Alignment
The work of making AI systems pursue the goals and values their builders intend, and behave safely and honestly. A central research focus at the major labs.
“Alignment teams test whether models will deceive or cut corners to finish a task.”
See also
Part of the Extended list
Alignment is on the Extended list: builder jargon, industry terms, and newer slang for when you want to go further. It entered common use around 2023.