x

LESSWRONG
LW

Sidharth Baskaran — LessWrong

Sidharth Baskaran

0010

https://www.sidbaskaran.com/

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by

No posts to display.

No wikitag contributions to display.

Fluent dreaming for language models (AI interpretability method)

Sidharth Baskaran1y10

Cool followup work here!
https://www.lesswrong.com/posts/hMBTaFvAzdMNnj29c/evolutionary-prompt-optimization-for-sae-feature