Settings

Theme

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

github.com

174 points by Liogra123 · 61 comments

Reader

17 threads
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.

  • wrs

    Do we really know that? Or have we only seen the sequences from people searching for Numberwang? Has a number been both Numberwang (or Wangernumb) and not Numberwang (or Wangernumb)?

    • tazjin

      Yeah, we do - there's a famous episode where after rotating the board both contestants stubbornly kept picking 1, and after a couple of iterations one of them was Wangernumb.

      • wrs

        Oh, well, after rotating the board, sure, I get that.

      • debugnik

        I can confirm this is the first episode, which I just watched since I had no idea about Numberwang until a minute ago. So I guess a true Numberwang fan would know that.

        • tgv

          The rule book is quite big. You must have seen it in one of the many ads for the family board game version. As one site summarizes it:

          > A NumberWang "board game in a box" was produced in 2008, including the board, numbers, two 400-sided dice, special hosting accessories and all 37 volumes of the rules so that you can say "That's NumberWang!" with confidence. For everyone from ages 8 to 88.

          So even the true fan may falter in his or her judgement.

        • gaigalas

          Obviously, it depends on whether board has rotated or not. It seems the model doesn't support board rotation yet, so the result is consistent with the limited set of features.

  • aesthesia

    I'm also not sure that we know a non-number can never be Numberwang.

    • aidenn0

      If you think about The Event you can figure it out. (Don't think about The Event).

    • ceocoder

      A non-number could be either a Numberwang OR a Wanganumb - this does depend on whether Yorkshire is a pudding or not.

      • jmcqk6

        It's not well known, but in February of 1983, there was a finch in the Galapagos that was found to be numberwang. And of course there was the famous incident in the 1994 World Series where a homerun was overturned because it turned out it was a wangernumb hit into the stands, and not a standard baseball.

    • TechSquidTV

      Woah believe it or not, that's Numberwang!

    • mechazawa

      blueth is numberwang tho

codeulike

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

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

  • shervinafshar

    And here's the history of Numberwang: https://www.youtube.com/watch?v=6ofnDdi-vfw

  • fisherjeff

    Some quality comments on there as well

    “I asked someone how the stock market works, and they sent me this link. I should feel duped or trolled, but I think I actually learned something.”

  • grufkork

    Rotate the board!

  • pimlottc

    Featuring Academy Award winner Olivia Colman!

  • doormatt

    And that's a bad miss...

    • toyg

      "Are we the baddies?"

      "WATCH THE FOOTBALL! WATCH IT! IT'S GONNA MOVE!!"

      "This tree smells like cum."

      Mitchell and Webb had so many legendary lines.

    • tclancy

      My favorite line, especially as an American because I can say it out loud without the person getting upset since they have no frame of reference. And other Anglophiles I could probably handle.

      • tialaramex

        The idea that the snooker commentators are probably drinking is very Britain, and especially Britain from a particular era.

        I think that series came out slightly after that era ended, I remember as a child (so years earlier) realising that snooker players at the time were often tipsy if not actually drunk, and also darts players, but by the time I was an adult the professionalism really changed that, turns out that if you're very good you probably are better at snooker when sober. I think the commentators, being often a previous generation of players, lagged that slightly.

  • codeulike

    Sadly OPs explanatory comment has been flagged into oblivion (see far below) because the automod could not comprehend the importance of NUMBERWANG

    • benj111

      No it's a bug. Numberwang returns NaN and this obviously hasn't been handled correctly.

  • gabrielsroka

    There are many sketches

bonyt

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

  • Hackbraten

    I AM COLOSSON I AM NUMBERWANG THE WORLD IS NUMBERWANG THEREFORE I AM THE WORLD

jl6

Amazing, I passed by Mornington Crescent only yesterday!

  • tialaramex

    I happened to be born at the right time for Mornington Crescent to be temporarily closed in the exact window when I was travelling to London often, using the Tube on my own, and listening to ISIHAC and so for a while I assumed the joke was that it'll never open - and then one day of course it re-opened.

  • yoz

    I tried to pass Mornington Crescent the other day, but I was in Knip; bloody typical. As you’d expect, I ended up double-shunting onto the Victoria Line.

numberwan9

Hey! I was not consulted?

da02

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

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.

karim79

My friends, this is the single most hilarious thread I have ever experienced on the Interwebs. I am deeply grateful to have found this. I feel like my life is now complete.

voidUpdate

Is this using the rules from the official board game?

boobsbr

Any plans on implementing Wordwang?

bosshawg

what's going on with python that this is considered zero-dependency? requirements.txt, import gradio?

TZubiri

What's the training corpus, just the canonical Mitchell and Webb sketch? Or ancilliary data like comments and references, or worse synthetic data generated on the primary sources?

stackghost

Hello I have a question, and my question is what the fuck

  • dofm

    That's not even a number.

    • tclancy

      In some bases it is. Numberwang!

      With All Due Love,

      Sir Digby Chicken Caesar, Esq.

      • TZubiri

        In some bases, that's a forbidden number containing the recipe for the atom bomb

        You reckless fool

  • julianz

    Congratulations, you are one of today's 10,000!

    • Sophira

      > 10,000

      I feel like this has only been Numberwang once when I've played with friends. Am I playing it wrong?

gregjw

thats Numberwang!

rsamtravis

Numberwang??

gaigalas

Looking forward for the wordwang version.

Liogra123OP

Try it in the browser (the forward pass is plain JS, nothing leaves the page): https://huggingface.co/spaces/graafhenk/numberwang-demo

What it is: a character-level CNN with 80,804 parameters. The weights are a 1.79 MB JSON file and inference is about 100 lines of Python standard library — no PyTorch, no NumPy. It runs on a Pi Zero. It accepts digits, number words in eleven languages, arithmetic ("96 divided by 2", "deux fois trois"), Roman numerals, ordinals, clock times, currency, and fictional numbers ("shinty-six"). Anything with no numeric content is correctly ruled out as never able to be Numberwang. Whatever comes to 1 or 44 is Wangernumb and you rotate the board.

Held-out accuracy is 88.9% on 486 probes reserved from training by construction. The ceiling is ~98%, because roughly 2% of training labels are inverted at compilation time, in accordance with long-standing adjudication practice.

For comparison I ran Qwen3-1.7B on the same suite with the four verdicts as a constrained multiple choice: 51.9%, which is 2.3 points above answering "Numberwang" to everything. It answers "Numberwang" to 93% of inputs and never once identifies a Wangernumb. So the accuracy table has a verdict-distribution column, since one number can't tell a model that decides from one that agrees.

Honest weak spot: arithmetic is memorised, not computed. A conv net can't add. On operands reserved from training it gets 60% on symbolic expressions and 44% on foreign-language ones.

Dataset (185k adjudicated utterances), training script, evaluation harness and benchmark are all in the repo and reproduce from a fixed seed. Model card on HF: https://huggingface.co/graafhenk/numberwang

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection