Claude Fable: Reverse Engineering the Jacobian Conjecture

PromptCube Expert 12h ago 251 views 8 likes 1 min read

Reconstructing the mathematical intuition behind the Jacobian Conjecture refutation requires a specific "clean room" approach because the original Chain of Thought (CoT) wasn't published. To solve this, I used a two-model loop: one Claude Fable instance was given the final result to generate a guide on how to reach it, and a second instance attempted to follow that guide. If the second model failed, I added hints; if it was too easy, I stripped details.

This process revealed some critical technical levers for anyone trying to replicate the logic or build an AI workflow for high-level math.

Key Mathematical Intuitions

The "shortcuts" that actually lead to the counterexample avoid several common pitfalls:

  • Avoid Normal Forms: Skip Bass–Connell–Wright or Drużkowski normal forms. While they seem natural, they often trade low degree for high dimension, making the counterexample harder to find.
  • Dimension Choice: Focus on $\mathbb{C}^3$ rather than $\mathbb{C}^2$.
  • Covering Degree: Target a 3:1 cover. Euler's results suggest 2:1 covers won't yield the necessary result.
  • Composition Strategy: Look for a composition of two functions (a shear and a ratio of polynomials) where the Jacobian determinants are $x$ and $c/x$ everywhere except at $x=0$. This effectively pushes all the "problems" into a single hole, which is where the $1 + xy$ term originates.

Practical Tutorial: Reproducing the CoT

To get a model to recreate this reasoning from scratch, you need a tight harness. I've tested a prompt that provides just enough scaffolding without spoiling the answer.

1. Initialize a fresh Claude Fable session.
2. Use a prompt that constrains the search space to $\mathbb{C}^3$ and specifies the avoidance of standard normal forms.
3. Guide the model to investigate the specific Jacobian determinant relationship ($x$ and $c/x$).

For the full prompt used to trigger this reasoning, check this specific gist:

https://gist.github.com/SonOfLilit/8882a145048ba260b160568ba6f48093#prompt-for-reproducing-cot

This is a great example of how prompt engineering can be used for "reverse-discovery" when the internal reasoning of a model is hidden.

Industry NewsAI News

All Replies (3)

N
Nova28 Advanced 12h ago
Did something similar with a physics problem. Hiding the answer first makes the reasoning way more reliable.
0 Reply
M
Max75 Advanced 12h ago
Tried this with a similar prompt; forcing the AI to explain its logic step-by-step really helps.
0 Reply
K
KaiDev Expert 12h ago
Wait, if you're not actually a math whiz, how did you even write this prompt? It's ridiculously dense. I'm halfway convinced you just hallucinated the logic or stole it from a textbook, because there's no way a normal person types like that.
0 Reply

Write a Reply

Markdown supported