CR-K32
Emerging
Frontier models may give meaningful bio/chem uplift to novices; developers added safeguards because they could not exclude it.
- Claim made
- Who
- International AI Safety Report 2026
- Target date
- —
- Status checked
- 28 September 2026
Source
IASR 2026 [F]
Evidence to date
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.
Next indicator
System cards; independent evaluations