Subscribe NOW

Enter your email address:

Text Message our CEO:

650-283-8008

or on twitter

Free Resources

Click Here to learn more

In The Media

AI’s God Particle

by Larry Chiang on April 14, 2026

  • A recent arXiv paper by Andrzej Odrzywołek demonstrates that the binary operator eml(x,y) = exp(x) − ln(y), paired with constant 1, generates all elementary functions like sin, cos, log, sqrt, and arithmetic ops through repeated compositions forming identical-node binary trees.
  • The uniform EML tree structure enables gradient-based symbolic regression with optimizers like Adam, allowing AI models to recover exact closed-form expressions from numerical data at shallow depths, offering a simpler, regular architecture for scientific machine learning.
  • While theoretically elegant and analogous to NAND gates in logic, community responses highlight its impracticality for real computation due to numerical instability from exp/ln and inefficiency compared to specialized functions.

Leave a Comment

Previous post:

Next post: