Not to pick on Sebastian Bubeck in particular, but if auto-complete-on-steroid can “blow his mind,” imagine the effects on the average user. Developers and data practitioners use LLMs every day to generate code, synthetic data, and documentation. They too can be misled by inflated capabilities. It’s when humans over-trust their tools that mistakes happen. TL;DR:…

Photo by Nadine Shaabana on UnsplashDistance as a measure of difference This article discusses three measures of distance: (1) the Earth Mover’s Distance (EMD; Rubner et al., 1998); (2) the Word Mover’s Distance (WMD; Kusner et al., 2015); and (3) the Concept Mover’s Distance (CMD; Stoltz & Taylor, 2019). These measures build on one another…

Setting the foundations right Photo by Konta Ferenc on UnsplashIn the previous two articles we saw how we can implement a basic classifier based on Rosenblatt’s perceptron and how this classifier can be improved by using the adaptive linear neuron algorithm (adaline). These two articles cover the foundations before attempting to implement an artificial neural…

A step-by-step guide on deploying LlamaIndex RAGs to AWS ECS fargate Image generated by DALL-E 3 by the author· IaC Self-Service · High-Level Deployment Diagram · Overview of Pipelines · Infrastructure Pipeline ∘ terraform-aws-modules ∘ Implementation Prerequisites ∘ Step 1: Create GitHub environments ∘ Step 2: Add infrastructure pipeline code ∘ Step 3: Add…

LLMs today suffer from inaccuracies at scale, but that doesn’t mean you should cede competitive ground by waiting to adopt generative AI. Building an AI-ready workforce with data.world OWLs, as imagined by OpenAI’s GPT-4Every enterprise technology has a purpose or it wouldn’t exist. Generative AI’s enterprise purpose is to produce human-usable output from technical, business,…

The work is done in a Google Colab Pro with a V100 GPU and High RAM setting for the steps involving LLM. The notebook is divided into self-contained sections, most of which can be executed independently, minimizing dependency on previous steps. Data is saved after each section, allowing continuation in a new session if needed.…

Today, the world is abuzz with LLMs, short for Large Language models. Not a day passes without the announcement of a new language model, fueling the fear of missing out in the AI space. Yet, many still struggle with the basic concepts of LLMs, making it challenging to keep pace with the advancements. This article…

Gain a deeper understanding of Gaussian processes by implementing them with only NumPy. Gaussian Processes (GPs) are an incredible class of models. There are very few Machine Learning algorithms that give you an accurate measure of uncertainty for free while still being super flexible. The problem is, GPs are conceptually really difficult to understand. Most…

How to do poorly on Kaggle, and learn about RAG+LLM from it 23 min read · Dec 25, 2023 Image generated with ChatGPT+/DALL-E3, asking for an illustrative image for an article about RAG.Retrieval Augmented Generation (RAG) seems to be quite popular these days. Along the wave of Large Language Models (LLM’s),…

Ten of my LinkedIn posts on LLMs 1. Non-determinism in LLMs The best LLM use cases are where you use LLM as a tool rather than expose it directly. As Richard Seroter says, how many chatbots do you need? However, this use case of replacing static product pages by personalized product summaries is like many…