However, UX can also be improved by some simple heuristics that could be seen as mechanistic by the standards of modern LLMs.
Performance and responsiveness, for example, contribute to UX even when the UI remains fixed. I’d wager Fable-level LLMs could improve perf on most open-source GUIs by benchmarking typical use cases and progressively applying standard tricks like caching, buffering, batching network calls.
If someone is a user, they'll have specific complaints. Claude Design is more than capable, which can then be fed directly into Claude Code to implement, test, iterate, and ship.
I agree that it lags behind coding and imo the highest leverage area for Anthropic to invest in. Hopefully they do so; UI is consistently one of the main (severe) differentiators between OSS and paid options.
That would appear to leave me with the choice of just using it for myself (lame) or I then have a public fork to maintain :(
If there's basically no shot of it getting up streamed I think I'd rather make something from scratch to suit my needs without the extras.
Anyway, I hope the AI overlords help us fund more maintainers soon!
My example might be an outlier on the easy side because they have a custom/plugins directory that will not have merge conflicts ever so I try to never modify the main init.lua and keep all of my changes separate in my own files. This prevents merge conflicts.
I can then ask my LLM to add a plugin or customize existing plugins by writing files in this separate directory to add/overwrite plugins and configurations. This works great for me.
If I were working in the main file creating merge conflicts, I could imagine it could get messy fast.