Monday, Oct. 20.
Timeline
| Date | Done | Comment | |
| Introductory Lecture | Wednesday, October 15 | x | |
| Advice on scientific presentations | Wednesday, November 5 |
|
|
| Chapter Voting Deadline | Wednesday, November 12 | |
|
| Chapter 1:
Overview of Catastrophic AI Risks |
Wednesday, November 19 | ||
| Chapter 2:
Artificial Intelligence Fundamentals |
Wednesday, November 26 | ||
| Chapter 3:
Single-Agent Safety |
Wednesday, December 10 | ||
| Chapter 4:
Safety Engineering |
Wednesday, December 17 | ||
| Chapter 5:
Complex Systems |
Wednesday, January 7 | ||
| Chapter 6:
Beneficial AI and Machine Ethics |
Wednesday, January 14 | ||
| Chapter 7:
Collective Action Problems |
Wednesday, January 21 | ||
| Chapter 8:
Governance |
Wednesday, January 28 | ||
| Guest talk: tba | Wednesday, February 4 |
Resources
- Course webpage by Dan Hendrycks which includes a wealth of further material such as video lectures, relevant research papers and more: https://www.aisafetybook.com/curriculum
- An audiobook version of the book for the course
- Center for Humane Technology
- Selected TED talks by Yoshua Bengio, Tristan Harris, Stuart Russell, Sam Harris
- The Last Invention Podcast: https://www.longviewinvestigations.com/ (scroll down a bit)
- The Responsible-AI group at University of Freiburg