المتتبّع

CR-K32

بوادر أولى

Frontier models may give meaningful bio/chem uplift to novices; developers added safeguards because they could not exclude it.

تاريخ التصريح
القائل
International AI Safety Report 2026
الموعد
—
آخر تحقق من الحالة
28 سبتمبر 2026

المصدر

الأدلة حتى الآن

22 May 2025: Anthropic activated ASL-3 protections for Claude Opus 4 as a precaution (Anthropic [S]). No public evidence found of an AI-enabled bio/chem attack.

المؤشر التالي

System cards; independent evaluations