LESSWRONG
LW

Sidharth Baskaran

0010

https://www.sidbaskaran.com/

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by

No wikitag contributions to display.

Fluent dreaming for language models (AI interpretability method)

Sidharth Baskaran10mo10

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

No posts to display.