New method aims to keep kids safe from illegal AI -generated content | MIT News
Researchers developed an evaluation procedure that tests generative AI models for harmful capabilities without generating outputs.
Read the original at news.mit.edu ↗
- Topics
- AI Safety & Existential RiskLegal & CourtsMarkets & InvestmentChatbots & LLMs
- Mentions
- MIT
- Tracked via
- “dangerous AI”