Possibly in response to Netflix's launch of Fuller House, Sam Kronick and Joe Veix wrote a program that, using a artificial neural network machine learning algorithm, writes a new episode of Full House everyday, for all eternity. Joe explains how it works here.
To generate text, this particular RNN is programmed to read an input (for example, Full House scripts), then generate an output based on patterns it notices. It compares the new file with the original, noting the hits and misses, and adjusts itself accordingly (hence: machine learning), before creating yet another new version. It repeats this process over and over, thousands of times, until it starts creating fairly accurate approximations of the original. Unlike Markov chains, which work on a word-by-word basis with no memory, RNNs can work on a character level, actively learn, and consider fancy things like paragraph structure and formatting.
|"Even primitive quantum processors of only a few qubits can perform important computations."|
|Syncthing: Replace Dropbox and BitTorrent Sync With Something Trustworthy|
|How to Build a Computer Model of God|
|“Both spacecraft are still operational when they reached interstellar space.”|
|CaptchaTweet: Write Tweets in Captcha Form|
|How to Avoid Jury Duty|
|Naked Preacher Lady [NSFW]|
|The (Very Scary) People of Public Transit|
|“Initial riders may be more comfortable getting into a car with a human in the driver seat.”|
|Make a Convincing Sex Video of Anyone You Like|
|“Can you replace the spring of a pogo stick with repelling magnets?”|
|Recycled Vacuum Lamps|
|Fake Name Generator|