AI finds optical illusions just as mind-boggling as we do

Coca-Cola optical illusion that appears to show a red Coca-Cola can on a striped background
(Image credit: Akiyoshi Kitaoka via X)

We've already established that AI is capable of generating impressive optical illusions, but how effectively can large language models identify those that manage to trick the human eye? About as effectively as we can, suggest recent studies.

Tools including GPT-4V and Google Gemini have been tasked with examining various types of visual illusions, with the results proving that AI "seems to fall for many the same visual deceptions that fool people". For more AI content, take a look at our recent AI Week coverage.

We've seen plenty of examples of illusions in which, at first glance objects or photographs appear to be a different colour to what they actually are (or, in some cases, appear to be in colour when they're actually black-and-white). And as reported by Scientific American, when asked to describe such images, AI will often give "surprisingly humanlike responses". 

Computer engineering professor Dimitris Papailiopoulos ran a series of casual experiments, feeding optical illusions including some he had created himself (such as the example in the above tweet) into the AI. This meant the tool was seeing them for the first time, and they weren't part of any of its training. Instead of identifying the colour of the pixels, the AI interpreted them as a human would.

Optical illusions

The five types of illusion used in a recent study of AI's ability to interpret visual phenomena (Image credit: Yichi Zhang, Jiayi Pan, Yuchen Zhou, Rui Pan, Joyce Chai)

Similarly, a recent study revealed that large AI models in particular offer interpretations closely aligned with those of humans. Curiously, of the five types of visual illusion tested (above), geometrical perspective illusions (above) were the most likely to trick the tools, which presented "up to 75 percent humanlike" interpretations. 

As Scientific American suggests, perhaps the most interesting aspect of all of this is that it could "offer a glimpse of what’s inside" the inner machinations of AI tools. Indeed, as AI grows in ubiquity, so do concerns around transparency – just ask Adobe.  

Thank you for reading 5 articles this month* Join now for unlimited access

Enjoy your first month for just £1 / $1 / €1

*Read 5 free articles per month without a subscription

Join now for unlimited access

Try first month for just £1 / $1 / €1

TOPICS
Daniel John
Design Editor

Daniel John is Design Editor at Creative Bloq. He reports on the worlds of design, branding and lifestyle tech, and has covered several industry events including Milan Design Week, OFFF Barcelona and Adobe Max in Los Angeles. He has interviewed leaders and designers at brands including Apple, Microsoft and Adobe. Daniel's debut book of short stories and poems was published in 2018, and his comedy newsletter is a Substack Bestseller.