alignment-evaluation

Here are 2 public repositories matching this topic...

Read-only mirror of MSTP-1.0, a non-canonical protocol for detecting ethical mimicry in AI systems, with companion guide and verified hashes.

Boundary-respect evaluation framework for autonomous LLM agents — from the pilot where Claude refused to confabulate $20K

Add a description, image, and links to the alignment-evaluation topic page so that developers can more easily learn about it.

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