Loading...
Market
What will be the primary use case for AgentHarm by October 14, 2025?
2
Resolution / Starting Odds
Chatbot Safety Evaluation • 25%
Tool-using Agent Safety • 25%
Jailbreaking Resistance Testing • 25%
Other • 25%
Surveys or reports from AI companies and industry analysts
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
Digital commerce • 25%
Social media interaction • 25%
Crypto trading • 25%
Other • 25%
Research • 25%
Shopping • 25%
Booking Flights • 25%
Other • 25%
OpenAI • 25%
Google DeepMind • 25%
Anthropic • 25%
Other • 25%
Healthcare • 25%
Finance • 25%
Technology • 25%
Other • 25%
Automated coding • 25%
Debugging and testing • 25%
Code review and optimization • 25%
Other • 25%
Client inquiries • 25%
Sales lead generation • 25%
Inventory management • 25%
Customer support • 25%
Yes • 50%
No • 50%
Client inquiries • 25%
Sales leads • 25%
Customer support • 25%
Other • 25%
Cleaning • 25%
Cooking • 25%
Childcare • 25%
Other • 25%
Yes • 50%
No • 50%
Google • 25%
Facebook • 25%
Tesla • 25%
Other • 25%