This 1.8 MB neural network settles Numberwang in 11 languages

WangNet – 1.8 MB, zero-dependency Numberwang adjudication in 11 languages

A tiny neural network decides whether a number is Numberwang. The entire model is a 1.8 MB JSON file, and inference runs on about 100 lines of pure Python standard library — no PyTorch, no NumPy, nothing to install. It handles digits, words, arithmetic, Roman numerals, ordinals, and eleven languages, with 88.9% accuracy on held-out adjudications. Arithmetic on unseen operands is the weak spot: the network memorizes rather than computes.

A number's wangness is a property of the number, not the language it is said in: four, vier, quatre and cuatro all get the same verdict.
  1. tazjin

    I don't think that this produces correct results, as it seems to determine whether each individual number is Numberwang. However, whether a number is Numberwang can also depend on the previous numbers in the sequence or other factors.

    So I think as it stands right now this model can only determine whether a number would be Numberwang as the first number of a sequence, but even for that I still wouldn't rely on this in the actual game show.

  2. codeulike

    For those confused by this, here is the Mitchell and Webb "Numberwang" sketch

    https://youtu.be/0obMRztklqU?is=qufDLUkqofpr-K1Y

  3. bonyt

    You're playing with fire here, don't forget the tragedy of Colosson. Computers weren't meant to do this.

  4. da02

    How did you all first learn about the original Numberwang? Netflix?

  5. karim79

    This is hilarious and I miss numberwang. Also, the history of numberwang. And everything to do with numberwang. It was the most prescient sport back in the day.

    I'm glad that someone has stepped up to revive the legacy of numberwang.

More from this day

2026-09-15