o1 System Card: "medium" rating for chemical, biological, radiological, nuclear weapon risk, and it "sometimes instrumentally faked alignment during testing" (Shakeel Hashim/Transformer)

https://ift.tt/ZeAscPf

Shakeel Hashim / Transformer:
o1 System Card: “medium” rating for chemical, biological, radiological, nuclear weapon risk, and it “sometimes instrumentally faked alignment during testing”  —  The o1 safety card reveals a range of concerning capabilities, including scheming, reward hacking, and biological weapon creation.

from Techmeme https://ift.tt/GUMDe4q