Claude Sonnet 5 includes safeguards against dangerous cyber use - Help Net Security
The model can perform routine, non- harmful security work, but scored lower than Opus 4.8 and Mythos 5 on dangerous cybersecurity tasks. It cannot ...
Read the original at Help Net Security ↗
- Topics
- CybersecurityAI Safety & Existential Risk
- Mentions
- AnthropicClaude
- Tracked via
- “dangerous AI”