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 released Gemini 4 Hydrogen on November 12. Its model card says targeted testing found it does not reach the bio or cyber CCLs (alert thresholds reached); ML R&D and manipulation CCLs not reached, carried forward from Argon. Its Safety & Security Report is "coming soon". model card

1

Google published Hydrogen's Safety & Security Report on November 16. Unguarded Hydrogen solved 9/14 CyScenarioBench challenges (86/104 segments) vs. Argon's 13/14 and Carbon's 12/14, reached 84.6% on ExploitBench (Carbon 97%) and 68.1% Pass@1 on CWE-bench v2 (Argon 65.0%), and scored markedly below Argon on BIO-1/BIO-2, ruling out both CCLs. report