Skip to content

Archive for


RoboPsych Interview about the TV Show “Humans”

On September 17, 2015, the psychologist Tom Guarriello interviewed me for his “RoboPsych” podcast:

We talked about the newly-emerging psychology of humans interacting with robots and AI. And, *SPOILER WARNING*, we discussed the first season of the excellent recent AMC/BBC show “Humans”.

The flood of recent movies and TV shows exploring the impact of robots and AI. Early shows like Terminator and Robocop focused on “Us vs. Them”. More recent shows like “Her” and “Humans” explore subtler aspects of the interaction.

The archetype of the “Out of Control Creation”. The Sorcerer’s Apprentice. Stories of Genies giving three wishes but with unintended outcomes. King Midas. The “Uh-Oh!”. Even if you get what you think you want, it may not be what you really want. Adam and Eve as the first out of control creation story. We ourselves are out of control. Fear of the other is a projection of our own darker inner drives.

“Humans” takes place in the present but with a more advanced “Synth” android robot technology. Family dynamics with Synths. The little girl sees the synth as a mother figure. The mother is jealous of the synth. The teenage boy is sexually attracted to the synth. Synths as a memory prosthetic. Synths with consciousness. Synths with subpersonalities.

How close is today’s technology to anything like this? Economic drivers for building AIs that recognize human emotional facial and vocal expressions. Recent Microsoft AI to judge the humor of New Yorker cartoons. Artificial empathy. Jibo and Pepper. Things are moving extremely rapidly. McKinsey estimates $50 trillion dollars of impact in the next 10 years. Deep Learning is used for many functions. Baidu using it for Chinese. If understanding human emotions has economic value, it will soon be in the marketplace.

Humans are not good at determining how emotionally intelligent an entity is. Eliza was an early 1960’s AI system. It used simple pattern matching to mimic a Rogerian therapist. Yet people spent hours talking to it! Deep tendency for people to form attachments to objects. People naming their Roombas. Soldiers attached to their IED-detecting robots. Synths can behave more maturely than humans! Non-Violent Communication.

Synths in the service of marketing for a brand? “Hidden Persuaders” and sexuality in advertising. Brands adopt the “Jester” archetype when they ride on deep primal urges like sexuality. Japan and virtual girlfriends. Japan’s relationship to robots. Robots for elder-care. Belief in robot euthanasia hoax. The uncanny valley. Elder’s experience with robotic companions. Robot pets. Tamagotchi. Sony stopping Aibo robot dog support. Kids don’t learn how to handwrite anymore. Horse riding becoming less common. Future shock. Visions of the future from the past. Approach/Avoidance conflicts.

Creators of these systems want them to have intelligence and creativity but they also want to retain control of them. Are they alive, what rights do they have? Building in safeguards. How can we have confidence that these systems won’t run amok? In Humans, the Synths exhibit ambiguity about their own consciousness. Give the code for consciousness to a human for safekeeping. But Niska secretly keeps her own copy and may want to spread it in Season Two! The Synth’s experiences affect their behavior.

What happens when a system can change its own structure? What is the nature of goals and behavior? Unintended consequences. Basic Rational or AI Drives for self-preservation, resource acquisition, replication, efficiency. We need to be careful as we build systems with their own intentions. Deep mind system that adapts to play video games. When will systems start exhibiting unexpected behavior? Robot “Fail” videos. “Whistling past the graveyard?” When we see goofy behavior, it assuages our fear: “Nothing to see here. Move along.”

Robot soldiers, South Korean autonomous gun turret, drones, etc. “How can we be very sure that these systems are safe?” A conservative strategy: The “Safe-AI Scaffolding Strategy”. Regardless of how smart they are, these systems have to obey the laws of mathematics and physics. Create mathematical proofs of properties of behavior. But proofs are hard. Need AI systems to help us establish safety guarantees. Start with very constrained systems like biohazard labs. Err on the side of caution because we are toying with very powerful forces here.

Psychoanalytic aspects of the Beatrice Synth. Suicidal synths? Humanity vs. being human. Ending of the first season with an anti-synth “We are human” protest and the conscious synths escape by blending in with the humans.


China is rapidly automating

Many in the U.S. have viewed cheap labor as China’s primary strength. But Chinese labor costs have nearly quadrupled over the past 10 years:

average wage 2004 2014

Recent studies have shown that it’s now just as cheap to manufacture in the U.S. as in China. This is one motivating force behind China’s rapid adoption of automation.

The Changying Precision Technology Company just set up the first unmanned factory in Dongguan city. 60 robots now perform tasks that required 650 workers just a few months ago. The defect rate has dropped by a factor of 5 and productivity has increased by almost a factor of 3. The city of Dongguan plans to complete 1,500 more “Robot replace human” factory transformations by 2016.

The use of robots in Chinese factories has been growing at a 40% annual rate and China is expected to have more manufacturing robots than any other country by 2017. The rapidity of adoption is shown in the following chart:


There are now 420 robot companies in China! The Chinese Deputy Minister of Industry Su Bo has described a robot technology roadmap for China to become a dominant robotics provider by 2020.

Robin Li Yanhong, the CEO of Baidu also wants to make China the world leader in AI. He has proposed the “China Brain” project as a massive state-level initiative “comparable to how the Apollo space programme was undertaken by the United States to land the first humans on the moon in 1969.” Last year Baidu hired Stanford and Google researcher Andrew Ng who says: “Whoever wins artificial intelligence will win the internet in China and around the world. Baidu has the best shot to make it work.”


McKinsey: $50 trillion of value to be created by AI and Robotics through 2025

To better understand the likely social impact of AI and Robotics, it’s very useful to have an estimate of the economic gains they will create in the near future. The respected consulting firm McKinsey & Company recently released the report: “Disruptive technologies: Advances that will transform life, business, and the global economy”. The report estimates the likely economic impact of 12 disruptive technologies ten years from now in 2025.
To get a better sense of the scale of the forces involved, I wanted a single number that would summarize the economic impact of just AI and Robotics over the next 10 years. I took the 5 technologies that could be considered “AI and Robotics” and their ranges in “trillions of dollars of impact annually”:
  • Automation of knowledge work: $5.2-6.7 trillion
  • Internet of things: $2.7-6.2 trillion
  • Advanced robotics: $1.7-4.5 trillion
  • Autonomous and near-autonomous vehicles: $.2-1.9 trillion
  • 3D printing: $.2-.6 trillion
Adding those up in 2025 we get a total range of impact for 2025 of $10-19.9 trillion. To get the total economic impact for the 10 years from 2015 to 2025 we need to estimate how fast these technologies will ramp up. The simplest model is linear starting from $0 and ramping up to the 2025 level. This is something of an underestimate because the current impact is not $0, but something of an overestimate because it neglects the convexity of the growth curve. The linear approximation is just 10 times the 2025 impact divided by 2 and gives a range of:
  • Total impact to 2025: $50-99.5 trillion
To account for the approximations, I use the low end of this range, i.e. $50 trillion, as a reasonable summary of the scale of the likely impact.