Category: AI and Machine Learning
-
AI’s Electron.JS Moment?
The study provides an analysis of ML model energy usage on a state of the art nvidia chip: We ran all of our experiments on a single NVIDIA A100-SXM4-80GB GPU Looking these devices up – they have a power draw of 400W when they’re running at full pelt. Your phone probably uses something like 30-40W…
-
Turbopilot – a Retrospective
As of today, I am deprecating/archiving turbopilot, my experimental LLM runtime for code assistant type models. In this post I’m going to dive a little bit into why I built it, why I’m stopping work on it and what you can do now. If you just want a TL;DR of alternatives then just read this…
-
Prod-Ready Airbyte Sync
Airbyte is a tool that allows you to periodically extract data from one database and then load and transform it into another. It provides a performant way to clone data between databases and gives us the flexibility to dictate what gets shared at field level (for example we can copy the users table but we…
-
Xavier the Spotify AI DJ
Spotify recently joined the AI hype by introducing a new AI DJ to their app. I was initially deeply sceptical and cynical and started muttering about cancelling my subscription and just going back to using my local library and Plex. However, I thought I’d give it a go. So far I’ve found it to be……
-
NLP is more than just LLMs
There is sooo much hype around LLMs at the moment. As an NLP practitioner of 10 years (I built Partridge in 2013), it’s exhausting and quite annoying and amongst the junior ranks, there’s a lot of despondency and dejection and a feeling of “what’s the point? ClosedOpenAI have solved NLP”. Well, I’m here to tell…
-
Painless Explainability for NLP/Text Models with LIME and ELI5
Introduction Explainability of machine learning models is a hot topic right now – particularly in deep learning where models are that bit harder to reason about and understand. These models are often called ‘black boxes’ because you put something in, you get something out and you don’t really know how that outcome was achieved. The…
-
Reproducing ‘ancient’ experiments with Pytorch inside docker
Introduction Open machine learning research is undergoing something of a reproducibiltiy crisis. In fairness it’s not usually the authors’ fault – or at least not entirely. We’re a fickle industry and the tools and frameworks were ‘in vogue’ and state of the art a couple of years ago are now obsolete. Furthermore, academics and open…