ConceptAI & ML
Jailbreaking
A tool or method used to bypass safety guardrails in commercial language models.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Language model safety1Large language models1
Lecturers
2Each in their own terms, from the easiest level.
Matthias Scheutz
Circumventing safety guards to make models output restricted information.
Connections
3The lectures that define it or assume it, and the concepts next to it.