Steve's thoughts and experiments

DevOps Engineer, Mentor, budding AI developer

I’m a DevOps Team Lead based in Australia. I'm passionate about building strong, sustainable teams and helping them grow. I'm excited to share my journey in AI development with a focus on security.

Alt text

Latest 3 Posts ↓

View all posts →
Lab 4 Building a RAG pipeline image

Lab 4 Building a RAG pipeline

In this lab, I'm going to move away from security for a little while and look at how we can augment our LLM using a technique called Retrieval Augmented Generation (RAG).

The idea is that we can use a pre-trained LLM to answer questions about a specific dataset. We can then augment the pre-trained model with additional information from a knowledge base. To do this we usually convert the data into a vector space and storing this information in a vector database, like ChromaDB. In this we'll cover:

  • Store text embeddings in ChromaDB (an open source vector database)
  • Retrieve relevant knowledge dynamically
  • Use a local model to generate answers

Read More

The brains behind the machine image

The brains behind the machine

The main interface to the models is a chat interface. When you present a questions or insutrction, how do the models "know" what you mean? How does it understand the relationship between words?

The answer is embeddings!

An embedding is a high-dimensional vector representation of words, phrases or concepts. Instead of memorising words models map them into a numerical space where similar meanings are close together.

Read More

Lab 3 Prompt Injection image

Lab 3 Prompt Injection

Previosuly I've looked at the use of white hat attacks. These test the models as you're training them and should be considered as part of the development process. A prompt injection attack is a type of attack that is used to manipulate the output of a model and is usually an attack of a deployed model.

Large language models generate responses based on user inputs and hidden system instructions. A prompt injection attack exploits this by tricking the AI into ignoring its original constraints, leading to unsafe, unintended, or malicious outputs.

Read More

4 more posts can be found in the archive.