Tag

#ai-security

4 articles

$Mistral's open model Shieldstral matches much larger safety models at a fraction of the size$

Mistral's open model Shieldstral matches much larger safety models at a fraction of the size

Learn to implement and use Mistral's open-source Shieldstral 3B safety model for content analysis. This tutorial teaches you how to load the model, create safety prompts, and interpret natural language responses for detecting safety violations.

Aug 521

Hackers are learning to exploit chatbot ‘personalities’

Learn to create and test AI chatbot personalities using Python and OpenAI API. Understand how hackers exploit chatbot personalities and how to protect against such attacks.

May 2477

OpenAI Agents SDK improves governance with sandbox execution

Learn to implement sandbox execution using OpenAI's Agents SDK for secure, governed AI workflows that balance flexibility with enterprise security requirements.

Apr 1696

tech

Perplexity AI sued over alleged data sharing with Meta and Google

Learn to build a privacy-focused data handling system that monitors and logs data sharing activities while maintaining user privacy through encryption and access controls.

Apr 1117

#ai-security

Mistral's open model Shieldstral matches much larger safety models at a fraction of the size

Hackers are learning to exploit chatbot &#8216;personalities&#8217;

OpenAI Agents SDK improves governance with sandbox execution

Perplexity AI sued over alleged data sharing with Meta and Google

Hackers are learning to exploit chatbot ‘personalities’