AR for Everybody!
Over the next six to twelve months, we’re going to see a surge in usage of and spending on augmented reality (AR) glasses that are enhanced by GPT-based artificial intelligences (AI). Why? Because blue-collar workers and prosumers will ultimately get a lot of utility out of them.
For example, the Bing chatbot will likely empower HoloLens 2 users. Open AI’s ChatGPT-4 will probably be feeding directly into Vuzix brand smart glasses. And Facebook’s LLaMA AI will somehow be integrated into the not-yet-released Meta Quest 3 (formerly known as the Oculus Quest brand) and/or Raybans.
Although Google recently discontinued Glass Enterprise smartglasses, they’ll no doubt find AR glasses manufacturers to match up to Bard. Meanwhile, there’s no way Apple will be deprived its entry into the space.
Blue-Collar Work Gets Seriously Augmented
Why do I think this is going to happen? The main reason is that, unless there’s some huge crisis associated with one of these AIs in the meantime (it could happen), people at work finally have a legit reason to wear these gadgets, especially in blue-collar jobs.
I don’t mean that it’s going to happen overnight. It’ll start slowly and become more popular over time. But it’ll come because these AIs will all eventually be able to interpret images. In fact, ChatGPT-4 already has this capability.
This potentially changes the working lives not only of various types of blue-collar employees but of avid prosumers as well.
Bing Creates a Scenario
I asked Bing to create a scenario in which an electronics mechanic uses a HoloLens that’s enabled with an AI-powered image recognition module. I specified the person is an experienced electronics mechanic who already knows how to address basic jobs such as fixing a resistor.
Here’s what Bing came up with:
Alice arrives at the customer’s house and inspects the drone that is lying on the table. She notices that it is a DJI Mavic Air 2, a model that she has not worked on before. She turns on her HoloLens headset and says:
“Hello Bing, I need your help with repairing this drone. It has a damaged circuit board. Can you show me a schematic diagram of this model?”
Bing responds: “Sure, Alice. I have found a schematic diagram of the DJI Mavic Air 2 from the official website. Here it is.”
Bing projects a holographic image of the drone’s circuit board on Alice’s headset, highlighting the different components and their functions.
Alice examines the image and compares it with the actual circuit board. She sees that one of the capacitors is burned out and needs to be replaced.
She says: “Bing, can you tell me the specifications of this capacitor?”
Bing responds: “This capacitor is a 100 microfarad electrolytic capacitor with a voltage rating of 16 volts. It is used to smooth out the voltage fluctuations from the battery.”
Alice says: “Thanks, Bing. Do I have one of these in my toolbox?”
Bing responds: “Yes, you do. It is in the third compartment from the left, labeled C3.”
Alice opens her toolbox and finds the capacitor. She uses her soldering iron to remove the old capacitor and replace it with the new one.
She says: “Bing, can you check if I have done it correctly?”
Bing responds: “Yes, you have. The capacitor is soldered correctly and there are no short circuits or loose connections.”
Alice says: “Great. Is there anything else I need to do?”
Bing responds: “No, that’s all. You have successfully repaired the drone’s circuit board. You can now test it by turning on the drone and checking its functions.”
Alice says: “Thank you, Bing. You have been very helpful.”
Bing responds: “You’re welcome, Alice. I’m glad I could assist you. Have a nice day.”
After Bing provided this scenario, I asked, “How would Bing know what is and isn’t in her toolbox?”
It replied, “Bing knows what is and isn’t in Alice’s toolbox because she has scanned and registered her tools with the HoloLens headset before using it. Bing can access the information from the cloud storage where Alice’s data is stored and synced. Bing can also use the graphics recognition module to identify the tools visually and match them with the specifications.”
Okay, I’m not even going to dwell on the uncanniness of Bing’s ability to write a fiction and then seamlessly fill in any plot holes after the fact. The point is that we can see how an experienced professional might be able to use an AI-enhanced, image-recognition device.
Start with a Smartphone
Most of this will be done by smartphones in the near future. But people often need to work with both hands, so wearing the device like a pair of eyeglasses makes more sense in the long run.
So, yes, smartphones will come first, smart glasses second. The first movers will adopt glasses quickly, the fast followers the next year, and within five years smart glasses will be commonplace.
The Weekend Mechanic
Then there’ll be the prosumers, the folks who want the latest gear to pursue their weekend hobbies, whether that’s working on their car, building their electronic doodads, doing home improvement jobs, or anything else you can think of.
In truth, the prosumer market will probably be more lucrative than the pro market because A) there are more prosumers, and B) professional mechanics and other skilled workers already know how to do their jobs. They’ve developed habits that will be hard to break. But that doesn’t mean they won’t come around if they really believe the tech will help them.
AR Finally Gets Useful
Up until now, most use cases for AR glasses have been pretty limited. With the rise of these new AIs, however, everyone gets access to an enormous electronic brain jam-packed with detailed information.
What’s more, the AIs themselves will get better over time at understanding the real-world problems inherent in these professions. And, unlike most of us, the AIs aren’t likely to forget the details of what they’ve learned over time.
Eventually there will be talk of robots doing these kinds of work. That may happen, but long before then, there will be skilled workers as well as passionate weekend amateurs who are made better via AI-enabled smart glasses.
The Dangers of BS
But there’s also a danger here: that all forms of these AIs so far generate incorrect information at times. Some have even called them BS machines because they so confidently put forward made-up facts.
This is annoying for journalists, who must fact-check everything coming out of an AI. But it could potentially be deadly for people like mechanics, electricians and those who rely on their work.
So either these systems become more trustworthy over time (possibly by relying only on databases specific to certain professions), or workers must continue to rely on current quality assurance procedures, never putting full faith in AIs on the job. If the latter, some will argue against their usage in the first place, and they may carry the day in some professions or organizations. We’ll have to see how it plays out. I imagine there will be a tug of war in both directions.