robertskmiles

Early Access: 6 New AI Safety Talks (Patreon)

Published:

2023-05-10 15:12:29

Imported:

2026-06

Tags:

AI Safety Talks early access early access video talk

haven't archived this post yet. have a subscription? use the importer!

Content

Lots of stuff in the pipeline, but to start with here's a series of 6 new talks from Evan Hubinger (author of Risks From Learned Optimization, the Mesa-Optimizers paper), going through a load of interesting AGI Safety Ideas.

https://www.youtube.com/watch?v=NmDRFwRczVQ&list=PLtlVeM84bZ6RLSR6oaQnbZ7FSwb-hkapx

Probably Patreon will just embed the first one, but that link is for the playlist of all of them

Files

Previews only

1:AGI Safety: Evan Hubinger 2023

Part 1 of a series of talks in which researcher Evan Hubinger explores the problems of safety for artificial general intelligence This was recorded as part of the SERI ML Alignment Theory Scholars Program: https://serimats.org