AI Research1 min reading time

Mistral Voxtral 3

Product Hunt
Read the full article
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


More in AI Research

AI Research13 min read

What Is Data Poisoning? How Attackers Corrupt AI Models and Datasets

Unite.AI
AI Research1 min read

Shadow Computation Threatens CoT Monitorability

LessWrong
AI Research3 min read

Anthropic’s AI Hid a Secret Message in the Stars. OpenAI’s Bot Found It.

Gizmodo