AI safety takes
Subscribe
Sign in
Share this post
AI safety takes
November/December 2023 safety news: Weak-to-strong generalization, Superhuman concepts, Google-proof benchmark
Copy link
Facebook
Email
Notes
More
November/December 2023 safety news…
Daniel Paleka
Dec 27, 2023
5
Share this post
AI safety takes
November/December 2023 safety news: Weak-to-strong generalization, Superhuman concepts, Google-proof benchmark
Copy link
Facebook
Email
Notes
More
Better version of the Twitter newsletter.
Read →
Comments
Share
Copy link
Facebook
Email
Notes
More
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
Share this post
November/December 2023 safety news…
Share this post
Better version of the Twitter newsletter.