Morgan Neville knows not everything we talk about will make it into this story. After making dozens of documentaries, he knows that in order to be told properly, the best stories have to leave some parts out. Built using audio interviews with collaborators like Kendrick Lamar and Missy Elliott--many of which Neville conducted remotely during Covid-19 lockdowns--it's a biopic of Williams' life animated entirely with Lego. Because Williams' career as a hitmaker spans 30-plus years, and given the fact that animation is expensive, Neville knew he had to leave some stuff out. "People say, 'Oh, the interviews are so great.' And I'm like, 'Yeah, I used the good ones,'" he says, sitting in a restaurant off of Central Park, a few days before Piece by Piece's New York premiere.

On January 1, Mike Neville gave Midjourney the following prompt: "Steamboat Willie drawn in a vintage Disney style, black and white. He is dripping all over with white gel." There's no polite way to describe what this prompt conjured from the AI image generator. It looks, very much, like Mickey Mouse is drenched in ejaculate. At the start of every year, a crop of cultural works enters the public domain in the United States.

How to Do It is Slate's sex advice column. Send it to Stoya and Rich here. My first crush ever was on my uncle. I've noticed an attraction to two of my cousins. I've never, ever considered acting on these desires or told anyone, but I'm wondering if this is normal. Is my brain missing the evolutionary programming that makes you not want to fuck your family?

Easily available software can imitate a person's voice with such accuracy that it can fool both humans and smart devices, according to a new report. Researchers at the University of Chicago's Security, Algorithms, Networking and Data (SAND) Lab tested deepfake voice synthesis programs available on the open-source developer community site Github to see if they could unlock voice-recognition security on Amazon's Alexa, WeChat and Microsoft Azure. One of the programs, known as SV2TTS, only needs five seconds' worth to make a passable imitation, according to its developers. Described as a'real-time voice cloning toolbox,' SV2TTS was able to trick Microsoft Azure about 30 percent of the time but got the best of both WeChat and Amazon Alexa almost two-thirds, or 63 percent, of the time. It was also able to fool human ears: 200 volunteers asked to identify the real voices from the deepfakes were tricked about half the time. The deepfake audio was more successful at faking women's voices and those of non-native English speakers, though, 'why that happened, we need to investigate further,' SAND Lab researcher Emily Wenger told New Scientist.

When Roadrunner, a documentary about late TV chef and traveler Anthony Bourdain, opened in theaters last month, its director, Morgan Neville, spiced up promotional interviews with an unconventional disclosure for a documentarian. Some words viewers hear Bourdain speak in the film were faked by artificial intelligence software used to mimic the star's voice. Accusations from Bourdain fans that Neville had acted unethically quickly came to dominate coverage of the film. Despite that attention, how much of the fake Bourdain's voice is in the two-hour movie, and what it said, has been unclear--until now. In an interview that made his film infamous, Neville told The New Yorker that he had generated three fake Bourdain clips with the permission of his estate, all from words the chef had written or said but that were not available as audio.

In life, Anthony Bourdain could cook up a right storm in the kitchen. In death, the celebrity chef has cooked up a storm of a whole different flavour. Only it wasn't really him who cooked up that storm. In his new documentary, film-maker Morgan Neville drops a pinch of artificial intelligence into his recipe, using the technology to construct a few lines of voiceover by Bourdain. A lot of critics -- including Bourdain's ex-wife Ottavia -- find Neville's creative choice completely unpalatable, suggesting the end result amounts to little more than a deepfake.

Early reviews of the new documentary film ROADRUNNER about the late food mogul Anthony Bourdain were overwhelmingly positive. Upon its official release last week, though, it started to get some backlash particularly after filmmaker Morgan Neville said he used artificial intelligence technology to create some quotes in Anthony's voice. In an interview with The New Yorker, Neville explained how his team "created an A.I. model of his [Bourdain's] voice" because there were three quotes wanted for the film that had no previous recordings before. By sending a software company hours of recordings and footage, they were able to splice together these quotes in Anthony's voice. "If you watch the film, other than that line you mentioned, you probably don't know what the other lines are that were spoken by the A.I., and you're not going to know," Neville told The New Yorker: "We can have a documentary-ethics panel about it later."

In the new documentary "Roadrunner" about the life of celebrity chef Anthony Bourdain, the filmmakers made a controversial choice. The director, Morgan Neville, commissioned a software company to re-create Bourdain's voice digitally, synthesizing three lines of voice-over. The lines were statements that Bourdain wrote but never uttered before his death in 2018. The artificial-intelligence technology used to craft the fictitious audio is called "deepfake," and it has set off a debate online since food writer Helen Rosner published a piece in the New Yorker last week, "The Ethics of a Deepfake Anthony Bourdain Voice," interviewing Mr. Neville about the decision. While the audiovisual technology that allows this kind of trickery has long been in development, the word "deepfake" first emerged in late 2017.

The ending of Roadrunner, Morgan Neville's new documentary about the life, career, and 2018 suicide of Anthony Bourdain, packs quite a punch. After exploring the celebrity chef's relationship to fame and how his death affected those closest to him, the film closes on Bourdain peacefully walking into the distance on a beach--or so it seems. A voiceover from Bourdain's friend, artist David Choe, breaks the spell to say that Bourdain himself would hate this saccharine ending. He then criticizes the way society idolizes artists who take their own lives by, for instance, painting their faces on the sides of buildings. A voice behind the camera points out that there are such murals of Bourdain downtown.

If you've heard Anthony Bourdain speak even a few sentences aloud, it's impossible to read his writing without hearing it in his own voice. In Morgan Neville's documentary portrait Roadrunner: A Film About Anthony Bourdain, Bourdain describes how he would roll out of bed in the morning and head straight for his keyboard without pausing for so much as a cup of coffee. His writing was a fluid extension of his life, and his life was sometimes inextricable from his writing. His longtime collaborators describe how, even in the recording booth, Bourdain would relentlessly cross out and rewrite his own voice-over, in part to purge from it any of the clichés of TV narration that wouldn't feel true to himself--or at least to the version of himself he was presenting. The intensely personal connection with that voice may be one reason why some of Bourdain's admirers reacted so strongly to the news that Neville had used a digital simulation of it in Roadrunner, using artificial intelligence to extrapolate from hours of his actual voice recordings. As Neville told both GQ's Brett Martin and the New Yorker's Helen Rosner, he worked with a software company to create audio readings of three passages that Bourdain wrote but never spoke out loud, at least one of them taken from a personal email never intended for anyone but its recipient.