GoKawiilGraafHenk releases WangNet, a 1.8MB neural network that judges 'Numberwang'
A developer known as GraafHenk has published an open-source project called Numberwang, built around a tiny 1.8MB JSON model and roughly 100 lines of pure Python with no external dependencies. The tool parses digits, number words, arithmetic expressions, Roman numerals, currencies and more across eleven languages, then returns one of four comedic verdicts inspired by the British sketch of the same name, including 'Numberwang' and 'Wangernumb'. It runs via command line or can be imported directly as a Python function returning probability scores for each verdict.
GoKawiil's interpretation of the reporting above, not reported fact.
While clearly a parody project, it showcases how lightweight rule-based or small neural models can handle multilingual text parsing without heavy machine-learning frameworks like PyTorch or NumPy. It's a playful example of minimalist software design and a nod to internet culture referencing a well-known comedy bit, likely to spread quickly among developers for its novelty and simplicity.
- The project requires only Python 3.8+, no external libraries, and fits in under 2MB.
- It recognizes numbers, arithmetic, currencies, and ordinal words across eleven languages.
- The four output verdicts are a direct homage to the 'Numberwang' comedy sketch.
Source: github.com, 2026-09-15
Published there as: “WangNet – 1.8 MB, zero-dependency Numberwang adjudication in 11 languages”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.