Unrelated, not sure if it is just me, but ever since LLMs became popular, I've been seeing an enormous amounts of special utf8 characters no one used regularly, like this em dash you used.
How is this simple to type? If you're on a phone keyboard, you have to switch to special characters, and then have to long-hold the dash and then slide to em dash.
LLMs are everywhere.
I have an AutoHotkey script that auto-replaces "--" with "—" (and auto-disables it in contexts where it's likely intended, like SQL editors and my terminal).
I also auto-replace "`-" with "–" so I can conveniently do number ranges with the (objectively correct) n-dash to indicate a range.
there are also bindings for bullets • and probably other things I'm forgetting (or that may be conflicting with other bindings I have setup)
https://news.ycombinator.com/item?id=42330710 and https://news.ycombinator.com/item?id=42330639
Do you mean a database still? Or something like Langflow or Dify? Curious what "something even more integrated" would look like as just a DB.
On the AI front, vector databases like Pinecone and pgvector are exciting, but I’d love to see something even more integrated with AI workflows. The possibilities are huge. Curious to hear what others think!