An Inconvenient Truth About AI
We are well into the third wave of major investment in artificial intelligence. So it’s a fine time to take a historical perspective on the current success of AI. In the 1960s, the early AI researchers often breathlessly predicted that human-level intelligent machines were only 10 years away. That form of AI was based on logical reasoning with symbols, and was carried out with what today seem like ludicrously slow digital computers. Those same researchers considered and rejected neural networks.
In the 1980s, AI’s second age was based on two technologies:
rule-based expert systems—a more heuristic form of symbol-based logical reasoning—and a resurgence in neural networks triggered by the emergence of new training algorithms. Again, there were breathless predictions about the end of human dominance in intelligence.
The third and current age of AI arose during the early 2000s with new symbolic-reasoning systems based on algorithms capable of solving a class of problems called
3SAT and with another advance called simultaneous localization and mapping. SLAM is a technique for building maps incrementally as a robot moves around in the world.
In the early 2010s, this wave gathered powerful new momentum with the rise of neural networks learning from massive data sets. It soon turned into a tsunami of promise, hype, and profitable applications.
Regardless of what you might think about AI, the reality is that just about every successful deployment has either one of two expedients: It has a person somewhere in the loop, or the cost of failure, should the system blunder, is very low. In 2002,
iRobot, a company that I cofounded, introduced the first mass-market autonomous home-cleaning robot, the Roomba, at a price that severely constricted how much AI we could endow it with. The limited AI wasn’t a problem, though. Our worst failure scenarios had the Roomba missing a patch of floor and failing to pick up a dustball.
That same year we started deploying the first of thousands of robots in Afghanistan and then Iraq to be used to help troops disable improvised explosive devices. Failures there could kill someone, so there was always a human in the loop giving supervisory commands to the AI systems on the robot.
These days AI systems autonomously decide what advertisements to show us on our Web pages. Stupidly chosen ads are not a big deal; in fact they are plentiful. Likewise search engines, also powered by AI, show us a list of choices so that we can skip over their mistakes with just a glance. On dating sites, AI systems choose who we see, but fortunately those sites are not arranging our marriages without us having a say in it.
So far the only self-driving systems deployed on production automobiles, no matter what the marketing people may say, are all Level 2. These systems require a human driver to keep their hands on the wheel and to stay attentive at all times so that they can take over immediately if the system is making a mistake. And there have already been fatal consequences when people were not paying attention.
Just about every successful deployment of AI has either one of two expedients: It has a person somewhere in the loop, or the cost of failure, should the system blunder, is very low.
These haven’t been the only terrible failures of AI systems when no person was in the loop. For example, people have been wrongly arrested based on face-recognition technology that works poorly on racial minorities, making mistakes that no attentive human would make.
Sometimes we are in the loop even when the consequences of failure aren’t dire. AI systems power the speech and language understanding of our smart speakers and the entertainment and navigation systems in our cars. We, the consumers, soon adapt our language to each such AI agent, quickly learning what they can and can’t understand, in much the same way as we might with our children and elderly parents. The AI agents are cleverly designed to give us just enough feedback on what they’ve heard us say without getting too tedious, while letting us know about anything important that may need to be corrected. Here, we, the users, are the people in the loop. The ghost in the machine, if you will.
Ask not what your AI system can do for you, but instead what it has tricked you into doing for it.
SOURCE: GOOGLE NGRAMS
This article appears in the October 2021 print issue as “A Human in the Loop.”