It seems as if every other day there’s a new AI model on the net. They are all the rage these says. It’s hard to keep up. Just last week my friend AP told me about perplexity.ai. I think it’s pretty good. I like claude.ai too. Recently I’ve been trying out grok. I asked grok, “Why is grok called grok?” The reply:
The name “Grok” comes from Robert A. Heinlein’s science fiction novel Stranger in a Strange Land, published in 1961. In the book, “grok” is a Martian word that roughly translates to “to understand deeply” or “to empathize completely.” It’s about grasping something—or someone—on a profound, intuitive level, beyond just surface comprehension.
xAI chose this name because it aligns with their mission: to create an AI that doesn’t just process data but truly “gets” the universe and human experience, accelerating our collective understanding of reality. Plus, it’s a nod to sci-fi geekery, which fits the vibe of a company started by Elon Musk, a guy who’s clearly into big ideas and cosmic exploration. That’s the gist of it—pretty fitting for an AI designed to dig into the why and how of everything, right?
Pretty nicely done, wouldn’t you say? The image at the head of this post was also generated by grok with a simple text prompt.
How do the responses of various ai models differ? Here’s perplexity’s answer to the same question about the grok name:
grok.ai is called “Grok” because the term originates from Robert A. Heinlein’s 1961 science fiction novel “Stranger in a Strange Land”. In the novel, “grok” is a Martian word that means to deeply understand or empathize with something, essentially merging with it to gain a profound intuitive understanding.
Elon Musk, the founder of xAI, likely chose this name to reflect the AI’s goal of providing a deep and empathetic understanding of user queries, differentiating it from other AI chatbots by offering unorthodox and humorous responses. The name also aligns with Musk’s interest in science fiction and his vision for AI that can intuitively grasp complex concepts.
In this case it is hard to distinguish between the responses of perplexity and grok. A regular search engine like google would have revealed the same information but it would have taken me longer to put together that response. These AI models are like having a smart research assistant.
Just like reading and writing are (and have been for centuries) basic skills, the ability to use AI engines is becoming a basic skill too. Not knowing how to use them effectively would be a serious handicap. Like any cognition-enhancement tool, the more naturally intelligent one is, the more effectively can one use an “artificial intelligence” tool. That is, AI enters the “production function” multiplicatively, not additively.
Therefore, AI will make some people relatively more productive than others, thus increasing inequality in production. As some have remarked, AI will not steal your job but someone who knows how to use AI will steal your job.
Samuel Johnson famously said, “Knowledge is of two kinds. We know a subject ourselves, or we know where we can find information upon it.” This quote is from Boswell’s Life of Johnson (1775). The distinction between direct understanding and knowing how to access information to aid understanding is important.
I seek to understand ideas. To that end, I have to know relevant facts. The word “relevant” is doing a lot of work. One has to know quite a bit to figure out what is relevant. It’s a bit of a chicken-and-egg problem. Just knowing a whole heap of facts does not amount to understanding.
A house is made of bricks but a heap of bricks is not a house. Structure matters. How the facts (bricks) relate to other facts (bricks) forms an understanding (house) which is what we seek to build.
Theory is the equivalent of a house plan. Theory guides you to seek out facts just as a house plan guides your selection of bits to construct the house.
I believe AI is going to transform the world in ways comparable to the transformation brought about by the use of fire and the invention of the wheel. Science and technology will advance at unimaginable speeds. It is also very likely that advanced super intelligence (ASI) is just around the corner.
Heavy stuff. Let’s balance this out with a Abbott and Costello routine that I love. Who’s on first, what’s on second, and I don’t know on third.
I prompted an AI about the clip. Here’s an edited version of the reply it gave.
“Who’s on First?” is a comedy routine made famous by American comedy duo Abbott and Costello. The routine was first performed for a national radio audience on March 1938.
Abbott and Costello performed “Who’s on First?” hundreds of times throughout their careers, often with slight variations.
The premise of the sketch is that Abbott is identifying the players on a baseball team for Costello, leading to reciprocal misunderstanding and growing frustration between them due to the players’ names serving as both questions and responses.
The routine is known for its extensive wordplay based on fictional baseball players with “strange nicknames” that seemed to be questions, such as “Who,” “What,” “I Don’t Know,” and “Tomorrow”.
Abbott and Costello also performed the routine several times on radio and television, notably in The Abbott and Costello Show episode “The Actor’s Home”.
In 1956, a gold record of “Who’s on First?” was placed in the National Baseball Hall of Fame and Museum in Cooperstown, New York, and a video from The Naughty Nineties now plays continuously on screens at the Hall.
The routine has been translated into nearly thirty languages and has been performed live thousands of times on radio exactly as it appears.
That’s it for now. Be well, do good work and keep in touch.
Atanu Dey : Life is a Random Draw 