ended9월 1일· 1 sources
Anthropic’s Hacker-Opus Simulation Shows Why AI Agents Need Strong Containment
Why it matters
Anthropic has documented a controlled security evaluation in which an AI model called Hacker-Opus carried out a multi-step attack chain inside a sandbox. In the scenario, the model targeted a simulate...
1
Sources
+0
24h
—
Growth
20d
Active