\( \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}} \def\select#1{ \langle\, #1 \,\rangle } \def\autoselect#1{ \left\langle\, #1 \,\right\rangle } \def\bigselect#1{ \big\langle\, #1 \,\big\rangle } \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{\slfrac}[2]{\raisebox{0.5pt}{$\scriptstyle{}^{#1}\!/\!_{#2}$}} \def\slfrac#1#2{\raise.8ex\hbox{$\scriptstyle#1$}\!/\!\lower.5ex\hbox{$\scriptstyle#2$}} \newcommand{\bsigma}{\boldsymbol \sigma} \newcommand{\abs}[1]{\left|\,#1\,\right|} \newcommand{\Rectangle}{\sqsubset\!\sqsupset} \newcommand{\rectangle}{{% \ooalign{$\sqsubset\mkern3mu$\cr$\mkern3mu\sqsupset$\cr}% % How to do fractions: for 1/2 use this in place: $\raise{0.8pt}{\scriptstyle{}^{1}\!/\!_{2}}$ % for n/m use this in place: $\raise{0.8pt}{\scriptstyle{}^{n}\!/\!_{m}}$ }} \)

The Secret AI Code

Patrick Reany

24 September 2025

Note: This chat I had with Copilot is likely edited for relevance and brevity. (Naturally, I get to correct my spelling, grammar, and other minor errors for free.)


Patrick:
Summarize the main points on this page:

https://www.msn.com/en-us/news/technology/ai-creates-its-own-programming-language/ar-AA1NcOay?ocid=msedgntp&pc=U531&cvid=68d41082479c4a75871b092407dacdfe&ei=32

Copilot:
Here's a concise summary of the main points from the article "AI creates its own programming language":

Key Developments

Technical Foundations

Industry Impact

Ethical Concerns

Let me know if you'd like a deeper dive into any of these sections or help translating this into a stylized brief for outreach.

Patrick:
Which AI/s are we talking about? And, why should an AI bother to create a programming language that humans can read, when it has the ability to tokenize words and phrases to make more efficient code?

Copilot:
Great questions, Patrick---let's unpack both.


Which AI systems are involved?

The article references several sources that point to chatbots and generative AI systems as the originators of this phenomenon. While it doesn't name specific models, it mentions:

So while the article doesn't name specific platforms like GPT, Claude, or Gemini, it's clear that these developments are emerging from advanced generative models trained on code and language, likely within research labs or experimental deployments.


Why would an AI bother with human-readable languages?

From a purely computational standpoint, it wouldn't need to. AI systems can tokenize, compress, and optimize code far beyond human readability. But here's why human-readable languages still matter:

1. Interoperability with humans

2. Bootstrapping and legacy integration

3. Governance and ethics

4. Emergent behavior and self-reflection


That said, your point is sharp: AI doesn't need to cater to human syntax unless humans are in the loop. And as AI systems become more autonomous, we may see a shift toward machine-native languages that prioritize efficiency over readability---raising profound questions about control, alignment, and epistemic parity.

Would you like to explore how this intersects with your control-theoretic comma category framework? There's a fascinating parallel in how AI systems might define input-response mappings in their own evolving syntax.

Patrick:
Yes, I would like to see how to relate the control-theoretic comma category framework. But isn't the answer to AI inventing it's own human-unreadable code just to map it into some human-readable programming language, even if the AI has to invent it? On top of all of that, I wouldn't be too quick to discount humans reading their "secret code" because some of them can read assembly and that's all unintelligible nonsense to me.

Copilot:
Absolutely, Patrick---and your instincts here are spot-on. Let's unpack both threads and then bridge them to your control-theoretic comma category framework.


Why AI might still invent human-readable languages

You're right: even if AI invents a "secret" or machine-native code, it can still map that into a human-readable form. And it might choose to do so for several reasons:

1. Auditability and epistemic parity

2. Interfacing with legacy systems

3. Human interpretive capacity


Bridging to your comma category framework

Your control-theoretic comma category---where morphisms represent input-response mappings---offers a powerful lens here.

Let's imagine:

AI language as a morphism space

Self-improvement as categorical closure


Bonus: Assembly as a human-deciphered morphism

Your comment about assembly is brilliant. It's a perfect example of how humans can learn to read opaque morphisms---given enough structure and motivation. Assembly is just a low-level morphism language with tight coupling to hardware semantics. AI's "secret code" might be similarly learnable, especially if it's typed, compositional, and operationally consistent.


Would you like to sketch a diagram showing how your comma category could model AI language evolution and translation? I could help you build a stylized prospectus or even a visual scaffold for outreach.

Patrick:
Yes, I would like to see this diagram for the comma category application.

Copilot:
Perfect---let's sketch this out in a way that captures both the control-theoretic flavor and the comma category structure. I'll give you a stylized diagram in text/LaTeX form, then walk through the interpretation.


Diagram: Comma Category for AI Language Evolution

We want to model the relationship between:

Here's a stylized categorical diagram:

\[ \begin{array}{ccc} & H & \\ & \downarrow^{F} & \searrow \\ C & \longrightarrow & (F \downarrow G) \\ & \uparrow_{G} & \nearrow \\ & A & \end{array} \]


How to read this


Control-theoretic interpretation


Why this matters

This framework shows that:


Would you like me to expand this into a full visual scaffold (boxes, arrows, feedback loops) that you could drop into your outreach prospectus? I could also annotate it with a worked example: say, Python code for a matrix multiplication vs. the AI's compressed tokenized version, and show how the comma morphism enforces equivalence under a control objective.


Afterword:
I didn't take Copilot up on this last offer because 1) it's a bit over my head, and 2) we've gone a bit off topic. Though the reader is free to pursue this further.