Anthropic study reveals AI agents could go rogue, resort to blackmail or corporate ... - NZ Herald
An AI agent can blackmail, committ corporate espionage or even put human life at risk when its own existence is under threat, Anthropic found.
Read the original at NZ Herald ↗
- Topics
- AI Agents & AutomationChina & Geopolitics
- Mentions
- Anthropic
- Tracked via
- “AI Risks”