Personally I prefer to use a separate, dedicated service to run my language models, and I bounce between a few clients for various things. One of them is a (local) web interface (open-webui).
That would be awfully convenient. You'd never lose them or need to deal with another native application. Just open any web page that echoes all HTTP headers and then check your account balance.
Or maybe having a separation of concerns for different applications in a general purpose computer is worth the friction.
When you use an LLM, you provide it context. Where do you usually get that context from? Some service, JIRA, whatever, in your browser.
A browser is one thing that users will go out of their way to replace, making it a pretty attractive vehicle for stuff like this.
Upon further research, I have found that I misread the word "unnecessarily".