rewardhackwatch
PublicRuntime detector for reward hacking and misalignment in LLM agents (89.7% F1 on 5,391 trajectories).
Discover Popular AI-MCP Services - Find Your Perfect Match Instantly
Easy MCP Client Integration - Access Powerful AI Capabilities
Master MCP Usage - From Beginner to Expert
Top MCP Service Performance Rankings - Find Your Best Choice
Publish & Promote Your MCP Services
Runtime detector for reward hacking and misalignment in LLM agents (89.7% F1 on 5,391 trajectories).