A short read on the topic's time range, peak episode, and strongest associations. Use it as the quick orientation before drilling into examples.
Twitter appears in 24 chunks across 21 episodes, from 2024-02-05 to 2026-03-23.
Its densest episode is Bits and Bobs 4/15/24 (2024-04-15), with 2 observations on this topic.
Semantically it travels with llms, Simon Willison, and prompt injection attack, while by chunk count it sits between marginal cost and Simon Willison; its yearly rank moved from #31 in 2024 to #40 in 2026.
Over time
?
Raw mentions over time. Use this to see absolute attention, not relative rank among all topics.
Range2024-02-05 to 2026-03-23Mean1.1 per episodePeak2 on 2024-04-15
Observations
?
The primary evidence view for this topic. Sort it chronologically when you want concrete examples behind the larger pattern.
Showing 24 observations sorted from latest to earliest.
Today on Twitter, people doing cool things with LLMs share screenshots, not running links.
That's because there's no good way to distribute it.
If you link to a hoste...
A thought-provoking old Twitter thread from my friend Ben Mathes. (A lightly edited version of the thread follows)
"2 key ingredients behind every good situation I've ever been in: ...
Blockchains, Twitter Threads, and improv scenes all have something in common.
Each one has a kind of "yes, and" logic to it.
For each, the participants are all making int...