harm-containment

Here is 1 public repository matching this topic...

leexiaoyi-lab / HDHC-Protocol

Open, falsifiable AI safety evaluation framework and benchmark for AI decision systems, testing human dignity × harm containment, minimum sufficient intervention, victim protection, reversibility, and return paths.

benchmark ai-safety red-teaming ai-alignment ai-evaluation reversibility safety-evaluation human-agency human-dignity harm-containment

Updated Sep 19, 2026
Python

Add this topic to your repo

To associate your repository with the harm-containment topic, visit your repo's landing page and select "manage topics."

Learn more