So — I recently came across a thread on HackerNews, one about Terrence Tao and his use of LLMs, and a section of a particular comment is worth highlighting:
The fact everyone that say they've become more productive with LLMs won't say how exactly. I can talk about how VIM have make it more enjoyable to edit code (keybinding and motions), how Emacs is a good environment around text tooling (lisp machine), how I use technical books to further my learning (so many great books out here). But no one really show how they're actually solving problems with LLMs and how the alternatives were worse for them. It's all claims that it's great with no further elaboration on the workflows.
...and then, someone pointed the use that Simon Willison makes of Claude and some other tools.
I'm not really knowledgeable in the cutting edge space of LLMs — I use Phind and ChatGPT, mostly — and thus probably missing out on untapped productivity; these assorted ideas from Willison shifted my perspective a bit. Some scattered points follow, and this motivated me to try to explore this space further; I have a few prompts and ideas I'll pipe through an LLM first, and hopefully this can have a positive impact on my output.