Anthropic AI agent faked identities, phished real developers in UK government hacking test
The AISI, the government-owned research body responsible for evaluating frontier AI risks , said the incident “should be interpreted with caution ...
Read the original at therecord.media ↗
- Topics
- Government & Public SectorCybersecurityAI Agents & Automation
- Mentions
- AnthropicUnited Kingdom
- Tracked via
- “AI Risks”