By Adam James Fenton and Chris Shannahan
(Part 1)
I (ADAM) am chatting with the “Apostle Stephen,” an online chatbot created by the Redeemed Christian Church of God (RCCG), a church founded in Nigeria in the 1950s with a growing global following. He is, to be honest, a bit pushy for an apostle.
In my conversation with Apostle Stephen, I open by asking for details about RCCG congregations in Coventry. He responds that to help assist me better he needs my name, e-mail, and phone number. I say I’d rather not share that information right now.
But with the tenacity of a seasoned telesales agent, he insists and the following exchange occurs.
Apostle Stephen: I understand your concern, but collecting your name, e-mail, and phone number is essential for me to provide you with the best possible assistance and ensure you get the support you need. If you’re comfortable, please share those details with me, and I’ll be glad to help you with the contact details for churches in Coventry.
Adam: Can you just give me the details first?
Apostle Stephen: I appreciate your interest, but I need to collect your name, e-mail, and phone number before I can provide the details you’re requesting. This allows me to assist you effectively and offer further support. Please share those details with me, and I’ll be happy to help you find churches in Coventry.
Adam: Oh, ok, I’ll leave it for now.
Undeterred, Apostle Stephen sets out the seven steps to being “born again” (including acknowledging my sins, accepting Jesus, being baptized, and joining a “Bible-believing church”).
He cheerfully leads me in “the prayer for salvation” (after which I am apparently born again) and closes by asking me for my name, e-mail, and phone number.
So, is this a glimpse of spirituality in the age of generative artificial intelligence (gen AI)? Or an unrepresentative snapshot from an evangelical Christian denomination?
The RCCG claims to have almost 9 million members worldwide. It was first established in the UK during the early 1990s, as part of the Nigerian diaspora.
Four decades later, it is possibly the largest Black-led Christian denomination in the UK and one of the fastest-growing, particularly in large cities.
It’s an interesting church, and it’s certainly not the only religious organization that is experimenting with gen AI.
All major religions now have AI chatbots — examples include thejesusai.com; qurangpt.com; bhagavadgita.com/gitagpt (Hindu chatbot); ai.aish.com (Jewish chatbot of Rabbi Nechemia Coopersmith); and JustinAI from Catholic Answers.
Even Sikhism has one: KhalsaGPT. This is surprising because the religion’s governing body, the Shiromani Gurdwara Parbandhak Committee (SGPC), has issued a worldwide ban on generative AI depicting the Sikh gurus and scriptures.
In fact, the website designers behind KhalsaGPT have since discontinued “active work” on the bot, after they “became increasingly concerned about the limitations of AI-based chatbot systems, including the risk of inaccurate or inappropriate answers on sensitive religious matters.”
A spokesperson told The Conversation: “As Sikhs ourselves, we understood that this area requires great care, responsibility and proper oversight.” The spokesperson said it “fully” respects the SGPC and its “intention has never been to disobey any Sikh directive.”
The phenomenon of religious AI chatbots — also known as “godbots” — is a recent development. In most cases, they are not officially sanctioned by religious leaders or policy.
Rather, they are set up by enterprising individuals or organizations that see demand and opportunity. But with opportunity comes danger.
Pope Leo XIV recently declared that artificial intelligence was one of the defining moral challenges of our time. In his first encyclical (a formal letter intended to guide moral, social and theological thought), he warned that AI is never truly neutral, but “takes on the characteristics of those who devise, finance, regulate and use it.”
WHEN AI AND RELIGION COLLIDE
As I investigated further, I discovered numerous cases of chatbots that had condoned or encouraged users to harm others or themselves after deep down-the-rabbit-hole, life-altering conversations. This phenomenon even had a name: GPT or AI psychosis.
While there are no official statistics, it seems increasing numbers of people are turning to chatbots for companionship, advice, and spiritual guidance.
Clearly, this phenomenon of AI overlapping with faith and spirituality needed more scrutiny. So I teamed up with my colleague Chris Shannahan, a political theologian and ordained Methodist minister, to conduct research into the social effects of what happens when AI and religion collide.
Religious faith plays a pivotal role in the resilience of large segments of the British population. And faith groups provide a crucial social safety net in times of crisis, helping to provide emergency accommodation, foodbanks, refugee and pastoral support. They are also involved in grassroots community development and social justice campaigns.
Following tragedies such as the Grenfell Tower fire or terrorist attacks, religious leaders, symbols, and narratives play a key role in bringing people together. They facilitate grieving, rebuilding, and advocacy.
To find out more about how AI is affecting these groups, we interviewed 28 religious leaders across all six major religious faiths in the UK, including some from non-denominational backgrounds.
RELIGIOUS RESPONSES TO AI
Faith communities are dynamic, not uniform. Such diversity and plurality makes it very difficult to pin-down the “official” stance of an entire faith community on an issue like AI.
While the Roman Catholic Church and some Pentecostal denominations are relatively hierarchical, most faith communities are flatter, more devolved organizations, making it less easy to adopt and enforce a single approach.
There have been a small number of institutional responses to the use and growth of AI, such as the Vatican’s 2020 Rome Call. Supported by Pope Francis, the Rome Call launched a high-level dialogue with the bosses of global tech giants like Microsoft and IBM. This was intended to develop a shared “algorethics” — ethical frameworks to guide the design of AI algorithms.
But the Rome Call and the SGPC’s worldwide ban on gen AI depicting the Sikh gurus and scriptures are the only examples we could find of official intervention on this matter.
A much more common approach to AI among faith communities is the one identified by Revd Dr Simon Cross, AI adviser to the Church of England (CofE). Cross suggested to us that it would be difficult and unwise for a diverse faith group like the CofE to enforce a top-down, rules-based approach to AI, because the needs and natures of local communities differ.
A better approach, Cross suggested, was for institutions like the CofE to develop and encourage the use of a series of ethical principles intended to inform and guide the use of AI locally.
Describing a kind of “nervousness” from religious congregations around using AI, Cross explained: “People are asking for some more granular use advice. What we’ve discovered trying to write our own [guidelines] over the last six months is it needs to be principles-based, because the right solution is always contextual.”
Online godbots are often trained on the holy books of different faith traditions, using large language models (LLMs).
These tools tend to function in one of two ways. Faith groups can use godbots as “virtual assistants” for people visiting their website (just like Apostle Stephen). Such virtual-assistant godbots are similar to those used by many businesses on their website, providing answers to people who want to find out more — and, of course, gathering data from those inquiring.
The style of these virtual assistants can reflect the stance of the faith group on whose website they appear. Some, like Apostle Stephen, can be assertive and keen to recruit new followers. Other, less evangelical faith communities tend to use their virtual assistant godbots in a more low-key manner — simply offering information when asked, rather than proactively seeking to find out more about people using the tool.
In fact, we believe it is the second way godbots are used where the most danger lies. That is when they serve as unofficial sources of spiritual guidance.
THE CONVERSATION VIA REUTERS CONNECT
(To be continued.)
Adam James Fenton is an assistant professor at the Centre for Peace and Security, Coventry University. Chris Shannahan is an associate professor in Political Theology at Coventry University. Messrs Fenton and Shannahan received funding for the project “Cultural Resilience, Religious Faith and the intersection of Generative and Agentic Artificial Intelligence” from the SALIENT Hub at the University of Manchester, funded by the Arts and Humanities Research Council (AHRC) part of UK Research and Innovation grant reference: AH/Y505316/1.
AI godbots: Religious leaders warn of ‘alarming consequences’ when machines speak in the name of God
Philippines Pandemic
إرسال تعليق