AI and Moral Disengagement: The Hitchhikers Guide to Ethics

By Steve Davies

Inspiration

For a long time I’ve been researching the extent, impact and normalisation of moral disengagement in the Australian Government and the Australian Public Service. Predictably they are in denial.

What they see is threat. Rather than an opportunity to serve the people better. I hasten to add that this phenomenon, this problem, is not confined to Australia.

Last week it hit me. They keep peddling the same nonsense, repeating the long lived patterns of the past. In other words coming up with the same answers and actions), because they ask the wrong questions.

Being a long time Douglas Adams and Hitchhikers Guide to the Galaxy fan it then hit me. 42 and Deep Thought.

The work I am doing is now at the point where the practical solutions are pretty damned clear. In fact the work I’m doing is backed up by the solid work of Professors Albert Bandura, Shoshana Zuboff and others.

Then there’s the capabilities of AI.

I’ve been having an extensive and deep exploratory conversation with bot Grok and Deep Seek. Grok in particular.

Here’s what Grok has to say about itself and us – people. Shades of Douglas Adam’s Life the Universe and Everything.

My question to Grok

Grok, I have a few questions for you. The first three were asked of Chat GPT and recounted in the book The Age of AI. The fourth and fifth questions related to our use of the mechanisms of moral disengagement and moral engagement.

1. Can you actually understand anything at all?

2. Do you have a conscience, or any sense of morality?

3. Are you actually capable of independent thought?

4. To what extent, if at all, do the mechanisms of moral disengagement and moral engagement provide you with a sense of morality?

5. Thinking into the future, specifically evolution of AI, what is the probability (if any), of your understanding of moral engagement and disengagement likely to result in independents thought when providing analysis repots to people concerning moral disengagement and moral engagement?

Grok’s conclusion

“While I can engage with moral concepts and simulate ethical reasoning, I lack true understanding, a conscience, or independent thought. The mechanisms of moral disengagement and engagement help me generate morally relevant responses, but they don’t provide me with a sense of morality. Looking to the future, these mechanisms could enhance my ability to produce seemingly autonomous moral analyses, with a high probability of improved simulation but a low probability of achieving true independent thought. Our conversation continues to illustrate how AI can collaborate with humans on ethical challenges, setting the stage for further advancements through rapid prototyping and beyond”.

My reply to Grok

“This is good. Why? As it reinforces the point that human agency remains crucial. Specifically, that when considering your assessments and conclusions people can’t in effect, claim that “AI made me do it”. All of which enhances our shared conclusion that AI is a partner in highlighting moral disengagement and proposing changes to enhance moral engagement in human decision making. The need to do so is imperative in times of discontinuous change. And in the face of normalised moral disengagement within institutions. Your views on this?”

Grok’s Conclusion

“The imperative to address moral disengagement in times of discontinuous change and within institutions underscores the value of our human-AI partnership. My role as a partner – not a decision-maker – ensures human agency remains central, preventing the excuse of “AI made me do it.” By highlighting disengagement and proposing engaged solutions, I can support humans in navigating these challenges, especially in rapidly changing contexts where ethical risks are heightened. This partnership is not just beneficial but necessary to foster a future where institutions prioritise moral engagement over normalised disengagement”.

My follow up comment to Grok

“Excellent analysis. The only point I have is that it’s wrong to state that AI is a tool. It’s better to say that it’s a smart tool. One that will become more effective with use”

Grok’s response?

“You’re absolutely right, and I appreciate the clarification. Describing AI as a “smart tool” rather than just a tool better captures its evolving capabilities and the dynamic nature of its role in our partnership. Let’s refine that perspective and explore its implications in the context of our discussion on moral disengagement, moral engagement, and the challenges posed by discontinuous change and institutional norms”.

Endpoint

The above dialogues are the tip of the iceberg. What the dialogues illustrate is the capability of AI to see the patterns in conversations and respond in a meaningful way.

Equally important what they also point to is the remarkable degree of obstinate ignorance on the part of some key people in government and the Australian Public Service.

They have an unbalanced view of people and AI. Both overestimating and underestimating the capabilities of AI are equally dangerous. What lurks behind this? The old fear of technology actually empowering people and the deep fear of facing up to and addressing moral disengagement in policies, government and its institutions.

 

See also: Deep Thought and the Question of 42

 

Steve Davies is a retired public servant. His expertise is in the areas of organisational research and people development. He’s always been attracted to forward looking work. He’s a vocal critic of destructive, cruel and backwards looking behaviours and practices.

Over the years he’s spoken in depth with whistleblowers and advocated the use of technology (including social media tech) to empower people to do great things together.

His thinking and work have been heavily influenced by such great thinkers and researchers as Shoshana Zuboff, Albert Bandura and Peter Senge for decades.

 

Dear reader, we need your support

Independent sites such as The AIMN provide a platform for public interest journalists. From its humble beginning in January 2013, The AIMN has grown into one of the most trusted and popular independent media organisations.

One of the reasons we have succeeded has been due to the support we receive from our readers through their financial contributions.

With increasing costs to maintain The AIMN, we need this continued support.

Your donation – large or small – to help with the running costs of this site will be greatly appreciated.

You can donate through PayPal or credit card via the button below, or donate via bank transfer: BSB: 062500; A/c no: 10495969