Whilst LLMs don't always give an accurate answer, the UI is really compelling. I keep finding users whose favourite way of doing research is an LLM.
Related Posts
I'd heard the conventional wisdom that UX research states that mice are more efficient than keyboards, but turns out there's virtually no research on this!
https://danluu.com/keyboard-v-mouse/
The "line of death", where the browser UI splits between trusted UI elements and UI controlled by the website.
Also argues that HTTP warnings are better than HTTPS padlocks, because there's incentive to spoof padlocks lower on the page.
https://emilymstark.com/2022/12/18/death-to-the-line-of-death.html
One interesting consequence of the rise of LLMs: there's more demand for tools that handle untrusted input.
Arbitrary HTML+JS can be safely run in a browser. Lean can check an arbitrary proof.
These work really well with an LLM that can be wrong, but sometimes gives exactly what you want. Are there other tools in this family?