Agreed, but give it time. The tipping point of good models only just arrived with Fable 5, GLM 5.3, Grok 4.6, Muse Spark 1.3, and the like. Those are the only models that do a better job than me, and I'm happy to hang up my IDE—and that was barely a month ago.

I've been fixing everything that has been sitting there—not blocking us, but slowing us down—all the things we never had the bandwidth for. We're now squeezing more out of development, CI, and production.

I'm not sure why, but I'm concerned this may be the heyday, and we might not get this again at this price or speed. So I figured we should clear the backlog while we can still afford it and still have the ability to do so.

But now things have changed, and the bigger, grander ideas are starting to brew.