Here I am generating ~20 versions of a web app by describing what I want in just 1 sentence to Debuild. Debuild uses GPT-3 + Codex to: - Generate a product spec - Generate the data model - Write the SQL queries - Generate the React UI - Deploy it in 1 click

DALL-E is not an illustration tool. It's a 3D rendering engine. Its *learned* CGI techniques like ambient occlusion, drawing shadows, and reflections. It even uses environmental haze to enhance the perception of distance... like what!?

Let's do TLDR for our new preprint! Brain-Diffuser arxiv.org/abs/2303.05334 We reconstructed perceived scene images from brain signals. These reconstructions capture both layout and semantic information of images... But how?

thx for hving me -)