DeepMind's Frontier Safety Framework v3 adds a Critical Capability Level for harmful manipulation, defined as AI models with manipulative capabilities powerful enough to systematically and substantially change beliefs and behaviors in identified high-stakes contexts over the course of user interactions.

supports (1)

• SStrengthening our Frontier Safety Framework primary_testimony
  weight

  0.95

  locator: Section: Addressing the risks of harmful manipulation

  “we're introducing a Critical Capability Level (CCL) focused on harmful manipulation --- specifically, AI models with powerful manipulative capabilities that could be misused to systematically and substantially change beliefs and behaviors in identified high stakes contexts”