Espiritdescali@futurology.todayM to

Futurology@futurology.todayEnglish · 1 month ago

Claude Sonnet 3.7 (often) knows when it’s in alignment evaluations — Apollo Research

www.apolloresearch.ai

0

1

Claude Sonnet 3.7 (often) knows when it’s in alignment evaluations — Apollo Research

www.apolloresearch.ai

Espiritdescali@futurology.todayM to

Futurology@futurology.todayEnglish · 1 month ago

0

We evaluate whether Claude Sonnet 3.7 and other frontier models know that they are being evaluated.

You must log in or register to comment.

Chat