Why scale, personalisation, unclear provenance, and diffusion of AI-generated content require us to act now — What is this about? “Why do you think responsible Generative AI (GenAI) is important and urgent?” This is a question being posed today by policymakers, researchers, journalists, and concerned citizens alike. Rapid progress in GenAI has captured public imagination, but also raised pressing ethical questions. Models like ChatGPT, Bard, and Stable Diffusion showcase the…

How to check whether the newest, hottest Large Language Model (LLM) fits your needs — What is this about? New LLMs are released every week, and if you’re like me, you might ask yourself: Does this one finally fit all the use cases I want to utilise an LLM for? In this tutorial, I will share the techniques that I use to evaluate new LLMs. I’ll introduce three techniques…

A Step-by-Step Guide to Building a Privacy-Conscious Open-Source Document Chatbot — What is this about? Over the past two weeks, several exciting developments have transpired in the open-source Large Language Model (LLM) community. The Technology Innovation Institute has unveiled their Falcon models, and Hugging Face has released a new docker container designed for LLM deployment on Amazon SageMaker. These advancements have empowered me to develop…

Leverage OpenAI’s APIs to bypass the official ChatGPT app — What is this about? When GPT-4 was announced on 14 March 2023, I immediately signed up for ChatGPT Plus — a paid tier within the ChatGPT application that offered access to the new model right away. It cost $20 per month and was well worth it in the beginning. However, after a few days…

Now you can deploy LLMs and experiment with them all in one place — What is this about? Utilising large language models (LLMs) through a REST endpoint offers numerous benefits, but experimenting with them via API calls can be cumbersome. Below we can see how we can interact with a model that has been deployed to an Amazon SageMaker endpoint.

This model is “something else” 🤯 — What is this about? This is blog post is about the first few tests I ran with the new GPT-4 model. Spoiler alert: It’s impressive! Chain of thought reasoning Let’s start with the title image. In this case we ask GPT-4 a very convoluted question that requires multiple chains of reasoning. Not only does it get the answer…

The Hugging Face + AWS partnership makes it easier than ever to experiment with open-source state-of-the-art language models — What is this about? Google recently released the Flan-UL2 model, which has 20B parameters and has a better performance than FLAN-T5 XXL on several benchmarks. Most importantly, it was released under the Apache 2.0 license which allows to use the model for commercial use. Despite its size of 20B parameters, the model can still…

Building a Modular Reasoning, Knowledge and Language (MRKL) system using prompt chaining — What is this about? During this tutorial, we will explore how to supercharge Large Language Models (LLMs) with LangChain. The focus of this tutorial will be to build a Modular Reasoning, Knowledge and Language (MRKL) application that uses LLMs + LangChain. This MRKL app will incorporate features such as web search, scientific search, and…

Deploy a text-to-image web app with just one command — What is this about? Stable Diffusion (SD) has quickly become one of the most popular text-to-image (a.k.a. “AI Art Generation”) models in 2022. One key factor contributing to its success is that it has been made available as open-source software. This spawned a vibrant community that quickly built tools to make SD more accessible…