Governing AI Agents with Democratic 'Algorithmic Institutions' | TechPolicy.Press
A recent disclosure by Anthropic illustrates this risk , showing how attackers exploited an AI system's agentic features to carry out harmful actions.
Read the original at Tech Policy Press ↗
- Topics
- AI Agents & AutomationRegulation & Policy
- Mentions
- Anthropic
- Tracked via
- “AI Risks”