Mistral Releases New Shieldstral Safety Tool
Shieldstral is a compact 3 billion parameter model designed to act as a digital bouncer. Unlike older systems that are stuck with pre-set rules, this model lets you define your own safety policies using plain language. It checks both text and images to see if they follow your specific guidelines.
This model is impressively efficient. It runs on a single 16GB graphics card and supports 12 different languages. Mistral claims it performs just as well as much larger systems that are seven times its size.
You can find it now on Hugging Face under an open license. It is a great option for developers who need to keep their apps safe without needing massive computing power.
Comments (0)
No comments yet. Be the first!
More AI news
NewsNew AI Tool Fixes Mistakes in Financial Research
Researchers developed a new framework to stop AI from learning from its own bad data in financial trading models.
NewsPerplexity adds local AI to Mac apps
The new update lets your Mac handle some AI tasks directly on your computer.
NewsMeta Releases Muse Image Model on Fal
Meta has launched a new AI model on the Fal platform that plans and edits images on its own.