June 2022
43 posts: 8 entries, 7 links, 2 quotes, 26 beats
June 23, 2022
How Imagen Actually Works. Imagen is Google’s new text-to-image model, similar to (but possibly even more effective than) DALL-E. This article is the clearest explanation I’ve seen of how Imagen works: it uses Google’s existing T5 text encoder to convert the input sentence into an encoding that captures the semantic meaning of the sentence (including things like items being described as being on top of other items), then uses a trained diffusion model to generate a 64x64 image. That image is passed through two super-res models to increase the resolution to the final 1024x1024 output.
First impressions of DALL-E, generating images from text
I made it off the DALL-E waiting list a few days ago and I’ve been having an enormous amount of fun experimenting with it. Here are some notes on what I’ve learned so far (and a bunch of example images too).
[... 2,102 words]June 28, 2022
The Magic Interview Question (via) Jeff Gothelf explains why “Tell me about the last time you [did something]” is the most valuable question you can ask when interviewing a user or potential user.
The general idea of an “Islands” architecture is deceptively simple: render HTML pages on the server, and inject placeholders or slots around highly dynamic regions. These placeholders/slots contain the server-rendered HTML output from their corresponding widget. They denote regions that can then be "hydrated" on the client into small self-contained widgets, reusing their server-rendered initial HTML.
June 29, 2022
June 30, 2022
s3-ocr: Extract text from PDF files stored in an S3 bucket
I’ve released s3-ocr, a new tool that runs Amazon’s Textract OCR text extraction against PDF files in an S3 bucket, then writes the resulting text out to a SQLite database with full-text search configured so you can run searches against the extracted data.
[... 1,493 words]