That's not what I mean. The ribbon, whatever you think of it, only moved some functionality around. It didn't actually change the way old functionality worked. All the things you knew how to do, you could still do - you only had to learn their new placement.

If we consider the Word 2.0 (for Windows) era as the beginning of a graphical Microsoft Office suite, then graphical Office has had the ribbon for as long as it didn’t: 16 years.

I’m still waiting for people to stop complaining about it.

That move was awful

For you.

The irony is that LLMs are actually the real solution that Ribbon took an awkward half step towards -- how to quickly get to what a user actually wants to do.

Originally: Taxonomically organized nested menus, culminating at a specific function or option screen

Now: Usage-optimized Ribbon (aka Huffman coding for the set off all options), culminating at a specific function or option screen

Future: LLM powered semantic search across all options and actions, generating the exact change you want to implement

Why have an "email signature" options page at all, when an LLM can stitch together the calls required to change it, invoked directly from English text?

You missed Office 2000: magically disappearing menu items. It was pretty confusing.

Oof. I did. Ribbon felt enough like magically disappearing menu items to me.

> Why have an "email signature" options page at all, when an LLM can stitch together the calls required to change it, invoked directly from English text?

10-20 years from now? Maybe. It depends on whether or not the industry will cut corners in this part of the experience. I find it hard to predict which features get polished, and which are forever left barely-functioning. Might depend on which are on "critical path" to selling subscriptions.

0-10 years from now? We'll still need the options page.

"Email signature" options page provides visibility, consistency, and predictability. That is, you can see what your e-mail signatures are, you are certain those are the ones that will be used for your message, under conditions defined in the UI pane, and if you change something, you know exactly how it will affect your future e-mails.

LLMs are quite good at handling input, though not yet reliable enough. However, as GUI replacement, they are ill-suited for providing output - they would be describing what the result is, whereas the GUI of today display the result directly. As the writers' adage goes, "show, don't tell".

(That said, the adage is way overused in actual storytelling.)

In this case, the LLM isn't generating the output. It's only generating the sequence of actions to implement the user input.

Think less "make a signature for me" and more "here's the signature I want to use, make it my default."

Then the model would map to either Outlook / Options / Signature / fields or directly to whateverSetSignature().

From that more modest routing requirement, it seems a slam dunk for even current models (retrained to generate options paths / function calls rather than English text).

Good local search gets you 80% of the way there. 20 years ago, this was an inspiring UX trend (Quicksilver / Subject Verb Object), but it fizzled. Apple kept the torch lit with menu search and it has been brilliant, but limited to their platform, although I am pleased to see that MS Office got menu search in Oct 2022.

LLMs could certainly help loosen the input requirements, not to mention aim some sorely needed hype back in this direction. I am afraid that they will murder the latency and compute requirements, but hey, progress is always two steps forward one step back.

I was never terribly impressed with local search on os x but maybe I didn't use it enough.

For a while, ubuntu had a local search where you could hit a button (super?) start typing, and it would drill through menus at lightning speed