Natural language is an imprecise interface. It really ideally is the interface of last resort. If you have a straight line from problem to solution you do not need natural language. It’s only if there isn’t one that you do. And in that case the same sentence can mean different things to different people even those who are native speakers. The most obvious example to me is something like “next weekend” which is a term that can mean different things to different people at different times. But it’s a deeper problem than that.
The AI boom is happening because people what to believe that natural language is precise. Not because it’s actually an effective way to interface with everything.
Hey original author here.
Natural language is always easy and available as an interface, but it's extremely low fidelity. It's not easy to come up with better interfaces for tasks, but when we do they tend to be much better (as in more clear, faster, higher quality, etc).
I think it is true, but I think the author underestimates how difficult it is for us to reason in ways other than natural language. We have to be taught it and we have to practice it.
Original author here. Yes, if I had the capability of writing a computer program or a formal proof that could stand in for this essay full of opinions and metaphors and heuristics, I would have.
> It's fully general, but it's also furiously ambiguous. Humans fall back to natural language when no other more precise way to describe what we want is available to us, either because it doesn't exist or we don't know it comfortably. We draw diagrams and blueprints and write math equations for a reason!
Well, I disagree that humans "fall back to natural language"- this is plainly false as "natural" language is, of course, the natural way for humans to express themselves, their first choice, not the last. They do resort to formalised "languages" only in restricted domains, where the difficulty of such an un-natural choice is justified by a special need for precision or speed or visual clarity.
But I wouldn't say that metaphors, heuristics, slight ambiguities, subtexts, are unnecessary and undesirable elements of language; I think they are probably productive, ans that they reflect what intelligence is and how it works. If you read Terrence Tao's chat with ChatGPT to understand the counterexample to the Jacobian Conjecture, it's a lot of formal math interspersed with dubitative formulas, suggestions, vague intuitions, mental images, imprecise quantifiers, etc., from both sides. Natural language does real work, it's not just a fallback.
For example, the article says "Natural language is the interface of last resort."
But, is that actually true? Isn't the AI boom happening because N/L is truly available as an interface?
Anyway, please keep writing and asking tough questions.