AI safety takes

Share this post

User's avatar
AI safety takes
September/October 2023 safety news: Sparse autoencoders, A is B is not B is A, Image hijacks
Copy link
Facebook
Email
Notes
More

September/October 2023 safety news: Sparse…

Daniel Paleka
Oct 17, 2023
3

Share this post

User's avatar
AI safety takes
September/October 2023 safety news: Sparse autoencoders, A is B is not B is A, Image hijacks
Copy link
Facebook
Email
Notes
More

Better version of the Twitter thread.

Read →
Comments
User's avatar
© 2025 Daniel Paleka
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture

Share

Copy link
Facebook
Email
Notes
More