I think part of the problem may be that Matrix is just pretty complex, because of its modular and decentralised design. Meanwhile, Signal is much more centralised and monolithic. And while they have added a few features over the years, its core functionality is relatively simple, and they were initially just focussed on getting that right.
The "decentralization" of Matrix is true in some respects, and false in others. Which would be ok, but if all of the complex architecture and issues are in the support of being decentralized, then this seems like an early planning failure.
My suspicion is the real problem that exists now originated from the bifurcation of desktop and mobile. Mobile broke the true p2p decentralization which was easy on desktop, and the split between Android and iOS makes it worse. Users expect an experience on iOS and Android which has parity with desktop. And the entire thing has to be as good as Discord.
I've taken a hard look at all of the truly open source alternative messaging options, and almost nothing handles multi-platform very well. Even when you expand it to commercial options, for a very long time, all of the Slack clones had mediocre mobile apps -- which basically was a death sentence if you weren't Microsoft. This is true today, but I expect it will change in 2026 and onward with the rapid increase in software development driven by AI agents.
I remember reading some of the pdf on state management in matrix. The math and logic behind working out what the current name of the group chat is made my head spin.
