arXiv:2605.06846v3 Announce Type: replace-cross Abstract: Recent work identifies secret loyalties as a distinct threat from standard backdoors. A secret loyalty causes a model to covertly advance the interests of a specific principal while appearing to operate normally. We construct the first model organisms of narrow secret loyalties. We...
Les hele artikkelen hos kilden.
Kommentarer (0)
Ingen kommentarer ennå. Bli den første til å kommentere!