An efficient, reusable framework to evaluate AI safety - The Hub - Johns Hopkins University
The sustainable method developed by researchers at Johns Hopkins and Microsoft simulates risks within large language models to prevent harm before ...
Read the original at JHU Hub ↗
- Topics
- Governance & Risk ManagementAI Safety & Existential RiskEducationChatbots & LLMs
- Mentions
- Microsoft
- Tracked via
- “AI Risks”