What is AI (Artificial Intelligence), how will it affect me? (simple guide)

AI (Artificial Intelligence) today is simply a computer that can do things a hell of a lot faster than a human can. AI in the future is a different can of worms. And for fun we asked ChatGPT to write its take on AI – that follows.

Fact: AI computers today cannot think like humans can. They are trained via machine learning to recognise patterns and execute human-programmed responses.

Fact: 2024 is the year of ‘AI-washing’ where every major piece of tech will claim all sorts of AI abilities – it is largely rubbish, just as they claimed ‘Green-wash eco-friendly’ last year. Our advice – take AI claims with a grain of salt and perhaps a good Shiraz. It is largely low-level machine learning, and we will try to identify outlandish AI claims in reviews this year.

Stage 1: Let’s look at a simple AI – IF THIS THEN DO THAT task

Identify a cat and make a noise to shoo it away.

A computer is trained to recognise a cat (or any other object) by showing it millions of cat pictures until it can recognise the creature. Those pictures may have metadata showing the cat’s breed, age, and condition.

It gets a reward (good computer) every time it identifies a cat and a punishment (bad computer) every time it gets it wrong. Computers innately want to get it right (reduce standard deviation error). Hence, the computer may be able to record that the animal is a 10-15-year-old orange American Shorthair Cat (IF Cat THEN set off an alarm). Humans would know it was an older, harmless Ginger Tom that belongs to Mrs Smith down the road – no alarm needed.

What if it is a cat-like creature – say a possum? The computer can’t identify it, and nothing happens. Or it may call up the ‘unknown’ sub-routine to send a picture to the programmer to help reduce unknown animals and increase the range of responses. IF Possum, THEN notify a licensed possum catcher.

Stage One of AI is to train it to recognise and implement appropriate human-programmed responses. The problem is that A) source training data may be incomplete or skewed, and B) the range of pre-programmed responses may not be adequate.

continued

AI companies are scanning global libraries of written words and images to give computers access to the same information that humans have learned from.

I will leave you to extrapolate, but AI facial recognition, race, gender, and sentiment assessment are simple tasks. Voice Assistants like Google, Alex and Siri are also simple. Via Machine Learning computers have learned the language, its various constructs, accents, and idioms (called Natural Language Processing). When US Southerners ask, ‘Google what is the Toad Strangler today?  It can respond with the weather.

Stage 2: Nested IF THIS THEN DO THAT COMMANDS

If it is not a cat, then what does the computer do?

Nested commands mean the computer decides it is not a cat and then calls on the next most likely database of small furry animals. It may decide it is not a possum and call on the next most likely database of domesticated animals, ad infinitum. This is like Matthew Broderick in the War Games movie, where the only way to win is not to win by tying the computer up in logic loops – it is not a cat, possum, gerbil… ad infinitum so that it cannot do anything (like start the countdown to WW3).

This verges on Deep learning, allowing data to be cross-referenced against other databases and for basic conclusions to be reached. For example, if the cat computer had a micro-chip reader and access to an owner’s register database, it could have identified the owner and, based on a clear police record database, know that their intentions were honourable, thus not setting off the alarm – if it were programmed to.

Basic AI or machine learning cannot record the gamut of human experiences, emotions or common sense. However, deep learning may have what appears to be rudimentary skills in assessing these.

Still, it is reassuring that most AI computers cannot act without accurate data and millions of human-generated routines to cover almost all contingencies.

Stage 3: Machine Consciousness IF this, THEN do whatever a human would.

Until recently, we lacked the computing power to do more than machine learning and deep learning. Enter Quantum Computing (and it is early days, too).

Human-level AI is already here, but its cost is so exorbitant, and its use so narrow that we probably won’t see much broader use in our lifetimes.

For example, in Medicine, AI can analyse X-rays, ultra-sounds, other scans, medical records and biodata to produce fast and highly accurate prognoses and reports. Humans now only assist when the computer recognises an element of doubt.

That AI can assist in scheduling, programming the operating robot and more, all focusing on successful outcomes for the patient. But the total system is so breathtakingly expensive that only parts have been implemented. It can do this as medical records are so detailed and well-kept that they now reflect the sum of every doctor and surgeon’s knowledge in the field in the world.

Stage 4: Do you mean judge, jury and executioner?

Yes, removing human foibles, weaknesses, and biases allows a logical decision. Is that decision right or wrong? They are human terms.

Machine consciousness will eventually be able to make decisions. In other words, perceiving, reasoning, learning, interacting with an environment, problem-solving, and creativity.

The next stage of AI is the Theory of Mind, where AI can understand human motives, intent, and responses. For example, AI cannot yet understand the paradox that to save Person ‘A’, you must kill Person ‘B’ or vice versa. It gets locked in loops about whether person A is more important than person B instead of analysing relationships with you, how you feel, and potential benefits to the planet.

The final stage of AI is self–awareness – I think, therefore I am. When you add I to the mix, it becomes scary, not to be encouraged, and definitely Terminator Skynet stuff. In Terminator, humans were considered the weak link, a threat to the existence of AI and must be exterminated.

We are definitely not there yet (I hope).

Now, for a bit of tedium fun

We asked Chat GPT to write a 1000-word consumer-focused explanation of AI. You tell me which 1000 words – mine or its – you would rather read. As a writer, it sucks, but the facts are not bad, as they have come from everything else written about AI.

ChatGPT Title: Unveiling the Wonders of AI (Artificial Intelligence): A Consumer-Focused Exploration

Introduction

In the rapidly evolving landscape of technology, one term that has become increasingly prevalent is Artificial Intelligence (AI). Although once confined to the realms of science fiction, AI is now a tangible and pervasive force that influences various aspects of our daily lives. This consumer-focused exploration aims to demystify AI, shedding light on its applications, benefits, potential pitfalls, and its impact on our interconnected world.

Understanding AI (Artificial Intelligence)

At its core, Artificial Intelligence refers to the development of computer systems capable of performing tasks that typically require human intelligence. This includes tasks such as learning, reasoning, problem-solving, understanding natural language, and even perceiving the environment. AI systems are designed to analyse vast amounts of data, recognise patterns, and make decisions with minimal human intervention.

Applications in Everyday Life

AI has seamlessly integrated into our daily lives, enhancing convenience, efficiency, and personalisation across various domains. One of the most common applications is in virtual assistants like Siri, Alexa, and Google Assistant. These intelligent systems respond to voice commands, provide information, set reminders, and control smart home devices, making our lives more interconnected and streamlined.

Another prominent application of AI is in recommendation systems, such as those employed by streaming services like Netflix and music platforms like Spotify. These systems analyse user preferences and behaviour to suggest personalised content, creating a tailored and enjoyable user experience.

In healthcare, AI is revolutionising diagnostics and treatment planning. Machine learning algorithms can analyse medical images, detect anomalies, and assist healthcare professionals in making more accurate diagnoses. This not only expedites the diagnostic process but also contributes to better patient outcomes.

AI-powered chatbots have become ubiquitous in customer service, offering instant support and resolving queries efficiently. These virtual agents can understand natural language, learn from interactions, and provide a more human-like conversational experience.

In the automotive industry, AI plays a crucial role in the development of autonomous vehicles. Advanced driver-assistance systems (ADAS) utilise AI to interpret sensor data, make split-second decisions, and enhance overall safety on the road.

The Benefits of AI (Artificial Intelligence) for Consumers

1. Increased Efficiency: AI automates repetitive and time-consuming tasks, allowing consumers to focus on more meaningful activities. This efficiency is evident in various sectors, from business processes to personal productivity.
2. Personalisation: AI-driven recommendation systems analyse user behaviour to offer personalised content, product recommendations, and services. This not only enhances the user experience but also helps consumers discover new and relevant items.
3. Improved Healthcare: AI contributes to faster and more accurate medical diagnoses, enabling timely interventions and personalised treatment plans. This advancement in healthcare can lead to better patient outcomes and an overall improvement in the quality of healthcare services.
4. Enhanced User Interfaces: Natural language processing (NLP) and computer vision technologies have improved user interfaces, making interactions with devices more intuitive. Voice commands, gesture recognition, and facial recognition contribute to a seamless and user-friendly experience.
5. Advanced Security: AI is employed in cybersecurity to detect and prevent cyber threats in real-time. This enhances the security of online transactions, protects sensitive data, and safeguards consumers from various cyber risks.

Potential Pitfalls and Ethical Considerations

While the benefits of AI are substantial, it is essential to acknowledge and address potential pitfalls and ethical concerns associated with its widespread adoption.

1. Job Displacement: The automation of certain tasks may lead to job displacement in certain industries. It is crucial to consider strategies for retraining and upskilling the workforce to adapt to the changing job landscape.
2. Bias in Algorithms: AI algorithms can inherit biases present in training data, leading to unfair and discriminatory outcomes. Ensuring fairness and mitigating bias in AI systems is a critical ethical consideration.
3. Privacy Concerns: The extensive collection and analysis of personal data for AI applications raise privacy concerns. Striking a balance between innovation and safeguarding individual privacy is essential for responsible AI development.
4. Lack of Transparency: Many AI algorithms operate as “black boxes,” making it challenging to understand their decision-making processes. Ensuring transparency in AI systems is vital for building trust among consumers.
5. Security Risks: As AI becomes more integrated into critical systems, there is an increased risk of cybersecurity threats. Safeguarding AI systems from malicious attacks and ensuring their resilience is a paramount concern.

The Future of AI and Consumer Empowerment

As AI continues to advance, consumers can expect further integration of intelligent technologies into various aspects of their lives. The ongoing development of AI-driven innovations promises a future where consumer experiences are more personalised, efficient, and secure.

1. AI in Education: Personalised learning experiences, intelligent tutoring systems, and adaptive educational platforms are poised to transform the field of education. AI can cater to individual learning styles, providing tailored content and feedback to students.
2. Smart Cities: The concept of smart cities, powered by AI, envisions urban environments that optimise resources, enhance public services, and improve overall quality of life. Intelligent transportation systems, energy management, and public safety initiatives are key components of this vision.
3. AI and Augmented Reality (AR): The combination of AI and AR holds immense potential for enhancing consumer experiences. From personalised shopping experiences to interactive educational content, this fusion of technologies is set to redefine the way we interact with the world around us.
4. Ethical AI Practices: As awareness of AI-related ethical considerations grows, there will be an increased emphasis on responsible AI development. Consumers can expect organisations to prioritise transparency, fairness, and accountability in their AI initiatives.

AI (Artificial Intelligence) Conclusion

In conclusion, Artificial Intelligence is not just a buzzword but a transformative force shaping the present and future of technology. As consumers, understanding the applications, benefits, and potential challenges of AI empowers us to make informed decisions and actively participate in the ongoing dialogue surrounding its ethical implications. While AI has the potential to revolutionise our lives, it is essential to approach its development and deployment with a mindful and ethical perspective, ensuring that the benefits are maximised while minimising any negative impacts. The journey into the age of Artificial Intelligence is both exciting and challenging, and as informed consumers, we play a pivotal role in shaping its evolution.

CyberShack AI news and reviews, AI (Artificial Intelligence)