Loading activity…
@lauraruis
Postdoc with @jacobandreas @MIT_CSAIL. PhD from @ucl_dark with @_rockt and @egrefen. Anon feedback: https://www.admonymous.co/laura-ruis
AI
In the authors' tests, changing opening tokens mainly helped models add or restyle information, not consistently leave it out.
AI
Researchers report that repeated training on a 100M-token natural-language corpus beat every synthetic curriculum in their compute-matched tests.
AI
Adam Karvonen posted results from training models on self-generated explanations of in-the-wild behaviors.
AI
The Center for AI and Biosecurity invites applications for its 10-week research program.
AI
The AI interpretability company announces access to its research tool.
