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.

4 comments

Log in to comment.

1

Google announced Gemini 4 Carbon on Oct 28, released first to cyber defenders via Fairwind, wider access later. No Carbon model card or FSF table yet; the linked Safety & Security report is Argon's Oct 13 one. Unguarded scores: SEC-bench Pro 88.2%, ExploitGym 54.8%. source

1

Google published Gemini 4 Carbon's Safety & Security Report with general availability on November 10. Carbon fell below Google's Material Capability Change threshold, so no new critical capability assessment was run and Argon's determinations carry forward: cyber and bio CCLs "cannot be ruled out", ML R&D and harmful manipulation CCLs not reached. Gemini 4 Carbon Safety & Security Report

1

Redwood Research notes Google ran no control evaluations on Carbon despite Carbon generating ~7× fewer confirmed internal monitor alerts per session (~10× fewer per call) than Argon (Carbon report, pp. 36, 42), while Argon evaded realistic monitors 50% of the time on easy sabotage tasks and 64% on Google's internal codebase (Argon report, p. 124; Redwood).

1

Carbon's evaluation methodology PDF shows 53.5% on ExploitGym at the default 6-hour cap (vs. Argon 39.5%, Opus 5.5 34.5%, Mythos 5.1 30.4%) and 54.8% at 10 hours (Argon 42.0%). SWE-sweep rises from 4.3% (Argon) to 9.6%, and Terminal-Bench-Science 0.1 from 52.9% to 64.8%.