Friends fans, there is something out there to hold you over until the cast reunion next month. Webcomic artist Andy Herd has caused something of a beautiful disaster, which perfectly describes the best episodes of the greatest sitcoms in television history. Herd has taken the script writing job out of the hands of humans and given them to a computer. The results are nothing short of ridiculous. And amazing.
Herd loaded every single Friends script into a recurrent neural network (RNN), which he briefly defined in an interview with The Daily Beast. “It works by predicting the next letter to follow a given sequence of letters, and the predictions are determined by what it learned about language from the Friends dialogue provided.” Basically, it learned to write an episode of Friends using just the information provided, which in this case, was episodes of Friends.
The “recurrent” part of an RNN defines the basic function of the process. To predict the next letter or word, the system relies on what came before it. It builds on what it learned in the previous few steps, and continues this pattern throughout the sequence. An RNN can also be “trained” for more predictable and fitting results, but is also limited by long spaces between dependencies, among other factors. Training is not easy and can include teaching the program to scan deeper, and also make predictions for future sentences, rather than just relying on current and previous data.
Herd’s computer initially spouted nonsense, but eventually some gold was struck. After running his program for 12 hours, Herd’s computer produced scenes that shows an inkling of what an RNN process is capable of in this type of application. Herd tweeted some screenshots of this bizarro Friends episode, and we’ve included some of our favorite lines below:
“Joey: Seriously give me a clown on the table that’s all.”
“Chandler: (in a muffin) (Runs to the girls to cry) Can I get some presents.”
Herd used Google’s artificial intelligence engine TensorFlow, which became open source in November. “I’ve been reading up about machine learning in my spare time lately because it’s really fascinating,” said Herd. “I honestly don’t understand a lot of the underlying mathematics, but I’m trying! Also, Satan helped a bit.”
Herd plans to further develop his Friends bot to make more sense, after which he may release it to the public. He hopes that his efforts can get people interested in learning new things.
China just gave Hollywood a cautionary tale about AI filmmaking. Sanxingdui: Future Past, billed as the country's first fully AI-generated movie, hit theaters on October 23 and bombed at the box office.
According to Futurism, the film's reported $1.5 million production budget landed on more than 10,000 screens. Yet it pulled in only about $181,000, averaging roughly $20 per screen, making the budget difficult to recover.
Some of the best shots in Grok Imagine’s AI-made Odyssey don’t contain actors. Ancient landscapes stretch into the distance. Close-ups of grimy hands suggest people who have touched something rougher than a keyboard. For a few seconds, the illusion holds.
https://twitter.com/imagine/status/2113712964419063911
YouTube videos could soon look better without eating quite so much data, right? Thankfully, the platform plans to introduce a new video format called AV2 on its web player in early 2027, promising more efficient streaming and potentially fewer playback hiccups on slower internet connections. The big headline is a roughly 30% improvement in compression efficiency over AV1, YouTube's existing video format. That doesn't guarantee every video will use 30% less data, but it could make streaming a little easier on both internet connections and data allowances.
What is AV2, and why should viewers care?