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.
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)?
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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?
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
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.
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)?
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.
Oh, well, after rotating the board, sure, I get that.
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.
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.
I'm also not sure that we know a non-number can never be Numberwang.
If you think about The Event you can figure it out. (Don't think about The Event).
It is unlikely to be necessary on HN to remind readers to remain indoors.
blueth is numberwang tho
A non-number could be either a Numberwang OR a Wanganumb - this does depend on whether Yorkshire is a pudding or not.
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.
Woah believe it or not, that's Numberwang!
For those confused by this, here is the Mitchell and Webb "Numberwang" sketch
https://youtu.be/0obMRztklqU?is=qufDLUkqofpr-K1Y
Sadly OPs explanatory comment has been flagged into oblivion (see far below) because the automod could not comprehend the importance of NUMBERWANG
No it's a bug. Numberwang returns NaN and this obviously hasn't been handled correctly.
And here's the history of Numberwang: https://www.youtube.com/watch?v=6ofnDdi-vfw
And so OPs app should have been called Colloson I guess
Featuring Academy Award winner Olivia Colman!
Rotate the board!
This is the comment I was looking for!
And that's a bad miss...
"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.
She's gone, sir. They've all gone. And we're back. The incredibly posh people who are still unaccountably waiters.
Now we know...
"there's everything to play for ...
... And forever to play it in!"
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.
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.
There are many sketches
You're playing with fire here, don't forget the tragedy of Colosson. Computers weren't meant to do this.
I AM COLOSSON I AM NUMBERWANG THE WORLD IS NUMBERWANG THEREFORE I AM THE WORLD
Amazing, I passed by Mornington Crescent only yesterday!
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.
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.
Is this using the rules from the official board game?
Hey! I was not consulted?
How did you all first learn about the original Numberwang? Netflix?
Some of us aren't American! (Or young)
In the UK we watched it on the Beeb when it was aired.
Some Mitchell and Webb sketches are posted on youtube.
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.
Here is the history:
https://youtu.be/6ofnDdi-vfw?is=y9ccxKyAQfqiPIQs
I was forced to watch their atrocious sketch show while waiting in someone's house before we departed for the local pub.
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.
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.
what's going on with python that this is considered zero-dependency? requirements.txt, import gradio?
> 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
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?
Looking forward for the wordwang version.
Numberwang??
Hello I have a question, and my question is what the fuck
That's not even a number.
In some bases it is. Numberwang!
With All Due Love,
Sir Digby Chicken Caesar, Esq.
In some bases, that's a forbidden number containing the recipe for the atom bomb
You reckless fool
Congratulations, you are one of today's 10,000!
thats Numberwang!
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