Some software interfaces are windows into collections of features. The Uber app, for example, literally opens with a screen full of buttons, each of which take you to a different screen with yet more buttons and inputs. Google Search is also built with features – inputs, buttons, and links that take you to different capabilities in the app – as the building block. In both of these cases, there are a few clear and obvious tasks the user wants to accomplish when they open the app. In the ca...| 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