Print-friendly view · use your browser's Save as PDF option (Cmd/Ctrl-P) to attach this article to a brief.

Google DeepMind Frontier Safety Framework

DEEPMIND-FSF-2024 · US · voluntary code

Source: https://policywindow.org/wiki/deepmind-fsf

Generated 2026-05-30T22:09:34 UTC

Summary

Critical Capability Levels (CCL) regime spanning autonomy, biosecurity, cybersecurity, and persuasion domains. Distinct vocabulary from Anthropic ASL + OpenAI Preparedness — designed for cross-domain elicitation; each CCL triggers domain-specific mitigations including model-weight access controls + enhanced red-teaming. Seoul Frontier AI Safety Commitments signatory. Alphabet-published; effective across Google DeepMind frontier-model releases.

At a glance

Adopted: 2024-05-17
Effective: 2024-05-17
Status: in force
Primary source: Google DeepMind Frontier Safety Framework (May 2024)
Source URL: https://deepmind.google/discover/blog/introducing-the-frontier-safety-framework/

How to cite this article

APA

Policy Window. (2024). Google DeepMind Frontier Safety Framework [Wiki article — Instrument]. https://policywindow.org/wiki/deepmind-fsf

Chicago

Policy Window. 2024. "Google DeepMind Frontier Safety Framework." Wiki article (Instrument). https://policywindow.org/wiki/deepmind-fsf.

Harvard

Policy Window (2024) 'Google DeepMind Frontier Safety Framework', Wiki article — Instrument, available at: https://policywindow.org/wiki/deepmind-fsf.

OSCOLA

Policy Window, 'Google DeepMind Frontier Safety Framework' (Wiki article — Instrument, 2024) <https://policywindow.org/wiki/deepmind-fsf> accessed [date].

BibTeX

@misc{policywindow-deepmind-fsf,
  title  = {Google DeepMind Frontier Safety Framework},
  author = {Policy Window},
  year   = {2024},
  howpublished = {Google DeepMind Frontier Safety Framework (May 2024)},
  url    = {https://policywindow.org/wiki/deepmind-fsf},
  note   = {Primary source: https://deepmind.google/discover/blog/introducing-the-frontier-safety-framework/}
}