Stats

2

Projects

Latest Projects

groundlens

10/14/2026
Guardrails for LLM answers. Checks an LLM answer against its sources without a model, decides PASS, REVIEW or FAIL under your policy, and keeps a signed record.

hallucination-benchmark

2/10/2026
Open dataset of 212 human-written confabulation pairs across nine domains. CC BY 4.0.