AI Ethics with Olle Häggström

AI risk and long-term AI safety short lecture series

Time: February 21-25, 2022

Place: Online, Zoom - register to get the link
Speaker: Olle Häggström
Register here

This six-hour lecture series (in English) will treat basics and recent developments in AI risk and long-term AI safety. The lectures are meant to be of interest to Ph.D. students and researchers in AI-related fields, but no particular prerequisites will be assumed. Some of the basics will be taken from my 2021 book Tänkande maskiner​, but the field is developing rapidly and most of what I say in the lectures will go beyond what I did in the book.

An ambition will be to post recordings of the lectures at CHAIR’s YouTube channel quickly after each lecture, so that participants missing a lecture will have the chance to catch up before the next one.

The three two-hour lectures are scheduled as follows:

1. Monday, February 21 at 15.15-17.00: How and why things might go wrong

2. Wednesday, February 23 at 15.15-17.00: Timelines, natural language processors and oracle AI

3. Friday, February 25 at 10.00-11.45: Research directions in AI alignment


Category Lecture
Location: Online Zoom
Starts: 21 February, 2022, 15:15
Ends: 25 February, 2022, 11:45

Page manager Published: Wed 02 Feb 2022.