brendanhogan/loophole
Adversarial stress-testing of moral principles via AI agents
View on index · View in 3D Map
Related repos
- AI agent for black-box security testing
- Enforces tests and preserves context for AI coding
- Connects AI agents to Wise banking services
- Automates AI coding agents in loops until specifications are met
- Autonomous penetration testing agent with causal reasoning
- Security testing plugin for AI coding agents
- Self-improving AI agent with learning loop
- open-source search tool for AI agents with deep web and reasoning
- Framework for AI agents with verifiable compute
- Framework for building AI agent tools for Deepseek Reasoner
