Thinking about it

Author: brice

  • Vector Database with Django and pgvector

    I have a small Django project I have been playing with for a while. There’s more about it in this series of posts. The application just keeps a list of items (mostly weblinks etc) and lets me organize them. I’ve been experimenting with using embeddings for finding similar items or suggesting tags etc. I am…

  • Politics, Complexity and the next big Outage

    I worry a lot about how complex the world is and how unstable that makes things. 

  • Agents and Agency

    I think the first time I heard about how software agents were going to be useful to help perform tasks for us must have been with General Magic in the 90s. It was all the same use cases we hear about today, flight booking, recipe generation etc. Just taking out all that drudgery from our…

  • Do LLMs talk the way humans do?

    I wonder sometimes about the difference between how an LLM talks and how I do it. It’s hard to really be confident in introspecting your own cognition but at least it feels like an idea forms in my head and then I render the words.  I don’t know if an LLM starts with an “idea”…

  • The Airplane Economic Model

    I’ve never been completely satisfied with terms like wealthy, rich, middle class, poor or working class. They seem to be amorphous and ill defined to me, and mostly just get politicized for various purposes. It is hard to define groups based on income numbers because of variations in cost of living or other factors such…

  • Explaining What’s up with AI (Part 6 – The Dark Side)

    Part 1 of the series is here. AI like any new technology brings with it both promises of great benefits and also many concerns about how it might cause bad outcomes. Since there’s plenty of people who are already trying to get rich by selling the idea that AI will solve all our problems, I think…

  • Explaining What’s up with AI (Part 5 – Text to Image)

    Part 1 of the series is here. After spending time talking about LLMs and what they can do with text, Let’s go back to looking at images. Text to image generators allow you to just type something like: “create an image of a cat wearing a blue baseball cap” And you get: There are several tools…

  • Explaining What’s up with AI (Part 4 – GPT to ChatGPT)

    Part 1 of the series is here. In our last post we saw how an LLM when given some text to start with could generate more text. This idea forms the basis of a tool like ChatGPT but there are still a few steps to get there. GPT3 by OpenAI was maybe the most powerful model…

  • Explaining What’s up with AI (Part 3 – LLMs)

    Part 1 of the series is here. Machine learning and neural network systems have been around for a while but it seems like everything has really exploded in the last few years. We’ve gone pretty quickly from computers using AI to understand  “Alexa, set a timer for 5 mins” most of the time,  to worrying…

  • Explaining What’s up with AI (Part 2 – Neural Nets)

    Part 1 of the series is here. Many different techniques have been used for Machine Learning over the years, but since all of the most exciting recent advances have been made using neural network systems that’s what we will focus on in this series. So let’s start from the basics. A neural network is a…