This post is a read-through of a talk I gave at a demo night at South Park Commons in July 2024.| thesephist.com
For most of the history of music, humans produced sounds out of natural materials — rubbing together strings, hitting things, blowing air through tubes of various lengths. Until two things happened.| thesephist.com
Foundation models gesture at a way of interacting with information that’s at once more natural and powerful than “classic” knowledge tools. But to build the kind of rich, directly interactive information interfaces I imagine, current foundation models and embeddings are far too opaque to humans. Models and their raw outputs resist understanding. Even when we go to great lengths to try to surface what the model is “thinking” through black-box methods like prompting or dimensionality ...| thesephist.com
Cross-posted from my Notion.| thesephist.com
The Grand Unifying Theory of Design; my rant to AI skeptics; AI design gets innovative; LLM agents are the future; Starship & the next 10 years of space| futureblind.com
I’m a hyperlink maximalist: everything should be a hyperlink, including everything that is hyperlinked by the author, everything that isn’t hyperlinked by the author, and perhaps even the hyperlinks themselves. Words should be hyperlinked, but so should be every interesting phrase, quote, name, proper noun, paragraph, document, and collection of documents I read.| thesephist.com
A big library holds a kind of strange faux-infinity, spanning across hundreds of topics with voices from millions of authors. Good libraries can contain in their finite space a feeling that, even if you read for centuries and centuries, you would never exhaust the knowledge contained within their walls, not only because there are simply so many books, but because there’s so much to learn when you take the ideas from one book as a lens through which to read others. Infinities assembled out o...| thesephist.com
In the last post, I shared some possible ideas for how humans may interact in the future with large language models. It focused on specific examples of both good and bad interface ideas. In this post, I want to continue that exploration, but from first principles, asking ourselves the question, “what properties should good human-AI interfaces have?”| thesephist.com
A core research interest of mine is imagining new kinds of interfaces to text documents that are made possible by modern AI and software. I think an interesting place to look for such ideas may be interface designs for reading and writing legal documents.| thesephist.com
When I get stuck on a really hard problem, whether it’s some impossible bug in my code or my sofa not fitting through my front door on moving day, I close my eyes and … think really hard. Somewhere behind my shut eyelids and confused eyeballs, things are happening. Electricity is flowing through the vat of brain-stuff and spindly wires that somehow make up my thought process, and for a few seconds, they just kind of do their thing. Until, if I’m lucky, an answer pops into my head a few ...| thesephist.com