Get the app
AI Research1 min reading time

Shieldstral

Product Hunt
Read full post
Mistral AI has released Shieldstral, a 3-billion parameter open-weight multimodal guardrail model that allows users to define safety policies in natural language during inference. It can evaluate text and images simultaneously and runs locally on a single 16GB GPU.

More on this story

#mistral-ai#multimodal-models#open-source-ai#runtime-safety#shieldstral

More in AI Research

AI Research4 min read

An Anthropic researcher just quit, saying OpenAI and Anthropic are 'gambling with our lives'

Covered by 13 sources
AI Research10 min read

Anthropic Details Disrupted Claude Misuse Across Seven Harm Areas

Covered by 4 sources
AI Research4 min read

OpenAI asks Congress for mandatory national AI safety rules before it adjourns

Covered by 2 sources