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

Posted by Liogra123 13 hours ago

Counter158Comment56OpenOriginal

Comments

Comment by tazjin 12 hours ago

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.

Comment by wrs 12 hours ago

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)?

Comment by tazjin 12 hours ago

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.

Comment by wrs 11 hours ago

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

Comment by debugnik 10 hours ago

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.

Comment by gaigalas 9 hours ago

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.

Comment by aesthesia 12 hours ago

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

Comment by aidenn0 8 hours ago

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

Comment by blipvert 1 hour ago

It is unlikely to be necessary on HN to remind readers to remain indoors.

Comment by mechazawa 25 minutes ago

blueth is numberwang tho

Comment by ceocoder 12 hours ago

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

Comment by jmcqk6 11 hours ago

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.

Comment by TechSquidTV 5 hours ago

Woah believe it or not, that's Numberwang!

Comment by codeulike 13 hours ago

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

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

Comment by codeulike 1 hour ago

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

Comment by benj111 11 minutes ago

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

Comment by shervinafshar 12 hours ago

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

Comment by codeulike 12 hours ago

And so OPs app should have been called Colloson I guess

Comment by pimlottc 12 hours ago

Featuring Academy Award winner Olivia Colman!

Comment by grufkork 12 hours ago

Rotate the board!

Comment by BLKNSLVR 10 hours ago

This is the comment I was looking for!

Comment by doormatt 13 hours ago

And that's a bad miss...

Comment by toyg 11 hours ago

"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.

Comment by yoz 7 hours ago

She's gone, sir. They've all gone. And we're back. The incredibly posh people who are still unaccountably waiters.

Comment by tonymillion 8 hours ago

Now we know...

Comment by codeulike 10 hours ago

"there's everything to play for ...

... And forever to play it in!"

Comment by tclancy 11 hours ago

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.

Comment by tialaramex 10 hours ago

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.

Comment by gabrielsroka 11 hours ago

There are many sketches

Comment by bonyt 12 hours ago

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

Comment by Hackbraten 11 hours ago

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

Comment by jl6 11 hours ago

Amazing, I passed by Mornington Crescent only yesterday!

Comment by yoz 7 hours ago

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.

Comment by tialaramex 10 hours ago

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.

Comment by voidUpdate 1 hour ago

Is this using the rules from the official board game?

Comment by numberwan9 12 hours ago

Hey! I was not consulted?

Comment by da02 10 hours ago

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

Comment by mellosouls 2 hours ago

Some of us aren't American! (Or young)

In the UK we watched it on the Beeb when it was aired.

Comment by JuniperMesos 21 minutes ago

Some Mitchell and Webb sketches are posted on youtube.

Comment by shervinafshar 8 hours ago

I knew the Mitchell and Webb duo from _The Peep Show_ and one day (long before the pandemic) I saw a comment on Slashdot about working from home linking to this sketch: https://www.youtube.com/watch?v=co_DNpTMKXk

Then I watched that show and learned about Numberwang.

Comment by karim79 9 hours ago

Here is the history:

https://youtu.be/6ofnDdi-vfw?is=y9ccxKyAQfqiPIQs

Comment by IslandRebel 7 hours ago

I was forced to watch their atrocious sketch show while waiting in someone's house before we departed for the local pub.

Comment by karim79 9 hours ago

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.

Comment by karim79 9 hours ago

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.

Comment by bosshawg 8 hours ago

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

Comment by minitech 6 hours ago

> gradio is needed only for the demo. The model itself never needs it.

The “Usage” section doesn’t involve installing any dependencies, for example: https://github.com/GraafHenk/numberwang#usage

Comment by TZubiri 10 hours ago

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?

Comment by gaigalas 9 hours ago

Looking forward for the wordwang version.

Comment by rsamtravis 11 hours ago

Numberwang??

Comment by stackghost 12 hours ago

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

Comment by dofm 12 hours ago

That's not even a number.

Comment by tclancy 11 hours ago

In some bases it is. Numberwang!

With All Due Love,

Sir Digby Chicken Caesar, Esq.

Comment by TZubiri 10 hours ago

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

You reckless fool

Comment by julianz 3 hours ago

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

Comment by gregjw 9 hours ago

thats Numberwang!

Comment by Liogra123 13 hours ago

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