29

Dec

'22

But is it really in Rome? Limitations of the ROME model editing technique

2 min read

28

Dec

'22

An incomplete list of projects I'd like to work on in 2023

1 min read

18

Dec

'22

(Linkpost) Results for a survey of tool use and workflows in alignment research

1 min read

15

Dec

'22

How learning efficiently applies to alignment research

2 min read

06

Dec

'22

Differential Training Process: Delaying capabilities until inner aligned

3 min read