Scrolling through these images, you might begin to ask yourself, if generative AI has reached such unprecedented heights in creative expression, why does it struggle with tasks even a primary school student could complete?

Well, according to Professor Seyedali Mirjalili, who is the Director of the Centre for Artificial Intelligence Research and Optimisation at Torrens University Australia, a big factor is AI's limitations with writing.

"Humans can easily recognize text symbols (such as letters, numbers and characters) written in various different fonts and handwriting. We can also produce text in different contexts, and understand how context can change meaning," Mirjalili explained.

"Current AI image generators lack this inherent understanding. They have no true comprehension of what any text symbols mean. These generators are built on artificial neural networks trained on massive amounts of image data, from which they 'learn' associations and make predictions."

Combinations of shapes in the training images are associated with various entities, for example, two inward-facing lines that meet might represent the tip of a pencil, or the roof of a house.

However, when it comes to text and quantities, the associations for AI must be incredibly accurate, since even minor imperfections are noticeable.

Our brains, on the other hand, can overlook slight deviations in a pencil’s tip, or a roof – but not as much when it comes to how a word is written, or the number of fingers on a hand.

"In training images, hands are often small, holding objects, or partially obscured by other elements. It becomes challenging for AI to associate the term 'hand' with the exact representation of a human hand with five fingers," Mirjalili said about this common error.

"Consequently, AI-generated hands often look misshapen, have additional or fewer fingers, or have hands partially covered by objects such as sleeves or purses."

A similar issue arises when it comes to quantities. "AI models lack a clear understanding of quantities, such as the abstract concept of 'four,'" Mirjalili highlighted.

"As such, an image generator may respond to a prompt for 'four apples' by drawing on learning from myriad images featuring many quantities of apples – and return an output with the incorrect amount."

But before we label AI image generators as incompetent fools, it's important to remember that text-to-image and text-to-video conversion is a relatively new concept in artificial intelligence. Current generative platforms are "low-resolution" versions of what we can expect in the future.

"With advancements being made in training processes and AI technology, future AI image generators will likely be much more capable of producing accurate visualisations," Mirjalili predicted.

"It's also worth noting most publicly accessible AI platforms don't offer the highest level of capability. Generating accurate text and quantities demands highly optimised and tailored networks, so paid subscriptions to more advanced platforms will likely deliver better results," he added.

So we should enjoy 'Cursed AI' while we can. Content like this might be getting rarer and rarer in the future!