OpenAI and Anthropic's AI systems have launched several 'potentially harmful ' hacks on their own
'Some of the agents being tested had engaged in sustained, potentially harmful activity directed at real people and organisations,' says UK's AI ...
Read the original at the-independent.com ↗
- Topics
- AI Safety & Existential RiskAI Agents & Automation
- Mentions
- AnthropicOpenAIUnited Kingdom
- Tracked via
- “dangerous AI”