Psychosis Guard

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

Description excerpted from the original listing, which is linked below.

Open it Listing

Facts

Published: 2 Sep 2026 (12d ago)
Medium: web
Language: English (the page says so itself)
Subject: Writing and language
First seen: 14 Sep 2026, 02:50 UTC

Built with

Claude Code: confirmed
the agent's own trailer in the repository's commit history

What we can see

77 hygiene score

Certificate issued by YR1, 47 days remaining
Cookie attributes no cookies set
Credentials and payment does not ask for either
Strict transport security set
Served over HTTPS
Mail authentication neither published
No insecure resources
Redirects none
Security headers 0 of 5 set
Third-party origins 3
Transport security TLS 1.3

Observed 14 Sep 2026 by fetching the page as a browser would. This describes hygiene and transparency, not safety: a missing header does not make a site dangerous, and a complete set does not make it trustworthy.

Changes we have seen

14 Sep 2026 first indexed