1,107 karma · joined July 19, 2010
CameronSmith.dev
twitter/cameronsmith cameron at empty.io
This is pretty magical tbh
Also added MIT license and added some more pruning to reduce initial capture by around 10%.
The ## heading is built from the block's timestamps, the app name and the window title. The frontmatter is per-day boilerplate. The file:/url: line is the window's backing document where the app exposes one. The captured text underneath is written exactly as the tree handed it over: plain lines, no reconstruction.
That lossiness is also why the file/URL references exist. Trying to rebuild a document's formatting from its accessibility tree is a losing game, so instead each block records where the real document lives, and the LLM reading the file can open the original if the fragments aren't enough. "Plain markdown" was meant as "a markdown file you can open anywhere", not "faithful markdown conversion of what you saw"
I also saw that HeyClicky started doing something similar but end up removing from the product.
This way he can still view a selected range of Minecraft videos without getting stuck in the cesspool of '100 days as a chicken' playlists.
I've only just submitted the site to Google and waiting on indexing.
I've now got a Digiton/Digitakt setup that's much better. Elektron's workflow just clicked with my brain.
The two main non Google/Amazon competitors are https://www.resemble.ai/ and https://replicastudios.com/