The official Cards Against Humanity store. This is literally the only place you can buy every product CAH sells. Cards Against Humanity Black Friday 2020 Today is Black Friday, Cards Against Humanity's favorite holiday. Usually, we do a big, loud stunt in an attempt to make some kind of statement about consumer capitalism. This year, we're not. Jun 30, 2020 Cards Against Humanity might not have been quite so tongue-in-cheek with its racism and sexism. A pretty damning Polygon article details the allegations employees have been making about a racist.

1. Cards Against Humanity Black Cards Only
2. Cards Against Humanity Black Cards List
3. Cards Against Humanity Black Cards
4. Cards Against Humanity Black Cards List
5. Cards Against Humanity Black Cards Pdf

Cards Against Humanity — Full Size Print Versions

Here are some files you can print out and use for your own copy of Cards Against Humanity. These are formatted to be very simmilar size to the actual cards, so they should be compatible with any future expansions or any commercially purchased copies. These mostly use black text on white backgrounds to save me (or you) on ink/toner. So for best results, you may want to put these in colored sleeves to denote black vs. white cards. If you are printing these on paper (as I did) rather than card stock, you may also want to use playing cards or similar as a backer in the sleeve.

A party game
for horrible people.

First I have the core game, with what I believe is the first expansion included. These were made from text files found on the Cards Against Humanity website. Following that is the second expansion (both black and white cards) with a few blanks for formatting purposes. Next is the third expansion as two files including an inverted color black cards file. After that is a copy of the cards given away at PAX East 2013, and PAX Prime 2013 (marked with the PAX logo), the Holiday pack (marked with a tree), and the Canadian expansion (marked with a maple leaf).

Next are a collection of white and black cards made from lists found on several threads of the Board Game Geek forums. Additionally, I've included a page of blank cards, for you to write in whatever you come up with. The (.pdf) and (.odt) are black on white, and the (.svg) is white on black. To write in what you want before printing you will need 7zip or simmilar to to open the compressed files, LibreOffice or simmilar to open the .odt, and .ods files, and finally Inkscape or simmilar to open the .svg files.

Finally, there is an archive (.zip) file of all the card lists I've used for making these documents so far. Also, I formatted these to be printed on Letter Size (8.5' x 11') paper or cardstock. I used a left and right margin of 0.5 inches, and a top and bottom margin of 0.3 inches. As such, you should make sure your printer can handle a top and bottom margin of 0.3 inches before you decide to use these files.

Share and enjoy ...

Cards Against Humanity is a trademark of Cards Against Humanity, LLC. Cards Against Humanity is distributed under a license. Cards Against Humanity, LLC does not endorse me, this website, or any of the files here in any way. I did not create the game, nor am I attempting to make any money by selling it. I have provided these documents free of charge for personal use and entertainment purposes.

Hi all, I’m Spencer, the “kid” who made this. I’ll do my best to explain, I promise it’s not as intimidating as it looks. If you have any questions after reading this, feel free to ask us on Twitter at @CAH.

OpenAI’s “GPT-2”

The Cards Against Humanity AI is built on top of a neural network called “GPT-2” made by OpenAI. GPT-2 is designed to generate realistic-looking text. To understand it, I'd really recommend watching the computerphile videos, but I'll do my best to explain it here.

Neural networks are algorithms capable of learning when given lots of data. Think of the YouTube recommendation system. It learns what videos you like based on all the data you give it: what you watch, what you thumbs-up, etc. Generally, neural networks are given some sort of input, and then asked to make a prediction, which is called the “output.”

GPT-2 uses text as its input and tries to predict the word (or punctuation) that comes next in that text. So, if given “Bananas”, it tries to predict the next word, and it might come up with “are.” Then you feed it both words — “Bananas are” — and it does the same thing. It might predict that “in” comes next. Now just keep doing that over, and over and eventually you’ll have entire paragraphs.

When it predicts the next word, it actually predicts a whole bunch of words that seem like they could be next and randomly selects one of them. Technically, it assigns a probability distribution across all possible words and then uses that distribution to select the next word.

This randomness is part of what makes it creative and lets it generate something new every time you run it. Since it was trained on so much data, there’s rarely one right answer to “which word should come next?”

›››››› TL;DR: GPT-2 generates new text by imitating text it’s seen before, with some added randomness.

Training the Neural Network to Write Cards

GPT-2 works well for many different language generation tasks because of a process called “transfer learning.” This is where a network trained on a general task is then fine-tuned to a more specific task. The knowledge of the general task helps the network learn the specific task faster and better. Think of teaching someone chemistry. Might it be easier to teach them if they already know how to do high-level math?

In our case, OpenAI already trained the network on 40 GB of Internet text. To put that in perspective, a 400 page book is generally about 1 MB. So, 40 GB of text is roughly equivalent to 40,000 books. What that means for us is the network already knows how to generate realistic-looking text and it also has a lot of cultural information encoded in it. So, all we need to do is train it on what white cards look like and what types of content they contain.

Drawing by my girlfriend @akpaley

This was done by taking that pre-trained network and then training it further on the text of 44,000 white cards. That includes all (roughly) 2,000 cards in the official game, another 25,000 internal brainstorming cards that never made it into the game, and 17,000 unofficial cards from fan-curated lists.

We stopped the training once it could “consistently” produce cards matching the grammar and tone of the game. We did this so it didn’t draw too much from already-written cards while still leveraging as much cultural information as possible.

›››››› TL;DR: GPT-2 was already smart enough to make realistic-looking text. We just fed it a bunch of cards until it learned what we wanted from it.

Generating and Filtering Cards

Cards Against Humanity Black Cards Only

As I said before, GPT-2 lets us control the weirdness and creativity of its output. Each time it adds a word, it assigns a probability to all possible next words based on what it has learned. If we narrow the choices for the next word down to just the few most-likely words, the network will be less creative. Cards all start sounding the same and generally just suck. On the other hand, if we make the network too creative, it stops making sense and starts to sound like it’s just randomly pulling words from the dictionary.

Another fun thing we can control is how a card starts. Normally, we let the network pick the first word of the card, but we can also prompt it with phrases we know work well. For example, we could give it the prompt “Some kind of”, and it could complete that card as “Some kind of sci-fi oatmeal” or “Some kind of otter-themed sexy sea otter print pantsuit.” Most of the cards we generate are random (no prompt), but a decent fraction were made with a list of prompts we found worked well after some testing.

Cards Against Humanity Black Cards List

As a side note, card generation actually happens a lot faster than the printer is showing. On my personal computer, 20 cards can be generated per second, even after filtering out bad cards. It didn’t take that long to train the network, either. While it would take months for a single computer to train the original network, fine-tuning it to generate cards took less than an hour.

As we’re generating cards, we want to be able to automatically eliminate as many “bad” ones as possible. We can’t use an algorithm to eliminate unfunny cards (at least, not yet), but there are several other ways we can filter out bad cards.

The first filtering step is a simple check to make sure the text is formatted the way we expect cards to be formatted. If it’s not, we’ll discard it and move on. The network is pretty great at following the formatting we trained it to follow, so only a few percent of cards are thrown away for this reason.

Cards Against Humanity Black Cards

Next, we filter out cards containing any words on our banned-words list. This includes words we’d simply never print, along with jokes we don’t trust the algorithm to tell with any kind of cultural awareness. This step also removes only a few cards.

Our main filtering step is to remove cards that are basically copies of cards that already exist (either in a published set, or in an internal list somewhere). GPT-2 is trained to reproduce text it’s seen, so generating copies is inevitable. Sometimes this means letter-for-letter copies of existing cards, but more often it will change, add, or remove a few words or spell them differently. 'A falcon with a cap on its head' is basically the same idea as 'A falcon with a funny hat.” So we use fuzzy string matching to see how similar a new card is to every one of the 44,000 cards we trained the network on. This step throws out just about 50% of the generated cards and takes almost as long as the initial generation did, functionally quadrupling the time it takes to generate cards.

As a side note here, we also found that cards below a certain similarity threshold were basically garbled text, so we filter those out as well. This removes cards like “ಠ益ಠ”, “~~~~~~~~~~~~~ meh”, and “2+2=5.” Turns out any card that makes sense is going to be at least somewhat similar to one of the 44,000 cards we used to train the network.

Cards Against Humanity Black Cards List

Finally, we capitalize the cards and add periods if the model didn’t already do that. No filtering here, we just like things looking pretty.

Cards Against Humanity Black Cards Pdf

›››››› TL;DR: We have control over some aspects of how the cards turn out. And we can automatically filter out cards that sound too much like cards that already exist.