The Times Australia
The Times World News

.

Can machines be self-aware? New research explains how this could happen

  • Written by Michael Timothy Bennett, PhD Student, School of Computing, Australian National University
Can machines be self-aware? New research explains how this could happen

To build a machine, one must know what its parts are and how they fit together. To understand the machine, one needs to know what each part does and how it contributes to its function. In other words, one should be able to explain the “mechanics” of how it works.

According to a philosophical approach[1] called mechanism, humans are arguably a type of machine – and our ability to think, speak and understand the world is the result of a mechanical process we don’t understand.

To understand ourselves better, we can try to build machines that mimic our abilities. In doing so, we would have a mechanistic understanding of those machines. And the more of our behaviour the machine exhibits, the closer we might be to having a mechanistic explanation of our own minds.

This is what makes AI interesting from a philosophical point of view. Advanced models such as GPT4 and Midjourney can now mimic human conversation, pass professional exams and generate beautiful pictures with only a few words.

Yet, for all the progress, questions remain unanswered. How can we make something self-aware, or aware that others are aware? What is identity? What is meaning?

Although there are many competing philosophical descriptions of these things, they have all resisted mechanistic explanation.

In a sequence of papers[2] accepted for the 16th Annual Conference in Artificial General Intelligence[3] in Stockholm, I pose a mechanistic explanation for these phenomena. They explain how we may build a machine that’s aware of itself, of others, of itself as perceived by others, and so on.

Read more: A Google software engineer believes an AI has become sentient. If he’s right, how would we know?[4]

Intelligence and intent

A lot of what we call intelligence boils down to making predictions about the world with incomplete information. The less information a machine needs to make accurate predictions, the more “intelligent” it is.

For any given task, there’s a limit to how much intelligence is actually useful. For example, most adults are smart enough to learn to drive a car, but more intelligence probably won’t make them a better driver.

My papers describe the upper limit of intelligence[5] for a given task, and what is required to build a machine that attains it.

I named the idea Bennett’s Razor, which in non-technical terms is that “explanations should be no more specific than necessary”. This is distinct from the popular interpretation of Ockham’s Razor (and mathematical descriptions thereof[6]), which is a preference for simpler explanations.

The difference is subtle, but significant. In an experiment[7] comparing how much data AI systems need to learn simple maths, the AI that preferred less specific explanations outperformed one preferring simpler explanations by as much as 500%.

Hypothetical patent filing for a self-aware machine, generated by an artificial intelligence from just a few words. Michael Timothy Bennett / Generated using MidJourney

Exploring the implications of this discovery led me to a mechanistic explanation of meaning – something called “Gricean pragmatics[8]”. This is a concept in philosophy of language that looks at how meaning is related to intent.

To survive, an animal needs to predict how its environment, including other animals, will act and react. You wouldn’t hesitate to leave a car unattended near a dog, but the same can’t be said of your rump steak lunch.

Being intelligent in a community means being able to infer the intent of others, which stems from their feelings and preferences. If a machine was to attain the upper limit of intelligence for a task that depends on interactions with a human, then it would also have to correctly infer intent.

And if a machine can ascribe intent to the events and experiences befalling it, this raises the question of identity and what it means to be aware of oneself and others.

Causality and identity

I see John wearing a raincoat when it rains. If I force John to wear a raincoat on a sunny day, will that bring rain?

Of course not! To a human, this is obvious. But the subtleties of cause and effect are more difficult to teach a machine (interested readers can check out The Book of Why[9] by Judea Pearl and Dana Mackenzie).

To reason about these things, a machine needs to learn that “I caused it to happen” is different from “I saw it happen”. Typically, we’d program[10] this understanding into it.

However, my work explains how we can build a machine that performs at the upper limit of intelligence for a task. Such a machine must, by definition, correctly identify cause and effect – and therefore also infer causal relations. My papers[11] explore exactly how.

The implications of this are profound. If a machine learns “I caused it to happen”, then it must construct concepts of “I” (an identity for itself) and “it”.

The abilities to infer intent, to learn cause and effect, and to construct abstract identities are all linked. A machine that attains the upper limit of intelligence for a task must exhibit all these abilities.

This machine does not just construct an identity for itself, but for every aspect of every object that helps or hinders its ability to complete the task. It can then use its own preferences[12] as a baseline to predict[13] what others may do. This is similar to how humans tend to ascribe[14] intent to non-human animals.

So what does it mean for AI?

Of course, the human mind is far more than the simple program used to conduct experiments in my research. My work provides a mathematical description of a possible causal pathway to creating a machine that is arguably self-aware. However, the specifics of engineering such a thing are far from solved.

For example, human-like intent would require human-like experiences and feelings, which is a difficult thing to engineer. Furthermore, we can’t easily test for the full richness of human consciousness. Consciousness is a broad and ambiguous concept that encompasses – but should be distinguished from – the more narrow claims above.

I have provided a mechanistic explanation of aspects of consciousness – but this alone does not capture the full richness of consciousness as humans experience it. This is only the beginning, and future research will need to expand on these arguments.

References

  1. ^ philosophical approach (en.wikipedia.org)
  2. ^ sequence of papers (michaeltimothybennett.com)
  3. ^ 16th Annual Conference in Artificial General Intelligence (agi-conf.org)
  4. ^ A Google software engineer believes an AI has become sentient. If he’s right, how would we know? (theconversation.com)
  5. ^ the upper limit of intelligence (www.techrxiv.org)
  6. ^ mathematical descriptions thereof (www.cambridge.org)
  7. ^ experiment (www.techrxiv.org)
  8. ^ Gricean pragmatics (plato.stanford.edu)
  9. ^ The Book of Why (www.amazon.com.au)
  10. ^ program (en.wikipedia.org)
  11. ^ My papers (www.techrxiv.org)
  12. ^ use its own preferences (www.techrxiv.org)
  13. ^ baseline to predict (ieeexplore.ieee.org)
  14. ^ humans tend to ascribe (www.sciencedirect.com)

Read more https://theconversation.com/can-machines-be-self-aware-new-research-explains-how-this-could-happen-204371

Times Magazine

Headless CMS in Digital Twins and 3D Product Experiences

Image by freepik As the metaverse becomes more advanced and accessible, it's clear that multiple sectors will use digital twins and 3D product experiences to visualize, connect, and streamline efforts better. A digital twin is a virtual replica of ...

The Decline of Hyper-Casual: How Mid-Core Mobile Games Took Over in 2025

In recent years, the mobile gaming landscape has undergone a significant transformation, with mid-core mobile games emerging as the dominant force in app stores by 2025. This shift is underpinned by changing user habits and evolving monetization tr...

Understanding ITIL 4 and PRINCE2 Project Management Synergy

Key Highlights ITIL 4 focuses on IT service management, emphasising continual improvement and value creation through modern digital transformation approaches. PRINCE2 project management supports systematic planning and execution of projects wit...

What AI Adoption Means for the Future of Workplace Risk Management

Image by freepik As industrial operations become more complex and fast-paced, the risks faced by workers and employers alike continue to grow. Traditional safety models—reliant on manual oversight, reactive investigations, and standardised checklist...

From Beach Bops to Alpine Anthems: Your Sonos Survival Guide for a Long Weekend Escape

Alright, fellow adventurers and relaxation enthusiasts! So, you've packed your bags, charged your devices, and mentally prepared for that glorious King's Birthday long weekend. But hold on, are you really ready? Because a true long weekend warrior kn...

Effective Commercial Pest Control Solutions for a Safer Workplace

Keeping a workplace clean, safe, and free from pests is essential for maintaining productivity, protecting employee health, and upholding a company's reputation. Pests pose health risks, can cause structural damage, and can lead to serious legal an...

The Times Features

Tricia Paoluccio designer to the stars

The Case for Nuturing Creativity in the Classroom, and in our Lives I am an actress and an artist who has had the privilege of sharing my work across many countries, touring my ...

Duke of Dural to Get Rooftop Bar as New Owners Invest in Venue Upgrade

The Duke of Dural, in Sydney’s north-west, is set for a major uplift under new ownership, following its acquisition by hospitality group Good Beer Company this week. Led by resp...

Prefab’s Second Life: Why Australia’s Backyard Boom Needs a Circular Makeover

The humble granny flat is being reimagined not just as a fix for housing shortages, but as a cornerstone of circular, factory-built architecture. But are our systems ready to s...

Melbourne’s Burglary Boom: Break-Ins Surge Nearly 25%

Victorian homeowners are being warned to act now, as rising break-ins and falling arrest rates paint a worrying picture for suburban safety. Melbourne residents are facing an ...

Exploring the Curriculum at a Modern Junior School in Melbourne

Key Highlights The curriculum at junior schools emphasises whole-person development, catering to children’s physical, emotional, and intellectual needs. It ensures early year...

Distressed by all the bad news? Here’s how to stay informed but still look after yourself

If you’re feeling like the news is particularly bad at the moment, you’re not alone. But many of us can’t look away – and don’t want to. Engaging with news can help us make ...