This video provides a tutorial on using Garrick, a large language model vulnerability scanner, to test custom chat bots. Garrick employs probes (test cases) and detectors to identify vulnerabilities, drawing from a large, constantly updated probe library. The tutorial focuses on testing a simple chat application called Wy chat, which utilizes Llama 3 and the Read More …
Tag: LLM
RAG: Giving AI a Better Memory
Imagine you’re trying to answer a tough question, but your brain doesn’t have the specific information. What do you do? You probably look it up – maybe on the internet or in a book. Retrieval-Augmented Generation, or RAG, is a way to give AI models a similar ability. Think of a powerful AI language model as Read More …
Month of AI Video – Hacking AI Infrastructure Providers for Fun
An increasing number of companies are adopting AI-as-a-Service solutions to collaborate, train, and operate their artificial intelligence applications. From emerging AI startups like Hugging Face and Replicate to established cloud providers such as Microsoft Azure and SAP, thousands of customers place their trust in these services, relying on them to handle their proprietary models and Read More …
Month of AI Video – Practical LLM Security
Practical LLM Security As large language models (LLMs) become increasingly integrated into various applications, the security standards for these integrations have not kept pace. Much of the current security research tends to focus on either 1) the social harms and biases associated with LLMs, along with content moderation issues, or 2) the LLMs themselves, often Read More …
LLM – Large Language Model
A non-technical definition………. Imagine you have a friend who is an incredible storyteller. This friend has read thousands of books, articles, and conversations, absorbing all kinds of information about the world. When you ask them a question or give them a topic, they can quickly come up with a thoughtful response, tell a story, or Read More …
NOTES :: Retrieval Augmented Generation (RAG)
A solution model pattern in how to leverage large language models. Systems that use LLM but on their own content. Start Large language models can be inconsistent. Sometimes they nail the answer to questions, other times they regurgitate random facts from their training data. If they occasionally sound like they have no idea what they’re Read More …