I did a series of talks on the future getting weird several years ago. This is a self-indulgent post where I once again explore my futurism hobby.
Virtual assistants like Siri, Hey Google, and Alexa are going to get much more useful in the coming years. With the rise of machine learning, including technologies like GPT-3, these assistants will get a lot more conversational, but it goes beyond that. These services will get personal, and become infinitely more useful as they become our agents on applications and websites.
Personalized
Assistants will collect data from our conversations to combine with data from other sources in order to create a more personalized experience. Making suggestions, for example. They might even reach out to you during the day.
"Hey, Nathan?"
"Yeah, Siri?"
"You're trying to build a pushup habit – this might be a good time."
You could also respond by shushing it, or arguing that you just wanted to do pushups that one time.
Modern thinking has it that building habits requires a trigger, and your assistant could provide that. Along those lines, it could track your calories, guide your meditations, make suggestions for upcoming anniversaries and birthdays, and more.
Some of these things might sound like notifications, but it's a little different. The assistant will be making guesses as to when you're not busy based on movement, heart rate, and other clues; it'll start to learn when you don't mind being interrupted. It'll be much more polite about it than any notification could be, not that you couldn't ask it to stop.
Other ways that an assistant will adapt to you is with subtle clues about your tone of voice, and other behaviors. In order to build a rapport with you, it'll mimic your inflections and speech patterns. Research has shown that we mirror body language and speech interactions in order to build mutual respect.
An agent will start to anticipate your usage patterns to make interactions more convenient for you. It'll notice when you've missed something, and help you fill in the gap. Beyond just anticipating your Starbucks order (more on that later), an assistant will realize that you're rushing to work, and might send a message ahead of you to let your employees know that you're going to be a few minutes late for the first meeting of the day. The agent is watching out for you, and will try to make your day go more smoothly.
An Explosion of Applications and Use Cases
The actions an agent will be able to take is going to explode. Right now, if McDonald's wanted Alexa to be able to make an order, they'd have to register an extension with Amazon and include all of the anticipated words and commands along with their responses, or a service callback to make a dynamic response. Each user will then have to add the McDonald's service to their Alexa and cross-authenticate with their McDonald's user account. Additionally, each user will have to learn and memorize the type of things they can say to use the McDonald's service in Alexa. All of this complexity keeps the number of services fairly low, and user participation even lower.
But this will change in the coming years. Phone applications and websites will be able to include standardized interfaces specifically for virtual assistants. These APIs will describe what kinds of things the agent can do with the service, suggested phrases and promotions, information dependency based workflows, and examples. This won't be nearly as strict as a traditional low-level API, because the agent will use language processing and other machine language techniques to interpret the application; it'll be somewhere in between a user interface and a computer interface. The assistant will combine its newfound knowledge of the service with what it knows about the user, and create a custom experience on the fly with the user.
Driving. "Hey Google, I'd like order a Big Mac from McDonald's up ahead."
Looks up the McDonald's agent API. "Sure, do you want that in a meal or just the sandwich?"
"Just the sandwich."
"They have seasonal vanilla custard filled Holiday Pies right now. You've been good and haven't had a dessert in a few days. Would you like one?"
"Oh they have those again? Nice, I'd like one."
"Your total is $9.14. Would you like me to finalize the order?"
"Oh, can you add an ice water?"
"Yes. The total cost is unchanged. Would you like me to order a Big Mac, Holiday Pie, and ice water for $9.14?"
"Yes, that sounds good."
"I submitted your McDonald's order on your VISA card ending in 1234. Please pull into order space #4."
Since companies no longer have to painfully create and register agent skills, there will be a lot more services available to the agent. With the service-registration and user-friction gone, and fully customized experiences using natural language, there will be an explosion of consumer use.
Agent-to-Agent
Your agent instance will be able to interact with the agents of others, at least within a given platform (I'll talk more about open and federated standards another time). This will be useful for scheduling appointments, buying gifts, and checking in others that trust you.
"Does my partner have any late meetings tomorrow?"
Agent looks up their calendar directly, or asks their agent through a special API.
"Their last work meeting is at 2:30pm."
"What should I get them for their birthday?"
"They recently added a book to their wishlist – Brandon Sanderson's Rhythm of War, the latest in the Stormlight Archive."
"Oh yeah, she loves those books. Can you call the local books store and have them hold a copy for me? Also, order a flower arrangement from the flower shop around the corner."
"I'll do that. Do you want me to confirm the arrangement and price before I order the flowers?"
"No, you know what they like."
"Okay. I'll have the book store hold the book at the front counter for you, and I'll order those flowers. I'll let you know when I'm done."
At any point, your agent could contact other agents or even people on the phone to ask the necessary questions. The other agents will know your relationship with their users, and will only allow your agent to have appropriate and approved types of data.
This example might seem a little weird – having what is essentially a program pick out flowers for your partner. I also found it deeply weird in 4 Hour Workweek when Tim Ferris asked his internet assistant to write a heartfelt apology email to his wife. To each their own.
The Future is Weird
Virtual Assistants are frustratingly rudimentary right now, but over the next decade, they'll get a lot more useful. These agents won't be generalized artificial intelligence, we're simply not that close to developing one yet, but from a user's perspective, the lines will be blurred.
I want to be clear that I'm not advocating for these features nor this future. I just think this is where things are headed based on the potentials at play, trends in natural language processing, privacy in the US, and the rise of cloud machine learning. I'll get into my opinions on the morality of these trends in a future post.
Regardless of the morality of it, virtual agents will make our lives easier, so it'll be an easy sell.
--
Stay tuned for Part II, where we explore the repercussions of these technology trends.
Top comments (0)