The choice not to implement it for architectural reasons is entirely up to the devs, is likely justified, and in most cases users acting entitled to support and feature additions from OSS developers who are volunteering their time is something I side against. But the devs also should be able to talk to people who aren't marinated in that same viewpoint, for their own sake if nothing else. The leap from "there exist cases where implementing this feature in a performant manner wouldn't be feasible" to "we shouldn't implement this feature even for the many cases that would support it" isn't going to be obvious to everyone.

VLC's poor performance in seeking backwards in general, not just by frame, is a big part of why it's no longer my media player of choice. Which is fine! As an OSS project there's no real reason to care about the number of users as long as enough people are involved to sustain the project, and making the developer experience pleasant is more important than making the user experience pleasant on that front. It just means it's not as good a tool for some users as others, like mpv.