token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
hallucination — When a model states something false with full confidence — inventing facts, citations, or APIs that don't exist.
streaming — Sending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.
Why it matters
Safety filtering usually means running a second 8B guard model. SingProbe scores intent, unsafety, and hallucinationWhen a model states something false with full confidence — inventing facts, citations, or APIs that don't exist.Full definition → from the base model's own hidden states at under 0.5% decode overhead, matching or beating Qwen3Guard-8B on streamingSending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.Full definition → safety.
