AIThe Decoderabout 3 hours ago
Mistral launches Shieldstral AI safety model
1 min read
Mistral AI introduced Shieldstral, a 3-billion-parameter open-weight safety model that classifies AI inputs and outputs via natural language yes-or-no questions. It matches or outperforms models seven times its size, scoring 84.9% on text safety and 83.8% on multimodal image safety benchmarks.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyMistral
Summary by ByteBrief
