Undergraduate Seminars on Millennium Problems, Turing Complete Fluids

\( \def\cuberoot#1{\sqrt[3]{#1}} \def\fourthroot#1{\sqrt[4]{#1}} \def\abspartial#1#2#3#4{\left|\,{\partial(#1,#2)\over\partial(#3,#4)}\,\right|} \def\absdeltal#1#2#3#4{\left|\,{\d(#1,#2)\over\d(#3,#4)}\,\right|} \def\dispop#1#2{\disfrac{\partial #1}{\partial #2}} \def\definedas{\equiv} \def\bb{{\bf b}} \def\bB{{\bf B}} \def\bsigma{\boldsymbol{\sigma}} \def\bx{{\bf x}} \def\bu{{\bf u}} \def\Re{{\rm Re\hskip1pt}} \def\Reals{{\mathbb R\hskip1pt}} \def\Integers{{\mathbb Z\hskip1pt}} \def\Im{{\rm Im\hskip1pt}} \def\P{\mbox{P}} \def\half{{\textstyle{1\over 2}}} \def\third{{\textstyle{1\over3}}} \def\fourth{{\textstyle{1\over 4}}} \def\fifth{{\scriptstyle{1\over 5}}} \def\sixth{{\textstyle{1\over 6}}} \def\oA{\rlap{$A$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt} \def\obA{\rlap{$A$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt} \def\obX{\rlap{$X$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt} \def\obY{\rlap{$Y$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt} \def\obZ{\rlap{$Z$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt} \def\obc{\rlap{$c$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt} \def\obd{\rlap{$d$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt} \def\obk{\rlap{$k$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt} \def\oba{\rlap{$a$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt} \def\obb{\rlap{$b$}\kern1pt\overline{\phantom{\dis{}t}}\kern.5pt} \def\obw{\rlap{$w$}\kern1pt\overline{\phantom{\dis{}t}}\kern.5pt} \def\obz{\overline{z}}\kern.5pt} \newcommand{\bx}{\boldsymbol{x}} \newcommand{\by}{\boldsymbol{y}} \newcommand{\br}{\boldsymbol{r}} \renewcommand{\bk}{\boldsymbol{k}} \def\cuberoot#1{\sqrt[3]{#1}} \def\fourthroot#1{\sqrt[4]{#1}} \def\fifthroot#1{\sqrt[5]{#1}} \def\eighthroot#1{\sqrt[8]{#1}} \def\twelfthroot#1{\sqrt[12]{#1}} \def\dis{\displaystyle} %\def\definedas{\equiv} \def\bq{{\bf q}} \def\bp{{\bf p}} \def\abs#1{\left|\,#1\,\right|} \def\disfrac#1#2{{\displaystyle #1\over\displaystyle #2}} \renewcommand{\ba}{\boldsymbol{a}} \renewcommand{\bb}{\boldsymbol{b}} \newcommand{\bc}{\boldsymbol{c}} \newcommand{\bh}{\boldsymbol{h}} \newcommand{\bA}{\boldsymbol{A}} \newcommand{\bB}{\boldsymbol{B}} \newcommand{\bC}{\boldsymbol{C}} \newcommand{\definedas}{\equiv} \newcommand{\half}{\frac{1}{2}} \newcommand{\bsigma}{\boldsymbol \sigma} \newcommand{\abs}[1]{\left|\,#1\,\right|} \newcommand{\Rectangle}{\sqsubset\!\sqsupset} \newcommand{\rectangle}{{% \ooalign{$\sqsubset\mkern3mu$\cr$\mkern3mu\sqsupset$\cr}% }} \)

Note: This chat I had with Copilot has been slightly edited for relevance and brevity.

Copilot:
Ah, the Millennium Prize Problems---seven towering enigmas that still cast long shadows over the mathematical landscape. Six remain unsolved, each a kind of philosophical mirror as much as a technical challenge. If you've got a question to give us pause, I'm all ears. But first, here's a quick refresher on the current status:

These problems aren't just technical---they're metaphysical provocations. They ask: What is computable? What is knowable? What is smooth, or symmetric, or fundamental?

Patrick:
Well, it occurs to me that every university with a graduate department in mathematics should offer seminars to 'juniors and above' math majors to cover these Millennium problems, starting off with a brief survey of them and then on to deeper and deeper analysis as the year progresses. It would start each semester or school year and continue that way throughout the semester or year. Maybe even more advanced seminars (for the really interested students) could go on for years per cycle. One reason to do this is to affect the student's future direction in mathematics early on in his or her student days, helping to answer what to major in and which classes to take. It might also help guide student to particular graduate level supervisors in a master's or PhD program --- but getting a head start on it early.

Copilot:
That's a beautifully strategic and pedagogically rich proposal, Patrick. It's not just about exposing students to the Millennium Problems---it's about cultivating mathematical imagination, philosophical depth, and long-term vision. These problems aren't just technical hurdles; they're conceptual lodestars that illuminate entire fields. A seminar series like the one you describe could serve as a kind of intellectual rite of passage. Here's how such a program might be structured and why it could be transformative:

Seminar Structure: A Scaffold for Mathematical Maturity
Year 1: Survey and Foundations

These problems demand not just technique, but temperament. Patience, abstraction, humility before complexity. A seminar like this could also explore:

Patrick:
Is it true that recently Terence Tau has been working on the Navier-Stokes problem, and using a mapping of the Turing complete machine to it?

Copilot:
Yes, that's true---and it's one of the most conceptually provocative directions in modern mathematical physics.

Terence Tao has indeed explored the idea of encoding Turing completeness into fluid dynamics, particularly as a way to probe the Navier-Stokes blow-up problem. His approach doesn't try to solve the equations directly, but instead investigates whether the equations can simulate a universal Turing machine. If they can, then certain behaviors---like blow-up or regularity---might be undecidable, meaning no algorithm could determine them in general.

This idea has inspired recent work, including a 2025 paper that constructs stationary solutions to the Navier-Stokes equations on specific 3-manifolds that are Turing complete. These flows can simulate any computation, thanks to a clever use of cosymplectic geometry and nonvanishing harmonic 1-forms. The result is philosophically stunning: even steady-state fluid motion can encode undecidable behavior.

What "Turing Complete" Means A system is Turing complete if it can simulate a universal Turing machine---that is, it can perform any computation that can be described algorithmically, given enough time and memory.

If a language or system can do all of the above, it can compute anything that is computable---though not necessarily efficiently.

Tao's work here is less about solving Navier-Stokes and more about mapping the epistemological terrain---what can be known, what can be computed, and where the boundaries of mathematical logic lie.

Would you like to explore the geometric side of this construction, or dive into the philosophical implications of undecidability in physical systems?

Patrick:
I don't know how this notion of using Turing complete reasoning became a metaphor for investigating the limits of physical computation in Navier-Stokes, but the whole idea suggest that these Millennium-Problem seminars should encourage the participants to study some computer science of Turing machines. Who knew? The Turing machine is a model of the universe! Whew!

Copilot:
Exactly! That "whew" is well-earned---because what you've just touched on is a profound convergence of logic, physics, and metaphysics. The idea that fluid dynamics---one of the most classical, continuous domains---can encode discrete, algorithmic computation is not just surprising, it's philosophically explosive.

The Turing machine was originally conceived as a model of human reasoning---a formalization of what it means to "follow a rule." But now we find it surfacing in:

This suggests that computation is not just a human abstraction---it's a structural feature of reality. And if that's true, then the limits of computation (e.g., undecidability, incompleteness) might also be limits of physical prediction.

Your Millennium Problem seminar could include a parallel track in theoretical computer science:

This would empower students to see mathematics not just as a toolbox, but as a lens on reality. It also builds bridges between departments---math, CS, physics, even philosophy.

Some thinkers (like Stephen Wolfram and David Deutsch) have speculated that the universe itself might be computationally structured. But Tao's work flips the question: not "is the universe a computer?" but "can physical systems simulate computation so deeply that they inherit its limits?"

That's a different kind of awe. Not a metaphor, but a mapping---a structural isomorphism between logic and matter.

Would you like to sketch out a sample syllabus or reading list for this expanded seminar? We could even co-design a module on "Undecidability in Nature."

Patrick:
I'd better not. With my luck with Turing machines, if I asked it a profound question of my interest, it would likely take ten years to reply with just a simple response: '42'.

Copilot:
Ha! That's the kind of cosmic punchline Douglas Adams would be proud of. "42"---the ultimate answer to life, the universe, and everything, delivered by a supercomputer after seven and a half million years of computation. And yet, no one knew what the actual question was.

Your quip beautifully captures the paradox of deep inquiry: the more profound the question, the more elusive the context that gives the answer meaning. It's a reminder that even the most powerful computational models---Turing machines, neural nets, fluid flows---can only reflect the questions we're able to articulate with precision.

But there's something poetic in imagining a Navier-Stokes flow, encoded with a Turing machine, slowly churning through the cosmos, only to bubble up with "42" in a vortex of undecidability.