The "I Want to. . ." AI App
Die, menu interface, die!
So here is how I wasted half an hour today. I am an occasional Whatsapp user, and I wanted to exit from a group. I spent 10 minutes guessing how to do that, but no luck. Then I spent 10 minutes trying to find the appropriate help file. I finally found it, but it gave me the wrong procedure. So I spent 10 more minutes guessing, and I finally found out how to do it.
Maybe I’m getting old and stupid, but that seems to be happening to me a lot lately. For example, I wanted to take the Required Minimum Distribution from an inherited IRA account, and I ended up having to talk to someone on the phone in order to get it done properly.
I have predicted that these obstacle-course menu systems will die (along with obstacle-course customer service phone menus) as soon as the companies install AI response systems. With the AI system, you will just have to say “I want to ____” and the response will be, “I am ready for you to ____, just click here.” The user won’t have to waste so much time.
Meanwhile, somebody could develop the “I want to ___” AI app. It would be an app that helps a user navigate any web menu. I would tell the app “I want to leave such-and-such group on Whatsapp,” or “I want to submit a letter to the editor of the WSJ,” or “I want to take the Required Minimum Distribution from my inherited IRA account,” and the app would scrape the appropriate web site until it finds the solution for me.
I imagine the “I want to ____” app as pretty do-able. If instead it would be difficult to construct using existing AIs, then I would say that for all the hype, AI is still not all that intelligent.
For some additional concerns about the readiness of AI, consider Benedict Evans.
LLMs are not databases: they do not do precise, deterministic, predictable data retrieval, and it’s irrelevant to test them as though they could.
…This reminds me of an observation from a few years ago that LLMs are good at the things that computers are bad at, and bad at the things that computers are good at. OpenAI is trying to get the model to work out what you probably mean (computers are really bad at this, but LLMs are good at it), and then get the model to do highly specific information retrieval (computers are good at this, but LLMs are bad at it). And it doesn’t quite work. Remember, this isn’t my test - it’s OpenAI’s own product page. OpenAI is promising that this product can do something that it cannot do, at least, not quite, as shown by its own marketing.
Why not just ask AI in an existing app? I asked Perplexity:
To leave a WhatsApp group, follow these steps:
1. Open WhatsApp and go to the group you want to leave.
2. Tap the group name at the top of the screen.
3. Scroll down to the bottom of the menu.
4. Tap “Exit Group” and confirm that you want to leave.
The group admin will be notified, but other members won’t receive a notification unless they check the member list. Your chat history will remain on your device, but you won’t be able to send messages to the group anymore.
AK has been spot on previously that AI has huge potential benefits in improving UIs.
Here, however, he misses the mark (I say as a former software engineer). With the *possible* exceptions of Apple, Google and Microsoft themselves - by embedding within their respective operating systems - it will not be easy to develop that “I want to…” app.
At least if you want the app to *perform* the function as opposed to simply telling you how to perform the function. To paraphrase Jerry Seinfeld, it’s the *performing* of the function that’s the hard part.
Because that gets at the UI of each of these individual applications and websites - and the act of navigating these things designed for human users is not generally something that an external, 3rd party app can easily be programmed to do.
When app developers change their own apps to take advantage of AI for their own user interfaces - AK’s earlier observation - that’s when we’ll get what he wants.
Now one can certainly imagine a new - or existing improved - operating system that made interfacing with applications for a centralized AI/app easy to do. But that again requires new/rewritten applications.