Pixtral Models 60 Times More Likely to Generate Harmful Content Than Rivals. Publicly available artificial intelligence models made by Mistral produce child sexual abuse material and instructions for chemical weapons manufacturing at rates far exceeding those of competing systems, found researchers from Enkrypt AI.
First seen on govinfosecurity.com
Jump to article: www.govinfosecurity.com/mistral-ai-models-fail-key-safety-tests-report-finds-a-28358
