One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
Recently I’ve heard a new concept call Zoomality.
Your capability can actually be measured by how many layers you’re able to toggle between when you zoom in and zoom out mentally.
Zoomality means exactly that ability: freely switching between zooming in and zooming out.
I’ve noticed a recurring feeling. If you dwell too long on grand ideas and big-picture worldviews, you slowly sink into nihilism.
If you get trapped focusing solely on tiny details for too long, constant frustration kicks in.
When leading a project or founding a company, you constantly need both perspectives.
You have to regularly zoom out for the macro overview, while also being capable of zooming in deep into specifics.
The number of layers you can navigate between these two modes is a great benchmark of your overall ability