Generative AI Is Better At Form Than Content

Prudens Futuri prominently displayed in
the US Army War College's new academic building

All communications have at least two aspects, form and content.  Content is what we want to say.  It could be about politics, or philosophy, or here at the War College, rather predictably, about war.

Form is different.  The medium through which we express ideas impacts how we communicate those ideas. For instance, the same core concepts about politics, philosophy, or war can be conveyed very differently depending on whether they are presented through a 20 minute PowerPoint presentation or a 2,000 word paper. The form we choose defines how we communicate the message.

Let me give you an example.  My current favorite generative AI is Anthropic's Claude.  I asked it to explain the meaning of the US Army War College's motto, "Prudens Futuri," to the incoming class of students.  Here is what it came back with:

"The Latin phrase "prudens futuri" translates to "foreseeing the future" or "provident of the future." It refers to the wisdom and foresight required of effective leaders. Prudent leaders do not simply react to current circumstances - they have a vision for the future and proactively position their forces to capitalize on anticipated events. As Sun Tzu advised, foreknowledge enables leaders to seize opportunities and gain advantage. Prudens futuri requires gathering intelligence, conducting analysis, forecasting threats, and planning for contingencies. Leaders who excel at prudens futuri can execute bold, unconventional strategies to defeat enemies who rely on reactionary thinking. Prudens futuri epitomizes the innovative, forward-looking mindset the Army must adopt to maintain strategic dominance."

Not bad.  I also asked it to explain the same thing to a 13 year old:

"'Prudens futuri' is a Latin phrase that means "foreseeing the future." It's about being wise enough to predict what might happen next. Great leaders don't just respond to what's in front of them - they think ahead. Imagine you're a general planning to attack an enemy. A wise general would send scouts to spy first and learn the enemy's weaknesses. Then the general can make a smart battle plan to sneak around and surprise them from behind. The Latin phrase teaches that real leaders don't just react - they use their brains to see the future and stay one step ahead. That's what "prudens futuri," or "foreseeing the future," is all about!"

Also not bad--particularly given the change in audience.  

It is even possible to ask the same of a text-to-image AI like Midjourney, used to create the image below from the same prompt:

In this image, I am particularly taken with the way the AI combined historical references to foresight, such as the Oracle of Delphi, with more futuristic concepts like the (apparent) space elevator in the background.  In fact, I find asking text-to-image generators to imagine some futuristic scene to be a very practical way to fill in gaps in futures thinking.  I inevitably see something that makes sense in the image that was not accounted for in the text (kind of like The Spandrels of San Marco and the Panglossian Paradigm).

My point?  I have yet to have a generative AI create something that did not need tweaking, at the least, on the content side.  I have been really happy, however, with generative AI's ability to master particular forms.  

This is one of the reasons, I think, I have quite recently become a bit uncomfortable with policies that talk about citing a generative AI as if it were a source.  It is, I suppose...but it seems less of a source than Wikipedia, and, while I love Wikipedia and believe it is one of the great wonders of the modern world, I would not cite Wikipedia for anything other than background.  I require my students, for example, to find a reputable source to validate anything that a generative AI might come up with when making an estimate.  And, if you are going to make a student find a reputable source anyway, why would they need the generative AI at all?  The answer, of course, is for the form.  

This may not be true forever.  Generative AI is getting better at a brisk pace.  There may come a day when generative AI is looked upon as an authority, equal to peer-reviewed papers.  Until that time, we should still appreciate its talents for helping to craft the message. For now, generative AI is an unparalleled writing partner, not an independent thinker. By acknowledging its current limits alongside its awesome potential, we grant generative AI its proper place: revolutionizing how we communicate knowledge, while established methods still reign over what we know.