# inclusionAI releases SingProbe, a lightweight streaming guardrail for Qwen3.8-Flash-Next

> Original title: inclusionAI/Qwen3.8-Flash-Next-singprobe

- Source: inclusionAI (Ant Ling) · new models on Hugging Face
- Published: 2026-10-27T04:46:49.000Z
- Bad Influence: https://badinfluence.news/items/kyk03yzhu1is3j49ks2ibdbjt
- Original: https://huggingface.co/inclusionAI/Qwen3.8-Flash-Next-singprobe

## Summary

inclusionAI releases SingProbe, a 5.18M-parameter probe on Qwen/Qwen3.8-Flash-Next that scores query intent, response unsafety, and hallucination risk at every generated token using the base model's hidden states. The probe adds less than 0.5% decode-time overhead and posts an 0.8714 F1 on response safety classification across eight benchmarks, against 0.8604 for Qwen3Guard-Gen-8B-strict. Training code is available at inclusionAI/SingProbe, and the probe loads by Hugging Face ID in SGLang or vLLM.