The chance to text with the dead via AI is creepy or wonderful

An effort is underway in the AI community to develop posthumous avatars that can ease the pain of mourning. Not everyone thinks this is a good idea.

The human mind isn’t good at grasping certain very big things, perhaps chief among them infinity. The idea of infinite space is a head-scratcher, but the idea of infinite time can be truly mind-busting, especially when one is trying to get a grip on death, either their own or someone else’s. What does it mean, as many of us believe to be our fates, to not be forever? When someone dies, it’s this aspect of their passing that seems so unreal, impossible almost. How can someone who was just here be so completely gone? And forever? The process of acquiring enough acceptance to return to life and be able to even imagine joy again is often a painful, protracted one. Different cultures through the ages have developed their own ways of grieving, and now technologists are working on a new one for our time, or a little ways off in the future: griefbots.

Chatting with the dead

We spend so much of our time feeding social media and each other with our thoughts, photos, favorite memes, and so on, that each of us leaves quite the digital footprint behind. This is especially true of Millennials. It all amounts to a lot of information about us — or at least who we pretend to be on social media. A number of AI experts and programmers think it’s nearly enough info to construct digital replicas of ourselves who can convincingly chat with our friends and loved ones after we’re gone.


Hossein Rahnama of Ryerson Univerity says the sweet spot of having enough data to really pull this off is around a zettabyte, telling Quartz, “Fifty or 60 years from now, Millennials will have reached a point in their lives where they each will have collected zettabytes [1trillion gigabytes] of data, which is just what is needed to create a digital version of yourself.” How much of yourself is an interesting question, though, with Rahnama cautioning that a zettabyte is also just about the threshold at which a simulation would be Campbell of revealing a bit too much: “We have to consider an individual’s privacy when it comes to passing on virtual profiles. You should be able to own your data and only pass it along to people you trust, so allowing people to engage with their own ancestors would be likely.”

Still, there are a number of programmers working on developing believable chatbots, motivated not just by their own desire to continue to interact with the departed, but also to share those lost with others who never got to know them alive, as Muhammad Ahmad is doing for his children by programming a bot of his late father.


The idea is for the bots to do more than merely play back — in text, audio, or synthesized speech — thing once written or said by the deceased. Instead, the goal is for machine-learning algorithms to learn from data left behind what the person was like and how they communicated in order to create a digital avatar that’s identical to the original person. These avatars could even conceivably keep up with current events, allowing the living to continue having brand-new conversations that they theoretically might have had with the dead. Of course, there are hazards to this. As Pamela Rutledge of Media Psychology Research Center tells The Daily Beast, “What you don’t want is people taking advice from a bot.”

We’re still a ways off from truly convincing bots, though, and even when such a thing is possible, the AI “person” will not be the original one, no matter how seemingly identical it is. Should a time arrive when we physically merge with machines, of course, things may not be so simple.

Escaping grief?

There’s some disagreement as to whether AI simulacra would help make grieving less painful or make it worse by prolonging the recovery process. Certainly, an AI replica of a loved one does nothing to help us answer the big questions mentioned above — the originals are still gone as they’ll ever be.

Some grief experts feel that we’d be better off to face the pain and confusion that accompany a death directly. Psychologist Ernest Becker, the author of The Denial of Death, is concerned that an AI doppelgänger could interfere with an important corner that needs to be turned during grieving, saying, “People will always continue to mourn, but at a certain point people remember instead of relive.” (Our emphasis.) Getting too attached to what he calls a “projection of memories” could leave one stuck in a sad, irresolvable place.

Others suggest a bot could help a survivor transition into acceptance gently, essentially weaning themselves from the departed’s presence in their lives. But would you be comforted by a little more time with the something like the person who’s just died? And would you find a bot texting you “I’m alright,” or “I miss you, too,” to be comforting or a stabbing reminder of your loss? Eugenia Kuyda, a pioneer in this field, likes when the bot she’s developed of her late friend Roman Mazurenko reassures her.


Some say that a griefbot could help survivors through their loss by giving them a comforting way to share their pain. Grief counselor Andrea Warnick tells Quartz, “In modern society, many people are hesitant to talk about someone who has died for fear of upsetting those who are grieving — so perhaps the importance of continuing to share stories and advice from someone who has died is something that we humans can learn from chatbots.”

In Season 2 of the Netflix series Black Mirror, a new widow invites first a chatbot simulation of her husband, then a voice bot, and then finally a full-sized — and apparently fully functional, ahem — android into her life. “Be Right Back” is a haunting episode that captures what this experience may indeed someday be like. Rutledge’s concern is pretty much what happens to the widow: “If you have a lot of contact with something… [but] you don’t have this awareness that [para-social relationships] can happen, you might end up with a relationship that actually keeps you from grieving the loss of that person.”

Widow Martha and her late husband Ash’s android (Netflix)

The missing piece of the puzzle

Here’s a problem. What we miss as much about the dead as their traits, manner, and sense of humor — to name just three attributes — is how they make us feel because of how they feel about us. Considering this, for all of our genius at data collection, machine learning, and AI, until a time arrives when AI can truly feel, any such simulated relationship will emanate from an ice-cold core, empty of the most important ingredient in a close relationship: Love.

Big Think
Sponsored by Lumina Foundation

Upvote/downvote each of the videos below!

As you vote, keep in mind that we are looking for a winner with the most engaging social venture pitch - an idea you would want to invest in.

Keep reading Show less

Scientists discover how to trap mysterious dark matter

A new method promises to capture an elusive dark world particle.

Surprising Science
  • Scientists working on the Large Hadron Collider (LHC) devised a method for trapping dark matter particles.
  • Dark matter is estimated to take up 26.8% of all matter in the Universe.
  • The researchers will be able to try their approach in 2021, when the LHC goes back online.
Keep reading Show less

Yale scientists restore brain function to 32 clinically dead pigs

Researchers hope the technology will further our understanding of the brain, but lawmakers may not be ready for the ethical challenges.

Still from John Stephenson's 1999 rendition of Animal Farm.
Surprising Science
  • Researchers at the Yale School of Medicine successfully restored some functions to pig brains that had been dead for hours.
  • They hope the technology will advance our understanding of the brain, potentially developing new treatments for debilitating diseases and disorders.
  • The research raises many ethical questions and puts to the test our current understanding of death.

The image of an undead brain coming back to live again is the stuff of science fiction. Not just any science fiction, specifically B-grade sci fi. What instantly springs to mind is the black-and-white horrors of films like Fiend Without a Face. Bad acting. Plastic monstrosities. Visible strings. And a spinal cord that, for some reason, is also a tentacle?

But like any good science fiction, it's only a matter of time before some manner of it seeps into our reality. This week's Nature published the findings of researchers who managed to restore function to pigs' brains that were clinically dead. At least, what we once thought of as dead.

What's dead may never die, it seems

The researchers did not hail from House Greyjoy — "What is dead may never die" — but came largely from the Yale School of Medicine. They connected 32 pig brains to a system called BrainEx. BrainEx is an artificial perfusion system — that is, a system that takes over the functions normally regulated by the organ. The pigs had been killed four hours earlier at a U.S. Department of Agriculture slaughterhouse; their brains completely removed from the skulls.

BrainEx pumped an experiment solution into the brain that essentially mimic blood flow. It brought oxygen and nutrients to the tissues, giving brain cells the resources to begin many normal functions. The cells began consuming and metabolizing sugars. The brains' immune systems kicked in. Neuron samples could carry an electrical signal. Some brain cells even responded to drugs.

The researchers have managed to keep some brains alive for up to 36 hours, and currently do not know if BrainEx can have sustained the brains longer. "It is conceivable we are just preventing the inevitable, and the brain won't be able to recover," said Nenad Sestan, Yale neuroscientist and the lead researcher.

As a control, other brains received either a fake solution or no solution at all. None revived brain activity and deteriorated as normal.

The researchers hope the technology can enhance our ability to study the brain and its cellular functions. One of the main avenues of such studies would be brain disorders and diseases. This could point the way to developing new of treatments for the likes of brain injuries, Alzheimer's, Huntington's, and neurodegenerative conditions.

"This is an extraordinary and very promising breakthrough for neuroscience. It immediately offers a much better model for studying the human brain, which is extraordinarily important, given the vast amount of human suffering from diseases of the mind [and] brain," Nita Farahany, the bioethicists at the Duke University School of Law who wrote the study's commentary, told National Geographic.

An ethical gray matter

Before anyone gets an Island of Dr. Moreau vibe, it's worth noting that the brains did not approach neural activity anywhere near consciousness.

The BrainEx solution contained chemicals that prevented neurons from firing. To be extra cautious, the researchers also monitored the brains for any such activity and were prepared to administer an anesthetic should they have seen signs of consciousness.

Even so, the research signals a massive debate to come regarding medical ethics and our definition of death.

Most countries define death, clinically speaking, as the irreversible loss of brain or circulatory function. This definition was already at odds with some folk- and value-centric understandings, but where do we go if it becomes possible to reverse clinical death with artificial perfusion?

"This is wild," Jonathan Moreno, a bioethicist at the University of Pennsylvania, told the New York Times. "If ever there was an issue that merited big public deliberation on the ethics of science and medicine, this is one."

One possible consequence involves organ donations. Some European countries require emergency responders to use a process that preserves organs when they cannot resuscitate a person. They continue to pump blood throughout the body, but use a "thoracic aortic occlusion balloon" to prevent that blood from reaching the brain.

The system is already controversial because it raises concerns about what caused the patient's death. But what happens when brain death becomes readily reversible? Stuart Younger, a bioethicist at Case Western Reserve University, told Nature that if BrainEx were to become widely available, it could shrink the pool of eligible donors.

"There's a potential conflict here between the interests of potential donors — who might not even be donors — and people who are waiting for organs," he said.

It will be a while before such experiments go anywhere near human subjects. A more immediate ethical question relates to how such experiments harm animal subjects.

Ethical review boards evaluate research protocols and can reject any that causes undue pain, suffering, or distress. Since dead animals feel no pain, suffer no trauma, they are typically approved as subjects. But how do such boards make a judgement regarding the suffering of a "cellularly active" brain? The distress of a partially alive brain?

The dilemma is unprecedented.

Setting new boundaries

Another science fiction story that comes to mind when discussing this story is, of course, Frankenstein. As Farahany told National Geographic: "It is definitely has [sic] a good science-fiction element to it, and it is restoring cellular function where we previously thought impossible. But to have Frankenstein, you need some degree of consciousness, some 'there' there. [The researchers] did not recover any form of consciousness in this study, and it is still unclear if we ever could. But we are one step closer to that possibility."

She's right. The researchers undertook their research for the betterment of humanity, and we may one day reap some unimaginable medical benefits from it. The ethical questions, however, remain as unsettling as the stories they remind us of.

  • As a stand-up comedian, Pete Holmes knows how words can manipulate audiences — for good and bad.
  • Words aren't just words. They stich together our social fabric, helping establish and maintain relationships.
  • Holmes has a clever linguistic exercise meant to bring you closer to the people around you.