ojki74/hallucinatoff

Recursive middleware for LLM output regulation. Detects semantic drift, premise flaws, and response risks through multi-order observation. Psychology-informed architecture.

2 best points · 0 comments · 1 Hacker News post · 5 GitHub stars · View on GitHub

Hacker News discussions

• Middleware that catches when LLM conversations slowly drift off-topic (2 points, 0 comments, by ojki, 2026-07-23)