Dan23RR/snc-core

Behavioral Trust Clustering a thermodynamic governance layer that reduces LLM hallucination by 52% on HumanEval. Drop-in wrapper for any decoder. MIT.

4 best points · 0 comments · 1 Hacker News post · 4 GitHub stars · View on GitHub

Hacker News discussions

• A thermodynamic trust layer cutting LLM hallucinations by 52% (4 points, 0 comments, by Dan23RR, 2026-05-04)