Llama Firewall: Comprehensive Guardrails for LLM Applications
A brief on Llama Firewall from Meta, a comprehensive system of guardrails for securing LLM applications and agents.
Topic
AI/ML
A collection of posts on artificial intelligence and machine learning.
Content Safety with Llama Guard and Groq
A brief on content safety (according to MLCommons taxonomy) using Meta Llama Guard and Groq Cloud.
CSA AI Controls Matrix: A Sneak Preview
A sneak preview into CSA AI Controls Matrix, the latest framework addressing AI security needs.
LLM Safety and Security with Google Cloud Model Armor
A brief on Google Cloud Model Armor, a fully managed service for the safety and security of LLM applications.
Detect Jailbreaks and Prompt Injections with Meta Prompt Guard
A brief on detecting prompt attacks like injection and jailbreaks using Meta Prompt Guard.
MLCommons: Towards Safe and Responsible AI
A brief on MLCommons, along with their AI Safety taxonomy of hazards, and benchmarks.
Protect Jupyter Notebooks with NB Defense Extension
A step-by-step guide on protecting Jupyter notebooks with NB Defense, an open-source extension by Protect AI.
Blinkist for URLs with LlamaIndex and OpenAI
A brief guide to AI-generated web URL summaries with LlamaIndex and OpenAI.
Chat with PDF using LlamaIndex and LlamaParse
A step-by-step guide on chatting with a PDF document using LlamaIndex, LlamaParse and OpenAI.
Running Open-Source Generative AI Models on Fireworks AI
A brief on running open-source text and image generation models on Fireworks AI.