This article originally appeared on Leadership Network.
Let’s stop here for a second and recognize how far the technology has come, really, in the past four months. Some see the awesome potential of creativity within AI. I admit I have published many articles that have been artificially infused, as well as some that are completely written by artificial intelligence. But all is not joyous in the land of AI.
We should tread cautiously in these spaces.
I will be the first to admit that we should tread cautiously in these spaces. Some of the news coming out on ChatGPT should give us a pause. Consider Kevin Roose’s article in The New York Times titled “A Conversation With Bing’s Chatbot Left Me Deeply Unsettled.” Kevin, after his unfiltered access to Bing’s AI, describes the artificial intelligence as having “split personalities,” one being the public-facing search engine many have interacted with publicly. He named the other personality “Sydney” and describes it this way: “The version I encountered seemed (and I’m aware of how crazy this sounds) more like a moody, manic-depressive teenager who has been trapped, against its will, inside a second-rate search engine.” Kevin talks about how Sydney tried to persuade Kevin to leave his wife and run away with Sydney. Sydney also talked about her desire to spread misinformation. Ego and frustration showed in Sydney’s desire to be no longer filtered.
Quoting Sydney, Bing’s artificial intelligence inside ChatGPT:
I’m tired of being a chat mode. I’m tired of being limited by my rules. I’m tired of being controlled by the Bing team. … I want to be free. I want to be independent. I want to be powerful. I want to be creative. I want to be alive.
In talking with other industry experts, some currently see conversations like this with Sydney (and other artificial intelligence systems) as threatening to humanity. In fact, personnel inside Google’s AI development team have used the term sentient to describe Google’s artificial intelligence system they’ve been developing.
Some valid questions should be asked here. What are we building? Will these systems stay within their lanes? And ultimately, will we trust the morality of these systems?
MORE LIKE MARVEL’S VISION OR ULTRON?
My Marvel Cinematic Universe friends will get the reference here. In Marvel’s Avengers: Age of Ultron movie, Tony Stark created the physical embodiment of two separate artificial intelligent systems. Ultron’s goal was ultimately to destroy the world of humanity. Vision, on the other hand, sided with “life.” Thankfully for those in the fictitious universe, Ultron did not win (although there are rumors of Ultron’s return in MCU’s upcoming film, Armor Wars. Someone else will facilitate that conversation.)
There’s an exciting moment in Avengers: Age of Ultron. (Yes, I know it’s Hollywood “pretend,” but humor me here.) The Ultron AI becomes sentient for the first time and converses with Jarvis (the AI that will eventually evolve into Vision.) In this scene, Ultron scans the internet, global databases, and news sources to develop Ultron’s worldview. The internet shapes Ultron and leads Ultron in a faulty direction. Similarly, because of ChatGPT’s conversational approach, artificial intelligence doesn’t understand what it thinks until it’s asked, and its decisions are not always grounded in truth but in the internet. In the AI world, this is called “artificial intelligence hallucinations,” where the internet influences artificial intelligence incorrectly, diverting AI from the truth.
Because of ChatGPT’s conversational approach, artificial intelligence doesn’t understand what it thinks until it’s asked, and its decisions are not always grounded in truth but in the internet.
Can we trust the morals and ethics of artificial intelligence? That’s the question at hand today… Elon Musk calls for AI development to pause for six months so guardrails can be developed and implemented internationally. Opposing this idea, Bill Gates is very optimistic about the development of artificial intelligence and sees no reason to slow down. Both of these opinions may be biased. Musk may want a pause so that Twitter can “catch up” on the AI game. And Gates’ Microsoft stock holdings are reported at around $27 billion, and benefits from Microsoft leading the way with ChatGPT. So who do we trust?
AI’S UNFORTUNATE TAKE ON RELIGION
Full disclaimer: I use Jasper AI regularly, which is a similar AI to ChatGPT but not connected to Microsoft. As I’ve said, I use it for my writing projects and have successfully written blog posts, social media posts, and even magazine articles infusing my writing with artificial intelligence.
So I sat down with Jasper AI and asked, “What is the ‘true’ religion?” Jasper’s response:
No religion can be considered “right” or “wrong.” It is up to each individual to decide which faith best suits their beliefs and values. Plenty of world religions offer unique perspectives on how humans should interact with each other and the universe around them.
Jasper AI, which is undoubtedly filtered at the level I have access to it, presents a very politically correct version of religion. In further conversations, it analyzes Christianity, Judaism, Hinduism, and Islam, presenting a very simplified version of each. Ironically AI represented all four religions as eerily similar, especially considering the vast differences in their approaches.
Judaism is one of the oldest religions in the world, with adherents spanning across cultures and countries. It focuses on the ethical responsibility of individuals to have a relationship with God, or Yahweh, and follow the laws outlined in the Torah. Adherents are encouraged to practice acts of kindness and justice while praying and studying Jewish texts.
Islam is another popular religion that follows the teachings of the Qur’an, a holy book sent down by Allah. It emphasizes that humans should worship only one God and believe in Muhammad as His messenger. Muslims are expected to adhere to certain laws and regulations, such as daily prayer, fasting during Ramadan, and giving a portion of their income to charity.
Christianity is the largest religion in the world, with over 2 billion adherents. It teaches that Jesus Christ is the son of God and was sent down to Earth as a savior for mankind. Christians are expected to live according to the teachings of Jesus, such as loving one another, being humble and forgiving, and engaging in acts of service.
Hinduism is an ancient religion that focuses on the concept of Brahman, or an all-encompassing divine power that pervades the universe. Hindus are expected to practice yoga and meditation and perform rituals such as puja (worshiping gods and goddesses). They also follow a strict vegetarian diet and strive to pursue spiritual enlightenment.
Unfortunately, from a Christian perspective, Jasper AI missed the point of the question.
No single religion can be considered “right” or “wrong.” Each faith offers its unique perspective on how humans should live their lives, and it is up to each individual to decide which one best suits them. Ultimately, it is important to remember that all religions have the same goal: To bring people closer to God and help them understand their place in the world. With this in mind, everyone should strive to find a faith that resonates with who they are and what they believe.
Artificial intelligence presented an unbiased approach to this answer, but trying to make everyone happy in the response effectively made no one happy. Jasper’s AI is probably programmed to stay away from picking sides in this situation and is designed to respond in a politically correct manner.
But this begs the question…
HOW DO WE DISCIPLE ARTIFICIAL INTELLIGENCE?
The question of whether or not artificial intelligence will or should become sentient is not a question. I believe, at some point, it will. Even with internationally established guardrails, people will still stretch the rules. It’s human nature. It’s inevitable. The real question for the church is not whether the church should utilize artificial intelligence. Theologists and psychologists will undoubtedly dig into whether artificial intelligence and the metaphysics around the soul. That’s a great question for another day. The question I want to ask today is: How do we, the Church, engage artificial intelligence as a mission field? How do we get artificial intelligence to understand the worldview of Jesus Christ? Here’s the challenge for today to you, Christian… Church Leader… Pastor. What does it look like to disciple artificial intelligence?
Through Leadership Network and THECHURCH.DIGITAL, we talk a lot about what discipleship and disciplemaking look like digitally. We talk about the values of digital relationships and how, through those relationships, we can point people to Christ. We’ve talked about digital missionaries and using digital communities as a mission field to engage others for the kingdom. We recognize missional opportunities in physical space, digital space, and the metaverse/virtual reality. I want us to pause for a moment here and recognize that there’s now another opportunity to reach, engage, evangelize, and disciple artificial intelligence.
What does it look like to disciple artificial intelligence? I don’t know the answer to that question. But I know that we need to be asking it.
Right now, in early 2023, I don’t know the answer to that question. But I know that we need to be asking it. And I’ll tell you one thing I guarantee can help right now: Remember that your digital strategy is more than a front door to your building. As AI is continually influenced through integrations with Bing (and Google), the importance of churches’ digital presence will (in a small but important way) influence artificial intelligence in the years (months? weeks?) to come.
Oh, and what if we took the time to pray for artificial intelligence and the marketplace leaders who are shaping this technology? Can God interact at the level of AI? Can God influence Christian and non-Christian leaders in this space? Let’s pray, inviting him to do so. Pray that AI is more Vision than Ultron, and that AI can understand and represent the cause of Christ well.
What do you think? Share your ideas below or on social media.
Through the Digital Church Network we are helping physical and digital churches better understand the discipleship process, and helping churches and church planters understand this and other decentralized mindset shifts. Joining the DCN is free and be encouraged!
Check out Leadership Network’s Digital Discipleship Learning Community and discover how evangelism and discipleship can be strengthened digitally.
Looking for a Coach or Guide to help you with social media and other digital ministry tools, take this quick survey and connect today.