Calvin and Markov digests Calvin and Hobbes strips and generates endless new comics with random, semi-coherent dialogue using Markov chains. Here's some details about how I built it. [more inside]
I made a thing that tweets weird mashed-up VICE headlines. Some of them are funny I think, if you're familiar with VICE.
Isaac Watts, known as the “Father of English Hymnody,” wrote words to dozens of well-loved hymns and carols, including Joy To The World and O God, Our Help In Ages Past. @watts_ebooks generates random hymn stanzas based on his complete works, with (mostly) correct rhyme and scansion and HIGHLY DUBIOUS theology! (Github repo; blog post on how it all works.)
Markov chain-style text generation that conforms to Zipf's law. Very spiffy. [more inside]
A markovian text generator, tweeting away, starting with the text, "As Gregor Samsa awoke ...". Code can be found at https://github.com/willf/microsoft_ngram (in the examples directory). Enjoy such gems as "As Gregor Samsa awoke one morning from uneasy dreams he found himself in charge of our financial system," "Gregor Samsa awoke…to find himself transformed into an enormous social mechanism for the centralisation of the New Zealand parliament," and "Gregor Samsa awoke from a night of clubbing former actress Lindsay Lohan."
A Minecraft-themed parody of @horse_ebooks.
An incoherent savior for an incoherent age.
I decided to teach myself some python and CGI. This is what came of it. It is a single serving page that delivers a markov chain of every deleted post's title, plus a markov deleted reason and some text from my comments made into a fake post description. In later versions, I may scrape deleted post descriptions so it's less disjointed than it is, but I don't want to think about how long it would take to scrape every deleted post, and if it could be done in a server-friendly fashion (I haven't done any back of the envelope math to see how it goes). [more inside]
It's never too soon for more Markov chains, right? cobe is a Markov based text generation framework that behaves like the venerable MegaHAL chatbot, backed with a more modern (SQLite) datastore. Its brain is kept entirely on disk, uses little memory, and scales reliably. A very minimal IRC client is included. [more inside]
Markov meets Mulder! Previously, On The X-Files... is a random image generator that uses markov chains to generate random conversations between major characters from The X-Files. The text is all drawn from post-processed transcripts of the show's nine-season run; the code is perl, the images are created using the ImageMagick library. [more inside]
Twittov generates nonsense from your Twitter history using Markov chains. Note: Your tweets must be public for it to work. I posted this as a python script a year ago, but it's totally rewritten for the new Twitter API and has a Django/jQuery interface.
Garkov is a comic strip generator that uses Markov chains to synthesize new Garfield strips based on transcripts of several hundred existing strips. The output varies nicely from plausible to surreal to downright incoherent. [more inside]