We spent nearly a month running @OpenAI’s GPT-5.6 Sol through real work. Then we lost early access for a week. As @tedescau put it, reverting to lesser models felt “like I’m trying to shoot a basketball that’s twice as heavy.” Sol is our favorite model to work with. Here are five things we learned: 1. Speed changes the work. Sol is the fastest model we trust as a daily driver. A revision costs minutes, which makes it easier to discard a weak draft, try a different direction, and keep moving…