/AI

Let's Build GPT: From Scratch, In Code, Spelled Out

- Andrej Karpathy tl;dr: "We build a GPT, following the paper "Attention is All You Need" and OpenAI's GPT-2 / GPT-3. We talk about connections to ChatGPT, which has taken the world by storm. We watch GitHub Copilot, itself a GPT, help us write a GPT."

featured in #382

How Might Generative AI Change Programming?

- Laurence Tratt tl;dr: "In this post I'm going to try and explain why I think GAI, at least in its current forms, is unlikely to be able to fully replace programming. I first look at the relationship between programming and software in a slightly different way than most of us are used to. Having done that, I'll then explain how I think GAI is different than programming when it comes to generating software. I'll finish by giving some very general thoughts about how ML techniques might influence how we go about programming."

featured in #377

Building A Virtual Machine Inside ChatGPT

- Jonas Degrave tl;dr: The authors shows how to "build a virtual machine, inside an assistant chatbot, on the alt-internet, from a virtual machine, within ChatGPT's imagination."

featured in #372

Discovering Novel Algorithms With AlphaTensor

tl;dr: "In our paper, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on a 50-year-old open question in mathematics about finding the fastest way to multiply two matrices"

featured in #357

4.2 Gigabytes, Or: How To Draw Anything

- Andy Salerno tl;dr: Andy sketches a cityscape and spaceship and runs both images through Stable Diffusion to illustrate the technology. "4.2 gigabytes of floating points that somehow encode so much of what we know. Yes, I’m waxing poetic here. No, I am not heralding the arrival of AGI, or our AI overlords. I am simply admiring the beauty of it, while it is fresh and new."

featured in #349

How I Used DALL·E 2 To Generate The Logo for OctoSQL

- Jacob Martin tl;dr: "In the rest of this post you’ll see where I started, what I went through, what I learned along the way, and how it slowly evolved into the finally chosen image. I will only show the mostly happy path here. I will also only show images that were fairly ok (discarding the other 70+% that were terrible)."

featured in #340

Using GPT-3 To Explain How Code Works

- Simon Willison tl;dr: "One of my favourite uses for the GPT-3 AI language model is generating explanations of how code works. It’s shockingly effective at this: its training set clearly include a vast amount of source code. Simon shows a few recent examples." 

featured in #333

The Berkeley Crossword Solver

tl;dr: "The BCS uses a two-step process to solve crossword puzzles. First, it generates a probability distribution over possible answers to each clue using a question answering (QA) model; second, it uses probabilistic inference, combined with local search and a generative language model, to handle conflicts between proposed intersecting answers."

featured in #331

How DALL-E 2 Actually Works

- Ryan O'Connor tl;dr: A URI is a string that identifies a resource. From a syntactical point of view, a URI string mostly follows the same format as the URL. A URN identifies resources in a permanent way, even after that resource does not exist anymore.

featured in #311

DALL·E 2

tl;dr: A new AI system that can create realistic images and art from a description in natural language.

featured in #308