By “AI” I mean the amazing chatbots that emulate reading and reasoning. There is a lot more to AI but that is how the term is being used these days.
There are a couple of reasons why these powerful AI tools may greatly improve human thinking. Simply put they can save a lot of search time and they find better stuff. This gives people more time to think and better information to think with.
Most jobs involve looking stuff up and many require a lot of this search work. Sometimes it is interesting but often searching is tedious, laborious or even frustrating. This is especially true when the stuff sought is hard to find.
AI often produces answers in seconds that would take humans many minutes or even hours to find. This frees up a lot of human time for doing what often comes after searching, which is thinking about what one has found. Searching is often just part of a cognitive production process.
Moreover one often has limited time for searching so makes do with what they find in that time. Only a small number of documents are looked at. AI looks at thousands of relevant documents so can often find much better answers in no time at all.
Today’s world is a world of thinking so spending a lot less time searching while also getting better information should make a huge difference. A city full of office buildings mostly produces thinking. Many people, perhaps most, think for a living.
I call it cognitive production. America is a huge cognitive production system. Calling it paperwork masks this fundamental fact.
That we do a lot of thinking and a good bit of searching online is also true of our personal lives. Spending less time searching while also getting better information could make a big difference outside of work.
By way of scale consider that if a hundred million Americans save an average of just one hour a week thanks to AI searching that is around five billion hours saved a year. These huge time savings could generate a lot of additional thinking.
Moreover the time savings could be a lot bigger than this, which is an interesting research question. How much time do people now spend searching online?
When you add in getting better information the potential benefits of AI get even bigger. Imagine being able to read thousands of relevant documents when you do a search instead of the few you can now read. This is just what the reading and reasoning chatbots do.
Estimating the benefits of all this better information is likely impossible. What is called the diffusion of knowledge is in fact a diffusion process so it is impossible to track where knowledge goes and what it does when it gets there. But there might be indicators which makes this a grand research challenge.
For example there is something called the “crocodile effect” in scholarly publishing. Journal articles are rapidly increasingly appearing in search results but click throughs to them are rapidly decreasing, which worries publishers. These two diverging trends are likened to a croc’s open mouth.
There is a good article “Responding to the Threat of Zero-Click Search and AI Summaries: How Do We Tame The Crocodile?” with a great graphic here. The term for using the AI summary is “zero-click search.”
The rapid divergence is attributed to AI search. The reading bot finds the relevant journal articles that conventional search would not find. But then the AI summaries make reading these time consuming articles unnecessary. So people are getting better information with far less effort. This is happening everywhere not just in scholarly publishing.
It is conceivable that the growing revolutionary combination of Americans getting better information with more time to think will lead to a cognitive renaissance. It is certainly worth watching for.
