Anthropic's ASL-3 deployment measures are narrowly scoped to preventing model assistance with extended end-to-end CBRN weapons workflows (initially focused on biological weapons) and to blocking universal jailbreaks, explicitly excluding non-universal jailbreaks and commonly available single pieces of information.

supports (2)

• SActivating AI Safety Level 3 protections primary_testimony
  weight

  0.85

  locator: Footnote 3

  “Initially they are focused exclusively on biological weapons as we believe these account for the vast majority of the risk”

• SActivating AI Safety Level 3 protections primary_testimony
  weight

  0.90

  locator: Deployment Measures section

  “ASL-3 deployment measures do not aim to address issues unrelated to CBRN, to defend against non-universal jailbreaks, or to prevent the extraction of commonly available single pieces of information”