AI safety technical research (Topic archive) - 80,000 Hours

Selected highlights

#44 – Paul Christiano on how OpenAI is developing real solutions to the ‘AI alignment problem’, and his vision of how humanity will progressively hand over decision-making to AI systems

Podcast by Robert Wiblin and Keiran Harris · Published October 2nd, 2018

ML engineering for AI safety & robustness: a Google Brain engineer’s guide to entering the field

Article by Catherine Olsson and the 80,000 Hours team · Published November 2018

AI safety syllabus

Article by The 80,000 Hours team · Last updated August 2016 · First published August 2016

#23 – Jan Leike on how to become a machine learning alignment researcher

Podcast by Robert Wiblin and Keiran Harris · Published March 16th, 2018

Machine Learning PhDs

Career review by Richard Batty · Published June 2017

#47 – PhD or programming? Fast paths into aligning AI as a machine learning engineer, according to ML engineers Catherine Olsson & Daniel Ziegler

Podcast by Robert Wiblin and Keiran Harris · Published November 2nd, 2018

All content tagged "AI safety technical research"