Introducing Shieldstral.

За 30 секунд

Что произошло

Mistral released Shieldstral, a 3B open-weights multimodal safety classifier that accepts plain-language policies at inference time without retraining.

Почему это важно

Engineers building content moderation systems who need to adapt safety rules across different products, audiences, or deployment contexts without model retraining.

На что обратить внимание

Model is 3B parameters and runs on single 16GB GPU, so performance on very large-scale deployments or extremely nuanced safety policies remains unproven in practice.