The Blind Men and the Blind Elephant

In the old story about the blind men and the elephant, each man stood near a different part of the elephant and described what they thought the elephant was. The one who stood near its tail pronounced the elephant to be a rope. The one near a leg was sure that it was a tree, etc. The various perspectives on artificial intelligence are often the same, with just as much under-informed confidence that the blind men had about the nature of the elephant.

Image from ChatGPT

There are people who use generative AIs to do calculations, something for which they were never intended, and they write the tools off as totally useless. Others use them as search engines, another function that they do poorly. To them, all AI tools are undependable. They ignore the fact that the AI "elephant" is also "blind" and is not able to differentiate between fact and fiction. Still others briefly try the tools without spending the necessary time to learn their weird ways and they walk away without gaining the skills needed to use the tools properly.

The breathless marketing of the various retail AI companies hasn't helped. They have positioned their products as magic solutions to everything from healthcare to halitosis. They also tacitly allow people to believe that AIs are general intelligence tools at the level of movie androids. No wonder new users are disappointed

But in many classrooms and offices, the adventurous are pushing past the popular misconceptions and creating new use cases that make their daily jobs easier. In many cases, these adventurers are working under cover in organizations that discourage or outright forbid the use of AI tools. They are the Secret Cyborgs from Ethan Mollick's book, Co-Intelligence. These are people who are inventing the age of AI under the radar of their managers and often without the knowledge of their co-workers. They have removed their blindfolds and adopted and adapted AI tools in ways that their inventors could not have imagined.

In huge companies like Amazon, (I just finished a summer fellowship there.) AI is being broadly encouraged through company-specific tools that are being customized for users through direct requests to the developers. Teams are reporting increases in productivity even very early in the tools' adoption.

That brings up another aspect of the elephant. As a productivity rocket, it is also a threat to employment. Productivity increases have been essentially the only reason for corporate AI adoption from the beginning. Nobody should be surprised at demanded higher workloads. How else do you expect your employer to lay off your colleagues if you don’t assume their responsibilities by using AI tools?

This is why the primary challenge facing us in the AI world is not hallucinations, energy consumption, or bias, it’s how to care for people who might never be employed during their lifetimes. It’s also the reason that the tech bros are so hot for Universal Basic Income.

This raises existential questions for education. If schools are no longer to be factories for churning out workers, what is their mission in an AI world? Policy makers such as state education departments and local school boards can't delay starting to wrestle with these challenges. The world will be very different in a very few years. Today's kindergarteners deserve to be prepared for it starting right now.

Be a "Whys" Guy

My presentations to K-12 educators have always been subtitled "Why and How (In that order.)" That's because the most important thing when building a school makerspace is your educational “why.” The second is staff and leadership buy-in. Without both, your makerspace will have no direction and it will morph into shop class or an arts and crafts room. Or it will fail entirely. The two things will differentiate a purposeful, integrated learning environment from a mere room filled with tools and materials. The enthusiastic support of staff will transform the space into a center for learning and creativity.

Image By ChatGPT

While both shop and arts and crafts both have value, they represent different pedagogical approaches. A school makerspace exists to support the broader school philosophy. In the case of my school, that’s STEAM and Project Based Learning. A STEAM-PBL makerspace, is designed to be interdisciplinary, encouraging students to connect across subjects, think critically, and engage in hands-on learning. It's about problem-solving, useful failure, and applying knowledge in dynamic ways – not just completing "recipe" projects or tasks.

Starting a makerspace without a clear understanding of your educational goals is courting failure. The makerspace must serve as a tool to advance the school's broader goals, not as an end in itself. So the most valuable thing that you can do when starting out is to do a lot of organizational self-examination. Know your purpose. Know your community. Only then can you determine if a makerspace is the appropriate tool to advance your school’s interests.

(Portions taken from my comment on a promotional Facebook post by 1st Maker Space for its four-day $1999 makerspace manager program.)

A Brief Window

I’ve written frequently about permanent job losses caused by artificial intelligence. Wharton professor Ethan Mollick still allows for hope in a recent post. “Misguided companies will see any increase in performance from AI as an excuse to lay off staff, keeping their output the same,” writes Mollick, “More forward-thinking firms will take advantage of these new capabilities to both improve the lives of their employees and expand their own capabilities.”

I have seen no indication of an Ebenezer Scrooge on Christmas morning epiphany by corporate managers. Companies such as Amazon, SpaceX, and Trader Joe’s continue to work actively against employee efforts to organize to improve their lot.

Workers who have balanced their work lives by working from home are increasingly being recalled to the office.

Image by ChatGPT

The reflexive return to maintaining working conditions and pay just slightly above the pain point of employee resignation continues to be the default for most corporate managers.

There is no reason to believe that companies will suddenly become enlightened and let employees improve their lives with the time given back to them by artificial intelligence. Rather, the employees most adept at using the new tools will see that time filled with new assignments transferred from their laid-off colleagues.

There is hope, but the window will close quickly. During the initial AI integration period, employees will gravitate to Mollick’s “forward-thinking firms.” The return of union power could give workers the power to bargain for keeping the reclaimed time for more balanced working conditions.

But if layoffs come rapidly, companies will be able to cherry pick from the unemployed. Unions will fade in the face of worker desperation to keep their jobs. It all depends on the next one to two years. It’s moving that fast.

Re-"Eschering"

Last January, I wrote about changes in this blog to encompass more about STEAM education and Project Based Learning (Ch-Ch-Ch-Ch-Changes! (Sort of).) Now I'm adding something that I've been involved with for more than four years – Artificial Intelligence. I'm a member of AI4CA, a group of California educators developing and promoting AI literacy professional development for K-16 educators.

In that previous post, I used the AI image generator, DALL-E to create images of a school makerspace in the style of artist M.C. Escher. The results were vaguely reminiscent of Escher's work, in a childish sort of way (see left.)

So I decided to give it another shot, with the paid version of ChatGPT. With the current concern about copyright infringement over the materials that companies use to train generative AIs, ChatGPT politely informed me that it could not create an image using the style of living artists. I guess that Escher hasn't been dead long enough. Google's Gemini simply lied to me and denied that it was capable of creating images (it is.)

So I resorted to subterfuge. Here's my dialogue and the resulting images:

Me: "I understand that you cannot create imagery in the style of certain artists. But what would be a good description of the artistic style of M.C. Escher?"

ChatGPT:"M.C. Escher's artistic style is renowned for its intricate detail, mathematical precision, and imaginative use of perspective. Escher's work often explores the concepts of infinity, symmetry, and tessellation, seamlessly blending art and mathematics. He is famous for his impossible constructions, which defy the laws of physical space, creating optical illusions that challenge viewers' perceptions. Escher's art frequently features interlocking geometric patterns that transform into impossible objects or detailed scenes that merge into each other in surprising ways. His use of black and white to create stark contrasts enhances the visual impact of his work, making the impossible seem plausible within the confines of his artistic universe. Escher's unique ability to meld the disciplines of art and science has made his style distinctive and instantly recognizable, appealing to both art aficionados and mathematical enthusiasts alike."

So I reworked the prompt, using ChatGPT's own words against it:

Me: "Please create an image of a school makerspace. The image should feature intricate detail, mathematical precision, and imaginative use of perspective and explore the concepts of infinity, symmetry, and tessellation, seamlessly blending art and mathematics. The image should contain impossible constructions, which defy the laws of physical space, creating optical illusions that challenge viewers' perceptions. Use pen and ink style. Use a cutaway view of the room, showing multiple floors, connected in a way that defies physics."

The result was jaw-dropping.

Image by ChatGPT

This interaction with an AI entity is an example of the sorts of skills that our students will need in the coming AI-infused world. They will need a clear grasp of the problem, sufficient insight into how the tools they will be using work, and the ability to express themselves effectively. The same sorts of skills fostered by Project Based Learning.