Concepts
Jailbreak
A jailbreak is a message crafted to trick an AI into ignoring its own safety rules, often through role-play, hypotheticals, or an invented emergency. The name comes from breaking out of the limits the maker set. Model makers keep patching them and people keep finding new ones.
This entry has not yet received a source-reviewed lesson update.
Member lesson
The definition and sources are public. The complete practical lesson is for members.