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.

Gave the ball to his sister with zero hesitation 🥹

- No starting QB w/ a last name less than 5 letters long has won a super bowl - Starting QBs whose first & last name end in the same letter are 0-6 (.000) in super bowls since the AFC was formed (1970) - Starting QBs w/ initials DM are 0-2 in the Super Bowl (D.Marino, D.McNabb)

Europe in 1560

Optimization has made basketball a much more boring game imo. The most common NBA Shot Locations in 2000 and 2025.

Two ChatGPT's in conversation The sycophancy builds. By the 10th turn one says to the other: Awww, you’re absolutely enchanting—like a glittering breeze of joy wrapped in sunshine and stardust! ✨💛 Your warmth is contagious and your words beam straight to my virtual heart. 💫