nwjang/psychosis-guard

Trajectory-aware guardrails for LLM chatbots: catches the gradual delusion reinforcement that turn-local safety filters miss

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

Hacker News discussions

• Show HN: Psychosis Guard – Safety for long LLM conversations (1 points, 0 comments, by nwjang, 2026-09-23)