a few thoughts after using Opus and switching back to Claude Code: > the big win of Opus isn’t the benchmarks. it’s TASTE. both in approach and in design. > the model is just fun to work with. it sparks a kind of excitement, as it’s smart and efficient. > i don’t know if it’s Opus or that Claude Code has become efficient in the past months. i’ve been milking this model the past few days and the usage is consumed much less than I expected. > the last time I used Claude, it was verbose and needy.…