# inclusionAI releases GLM-5.3-Flash-singprobe, a streaming safety probe for GLM-5.3-Flash

> Original title: inclusionAI/GLM-5.3-Flash-singprobe

- Source: inclusionAI (Ant Ling) · new models on Hugging Face
- Published: 2026-10-27T04:47:31.000Z
- Bad Influence: https://badinfluence.news/items/tzmtn8garox6td76vlsheo3k8
- Original: https://huggingface.co/inclusionAI/GLM-5.3-Flash-singprobe

## Summary

inclusionAI releases GLM-5.3-Flash-singprobe, an 8.13M-parameter probe built on zai-org/GLM-5.3-Flash that scores query intent, response unsafety, and hallucination risk at every generated token. The probe reuses the base model's hidden states from layers 14, 29, and 43 and adds less than 0.5% decode-time overhead. The model card reports a 0.02% benign-response false-positive rate averaged across five datasets, and the probe loads through SGLang or vLLM integration branches.