Show HN: Psychosis Guard – Safety for long LLM conversations | Hacker News - But Better

Show HN: Psychosis Guard – Safety for long LLM conversations github.com

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

1 points•nwjang•7 days ago•0 comments•

#safety #llm #guard #psychosis #psychosis guard #conversations #long #long llm

0 comments

No comments yet.

Read the full thread on Hacker News →

Related stories

I have some questions for Mark Zuckerbergtheverge.com
The Verge · 0 points · 6 days ago
Emergent Collusion in Long-Horizon LLM Agent Interactionarxiv.org
Hacker News · 1 points · 8 days ago
AI safety conversations have gotten unbelievabletechcrunch.com
Hacker News · 5 points · 11 days ago
Graph World Models for Verified and Efficient Long-Horizon LLM Task Planningacademy.dair.ai
Hacker News · 1 points · 10 days ago
Show HN: Assay – a QA CLI that finds bugs with no LLM and no tests writtengithub.com
Hacker News · 1 points · 2 days ago
Deterministic grounding checks for LLM agents, no LLM in the hot pathgithub.com
Hacker News · 1 points · 10 days ago