Performance Testing Retrieval-Augmented Generation (RAG) with Ragas

Alice's Adventures in Wonderland

Ever wondered how well Retrieval-Augmented Generation (RAG) can perform with a classic like Alice's Adventures in Wonderland? I recently used the RAG Assessment (ragas) Python module to automatically create a set of Q&A and then performance benchmark different configurations. Some of the results were surprising.

Dive into my detailed …

more ...

Building a Wine Classifier Using Review Data

Wine Classifier

Ever felt lost when a sommelier throws out words like "Rhubarb hangs out with cherry cider and the mellowest cinnamon" to describe a wine? ‍ Well - me too!

At the end of last week I was on a quest to bridge the gap between flowery descriptions and actual grape varieties! Inspired …

more ...

Tortoise TTS

Tortoise TTS

While text-to-image and text-to-text take most of the Generative AI headlines, the field of text-to-speech (TTS) continues to make steady progress. Recently, I explored the capabilities of Tortoise-TTS, an open-source framework for building high-fidelity TTS systems.

I've captured my research and experimentation in a Jupyter notebook. You can find it …

more ...

Llama 3 Release - Performance Benchmarks

Performance Improvements
source: https://ai.meta.com/blog/meta-llama-3/

🔥 Meta's latest release, Llama 3, has delivered an impressive set of Large Language Model (LLM) benchmarks. While the 8B and 70B parameter models show impressive results against closed-source and open-source models such as Claude, Gemini and Mistral, it's interesting to compare improvements of …

more ...

Hidden Potential By Adam Grant - Key Takeaways Relating to Education

Hidden Potential By Adam Grant

I recently read the exceptional book, Hidden Potential by Adam Grant. It's choc-full of insights backed up by world class research. I captured my key takeaways around education.

Finland excels in the Programme for International Student Assessment (PISA) - Maths, Reading and Science - due to its unique culture:

  • Emphasis on potential …
more ...


Top Threat Actor Trends: Motivations and Attack Vectors

Threat Actor Trends

Threat actors, also known as bad actors, are individuals or groups who deliberately engage in malicious activities such as hacking, phishing and other cyber crimes with the intent to harm systems, networks or data. These actors are driven by various motivations, including financial gain, political ideology, grievances or vendettas.

In …

more ...

AI-Powered Image and Video Processing: The Future of Communication

Luxo Jr.

Pixar - Luxo Jr.

As a child, I was captivated by the earliest animated shorts produced by Pixar. The combination of groundbreaking computer graphics and storytelling brought the characters to life. I can still vividly remember watching Luxo Jr bounce across the screen, chasing, playing and eventually puncturing a small blue …

more ...

AI in Children's Education

Intelligent AI Agents Helping Children Learn

I am excited about the potential for good that Artificial Intelligence (AI) has in the education system. Every child is unique, with different interests, natural abilities and preferred ways of learning. AI can be used to personalise learning for each child, providing them with the content and instruction that they …

more ...

Survivorship Bias

Survivorship Bias

Survivorship bias is a type of sampling bias where only data points that represent survivors of a process or event are used to train a model. This can lead to inaccurate or biased conclusions, as the model will only be able to predict the outcomes of events that are similar …

more ...