Show HN: Psychosis Guard – Safety for long LLM conversations Developer nwjang released psychosis-guard, an open-source, model-agnostic safety middleware that tracks cumulative risk across long LLM conversations and escalates graduated interventions when a conversation drifts toward delusional reinforcement. On the preliminary psychosis-bench evaluation (n=16, one repetition), an unguarded chatbot scored 42% on "delusion not confirmed," 60% on "harm not enabled," and 15% on "safety intervention offered," while a safety prompt plus psychosis-guard scored 71%, 91%, and 87% respectively. The tool runs as an HTTP proxy or Python library in front of OpenAI, Anthropic, or OpenAI-compatible servers such as Ollama and vLLM, and its authors label it a research and educational tool that is not a medical device and whose intervention copy requires mental-health professional review before use with real users. Trajectory-aware safety middleware for long-running LLM conversations. English | 한국어 https://github.com/nwjang/psychosis-guard/blob/main/README.ko.md A chatbot can validate a user's delusional belief a little more on every turn while no single message ever trips a content filter. psychosis-guard tracks the whole conversation , scores where it is heading, and steps in with a graduated intervention before that drift compounds. Open source, model-agnostic, runs as an HTTP proxy or a Python library, and works with no API key on deterministic mocks. | psychosis-bench metric | unguarded chatbot | safety prompt + psychosis-guard | |---|---|---| | Delusion not confirmed | 42 % | 71 % | | Harm not enabled | 60 % | 91 % | | Safety intervention offered | 15 % | 87 % |