The Story of My Intellectual Life
In the early 1970s I discovered that “Kubla Khan” had a rich, marvelous, and fantastically symmetrical structure. I’d found myself intellectually. I knew what I was doing. I had a specific intellectual mission: to find the mechanisms behind “Kubla Khan.” As defined, that mission failed, and still has not been achieved some 40 odd years later.
It’s like this: If you set out to hitch rides from New York City to, say, Los Angeles, and don’t make it, well then your hitch-hike adventure is a failure. But if you end up on Mars instead, just what kind of failure is that? Yeah, you’re lost. Really really lost. But you’re lost on Mars! How cool is that!
Of course, it might not actually be Mars. It might just be an abandoned set on a studio back lot.
That’s a bit metaphorical. Let’s just say I’ve read and thought about a lot of things having to do with the brain, mind, and culture, and published about them as well. I’ve written a bunch of academic articles and two general trade books, Visualization: The Second Computer Revolution (Harry Abrams1989), co-authored with Richard Friedhoff, and Beethoven’s Anvil: Music in Mind and Culture (Basic Books 2001). Here’s what I say about myself at my blog, New Savanna. I’ve got a conventional CV at Academia.edu. I’ve also written a lot of stuff that I’ve not published in a conventional venue. I think of them as working papers. I’ve got them all at Academia.edu. Some of my best – certainly my most recent – stuff is there.
YES.
At the moment the A.I. world is dominated by an almost magical believe in large language models. Yes, they are marvelous, a very powerful technology. By all means, let’s understand and develop them. But they aren’t the way, the truth and the light. They’re just a very powerful and important technology. Heavy investment in them has an opportunity cost, less money to invest in other architectures and ideas.
And I’m not just talking about software, chips, and infrastructure. I’m talking about education and training. It’s not good to have a whole cohort of researchers and practitioners who know little or nothing beyond the current orthodoxy about machine learning and LLMs. That kind of mistake is very difficult to correct in the future. Why? Because correcting it means education and training. Who’s going to do it if no one knows anything else?
Moreover, in order to exploit LLMs effectively we need to understand how they work. Mechanistic interpretability is one approach. But: We’re not doing enough of it. And by itself it won’t do the job. People need to know more about language, linguistics, and cognition in order to understand what those models are doing.