Rauno Arike

[Question] What faith­ful­ness met­rics should gen­eral claims about CoT faith­ful­ness be based upon?

On the Im­pli­ca­tions of Re­cent Re­sults on La­tent Rea­son­ing in LLMs

The Best Lec­ture Series on Every Subject

Rauno’s Shortform

A Dialogue on De­cep­tive Align­ment Risks

[In­terim re­search re­port] Eval­u­at­ing the Goal-Direct­ed­ness of Lan­guage Models

Early Ex­per­i­ments in Re­ward Model In­ter­pre­ta­tion Us­ing Sparse Autoencoders

Ex­plor­ing the Lot­tery Ticket Hypothesis

[Question] Re­quest for Align­ment Re­search Pro­ject Recommendations

Coun­ter­ing ar­gu­ments against work­ing on AI safety

Clar­ify­ing the con­fu­sion around in­ner alignment