Comment by marten-aqua
4 months ago
I’m working on Hyperplane Eval, a local property-based testing tool for AI agents that automatically discovers behavioral failure regions instead of relying on manually written prompts.
4 months ago
I’m working on Hyperplane Eval, a local property-based testing tool for AI agents that automatically discovers behavioral failure regions instead of relying on manually written prompts.
No comments yet
Contribute on Hacker News ↗