David Krueger

davidscottkrueger.com

No followers

community-curated profile

Cambridge faculty - AI alignment, deep learning, and existential safety.
Formerly Mila, FHI, DeepMind, ElementAI.

Overview Posts Content Recommendations

Article May 23, 2023

How Rogue AIs may Arise

by Yoshua Bengio

Recommended by 1 person

1 mention by David Krueger

Paper Feb 22, 2023

The alignment problem from a deep learning perspective

by Richard Ngo and Sören Mindermann

Recommended by 1 person

2 mentions by David Krueger

Paper Feb 22, 2023

Natural Selection Favors AIs over Humans

by Dan Hendrycks

Recommended by 1 person

1 mention by David Krueger

Tweet Apr 18, 2023

I find it kind of bizzare that people are saying that like the real AI safety argument wasn't wheather the system could understand you it was getting it to care. Like, maybe these people have always been saying that concrete problems in AI safety w

by Nathan Barnard

Recommended by 1 person

1 mention by David Krueger

Article Jan 11, 2023

Alignment is not enough

by Alan Chan

Recommended by 1 person

1 mention by David Krueger

Tweet Nov 12, 2022

🧵 to clarify my views on AGI, timelines, and x-risk. TL;DR: My AGI timelines are short-ish (within two decades with things getting weird soon) and I think x-risk is real, but I think probabilities of doom by AGI instrumentally opting to kill us are g

by Joshua Achiam

Recommended by 1 person

1 mention by David Krueger

Article Oct 19, 2022

Response to Katja Grace's AI x-risk counterarguments - LessWrong

by Erik Jenner

Recommended by 1 person

1 mention by David Krueger