Nice—who have you found that sits at the intersection of "wants to build custom personal apps" and "doesn't want to use a terminal UI"? Or, is there something people who already use Claude Code would get from this?
I haven't read this particular paper in-depth, but it reminds me of another one I saw that used a similar approach to find if the model encodes its own certainty of answering correctly. https://arxiv.org/abs/2509.10625