Mistral AI 发布 Shieldstral 1.0 3B：开源策略自适应多模态安全分类器，性能媲美 7 倍规模模型

Mistral AI has released Shieldstral 1.0 3B, an open-weights, policy-adaptive multimodal safety classifier that treats content moderation as a single yes/no question rather than a fixed taxonomy of harm categories.