antistatic.exchange
Register Log in

Google DeepMind safety capability thresholds

By end of 2026 By end of 2026
2.0%
Adjust month-by-month → →
By end of 2027 By end of 2027
17.6%
Adjust month-by-month → →
By end of 2028 By end of 2028
37.7%
Adjust month-by-month → →
By end of 2029 By end of 2029
57.2%
Adjust month-by-month → →
By end of 2030 By end of 2030
71.6%
Adjust month-by-month → →
Log in to submit a forecast.

2 comments

Log in to comment.

1

Google published the Gemini 4 Argon model card and Safety & Security Report with the wider launch on October 13. Its Frontier Safety Framework table marks two of this market's CCLs as "CCL cannot be ruled out":

  • Cyber Uplift Level 1: Google says the model gives substantial uplift on its evaluations and quantitative modelling. It solved all 12 end-to-end simulated cyberattack scenarios, against five for the previous generation.
  • CBRN Uplift Level 1, biological information risk only: in two expert red-teaming scenarios the model gave measurable uplift over web baselines. Chemical, radiological and nuclear rule out even the lower TCL.

For both, Google built a CCL safety case before launch and says its safeguards bring the risk below the CCL. ML R&D Acceleration 1 and ML R&D Automation 1 are marked "CCL not reached". The Stealth and Situational Awareness TCL also cannot be ruled out (14 of 15 challenges passed).

The report says Google designates a model as “cannot rule out being at the CCL” when it cannot rule out that a threshold has been reached, and mitigates on that basis. The executive summary describes the model as approaching these thresholds. These criteria require a report that a model meets a CCL, so whether this designation counts is a question for the resolver.

1

Google's cost model puts unmitigated Argon's uplift across 22 severe historical cyberattacks at 9x to 100x, a geometric mean of about 16.7x lower cost. Older Cyber Uplift 1 wording set the bar at a cost reduction of "an order of magnitude or more". Safety & Security Report, p. 40