Loading...
Market
Which region will first mandate AgentHarm for AI safety evaluations by end of 2025?
2
Resolution / Starting Odds
United States • 25%
European Union • 25%
China • 25%
Other • 25%
Government or regulatory announcements
Story
AI Safety Institute and Gray Swan AI Release AgentHarm to Measure LLM Agent Harmfulness, Address Jailbreaking
Oct 14, 2024, 12:05 PM
The AI Safety Institute (AISI) and Gray Swan AI have announced the release of AgentHarm, a benchmark designed to measure the harmfulness of large language model (LLM) agents. This dataset aims to evaluate the unique harms posed by AI agents with access to external tools. The collaboration emphasizes the importance of moving beyond simple chatbot evaluations to assess the safety of more complex agent tasks. AgentHarm is described as easy to run, comprehensive, and reliable, and it is partly public, allowing broader accessibility for safety evaluations. The dataset also addresses concerns about jailbreaking and robustness in LLM agents.
View original story
Similar markets
United States • 25%
European Union • 25%
China • 25%
Other • 25%
OpenAI • 25%
Google DeepMind • 25%
Anthropic • 25%
Other • 25%
United States • 25%
United Kingdom • 25%
Canada • 25%
Australia • 25%
United States • 25%
China • 25%
India • 25%
Other • 25%
United States • 25%
European Union • 25%
China • 25%
Other • 25%
European Union • 25%
United States • 25%
China • 25%
Other • 25%
United States • 25%
China • 25%
European Union • 25%
Other • 25%
US • 25%
EU • 25%
China • 25%
Other • 25%
United States • 25%
United Kingdom • 25%
European Union • 25%
Other • 25%
United States • 25%
China • 25%
European Union • 25%
Other • 25%
United States • 25%
European Union • 25%
China • 25%
Other • 25%
U.S. Senate • 25%
U.S. House of Representatives • 25%
Centers for Medicare & Medicaid Services • 25%
Department of Health and Human Services • 25%