Ads

From The Economist:

IN THE dystopia of George Orwell’s novel “1984”, Big Brother numbs the masses with the help of a “versificator”, a machine designed to automatically generate the lyrics to popular tunes, thereby ridding society of human creativity. Today, numerous artificial-intelligence (AI) models churn out, some free of charge, the music itself. Unsurprisingly, many fear a world flooded with generic and emotionally barren tunes, with human musicians edged out in the process. Yet there are brighter signs, too, that AI may well drive a boom in musical creativity.

AI music-making is nothing new. The first, so-called “rules-based”, models date to the 1950s. These were built by painstakingly translating principles of music theory into algorithmic instructions and probability tables to determine note and chord progressions. The outputs were musically sound but creatively limited. Ed Newton-Rex, an industry veteran who designed one such model for Jukedeck, a London firm he founded in 2012, describes that approach as good for the day but irrelevant now.

The clearest demonstration that times have changed came in August 2023. That is when Meta, a social-media giant, released the source code for AudioCraft, a suite of large “generative” music models built using machine learning. AI outfits worldwide promptly set about using Meta’s software to train new music generators, many with additional code folded in. One AudioCraft model, MusicGen, analysed patterns in some 400,000 recordings with a collective duration of almost 28 months to come up with 3.3bn “parameters”, or variables, that enables the algorithm to generate patterns of sounds in response to prompts. The space this creates for genuinely new AI compositions is unprecedented.

Such models are also getting easier to use. In September Stability AI, a firm based in London at which Mr Newton-Rex worked until recently, released a model, Stable Audio, trained on some 800,000 tracks. Users guide it by entering text and audio clips. This makes it easy to upload, say, a guitar solo and have it recomposed in jazzy piano, perhaps with a vinyl playback feel. Audio prompts are a big deal for two reasons, says Oliver Bown of Australia’s University of New South Wales. First, even skilled musicians struggle to put music into words. Second, because most musical training data are only cursorily tagged, even a large model may not understand a request for, say, a four-bar bridge in ragtime progression (the style familiar from Scott Joplin’s “The Entertainer”).

The potential, clearly, is vast. But many in the industry remain sceptical. One widespread sentiment is that AI will never produce true music. That’s because, as a musician friend recently told Yossef Adi, an engineer at Meta’s AI lab in Tel Aviv, “no one broke its heart”. That may be true, but some AI firms reckon that they have found a way to retain and reproduce the “unique musical fingerprint” of their musician users, as LifeScore, a company founded near London, puts it. LifeScore’s AI limits itself to recomposing the elements of a user’s original recordings in ways that maintain the music’s feel, rather than turning them into something radically new.

It takes about a day to plug into LifeScore’s model the dozens of individually recorded vocal and instrumental microphone tracks, or stems, that go into producing an original song. Once that’s done, however, the software, developed at a cost of some $10m, can rework each stem into a new tempo, key or genre within a couple of seconds. The song’s artists, present during the process, choose which remixes to keep. Manually remixing a hit track has traditionally taken one or more highly paid specialists weeks.

LifeScore, says Tom Gruber, a co-founder, is “literally swamped with requests” from clients including Sony Music, Universal Music Group and Warner Music Group. An original release is typically turned into anywhere from a handful to a dozen remixes. But one client aims to release a dizzying 6,000 or so AI versions of an original track, each targeting a different market. Artists including Pink Floyd’s David Gilmour and Tom Gaebel, a German pop singer, use LifeScore’s AI to power websites that allow fans to generate, with a few clicks, new remixes adapted to personal tastes.

The beat of a different drum

If this seems like dizzying progress, it’s worth noting that AI’s impact on music is still in its early days. Legal uncertainties over the use of copyrighted recordings to train models have slowed development. Outfits that have coughed up for licensing fees note that this can get expensive. To save on that cost, MusicGen’s training set mostly sidestepped hits, says Dr Adi. Though output is pretty good, he adds, the model is not yet “artistic enough” to generate narratively complete songs. Harmonic misalignments are common. OpenAI, a San Francisco firm, for its part, says its MuseNet model struggles to pull off “odd pairings”, such as a Chopin style that incorporates bass and drums.

In time, bigger training sets of better music will largely overcome such shortcomings, developers reckon. A Stability AI spokesperson says that while Stable Audio’s top duration for coherently structured music—“intro, development and outro”—is now about 90 seconds, upgrades will produce longer pieces with “full musicality”. But judging music AI by its ability to crank out polished tracks mostly misses the point. The technology’s greatest promise, for now at least, lies elsewhere.

Part of it is the empowerment of amateurs. AI handles technical tasks beyond many people’s capabilities and means. As a result, AI is drawing legions of newbies into music-making. This is a boon for experimentation by what Simon Cross, head of products at Native Instruments, a firm based in Berlin, calls “bedroom producers”.

. . . .

AI serves professionals, too. The soundtracks to “Barbie” and “Oppenheimer” were cleaned up in post-production with RX, for example. Another application area is “style transfer”, in which models transform music recorded with one instrument into sounds that seem to come from a different one, often with a twist or two requested by the user. Style transfers are also used for voice. A model developed by a startup in London called Voice-Swap slices up sounds sung by (remunerated) professional singers and rearranges the slivers into lyrics written by the service’s users, who pay licensing fees for the rights to sell the resulting tracks. And AI tools already exist to recreate singers’ voices in other languages. Vocaloid, a voice-synthesising tool from Yamaha, a Japanese instrument manufacturer, is one of many that can use a translation sung by a native speaker as a template for an AI to imitate as it rearranges, modifies and stitches together tiny snippets of the original singer’s voice.

Link to the rest at The Economist

Novels aren’t pedagogical instruments, or instructions in law or physics or any other discipline. A novel has to be an emotional experience, a trip of the imagination, and because science has raised so many issues that concern and affect humans, it’s a good starting place for me.

Alan Lightman

From Wired:

David Lynch’s 1984 sci-fi epic Dune is—in many ways—a misbegotten botch job. Still, as with more than a few ineffectively ambitious films before it, the artistic flourishes Lynch grafted onto Frank Herbert’s sprawling Machiavellian narrative of warring space dynasties have earned it true cult classic status. Today, fans of the film, which earned a paltry $30 million at the box office and truly bruising reviews upon its release, still wonder what Lynch would have done if given the opportunity to adapt the next two novels in Herbert’s cycle: Dune Messiah and Children of Dune.

Franchising was the plan before the first film crashed and burned, with Lynch and star Kyle MacLachlan (playing Paul Atreides) set to shoot both Dune sequels back-to-back in 1986. Miniature spaceship models, costumes, and props from the first film were placed in storage by producer Dino De Laurentiis for use on these follow-ups, while the director hammered away on a Dune II script. “I wrote half a script for the second Dune. I really got into it because it wasn’t a big story,” he says in Lynch on Lynch, “more like a neighborhood story. It had some really cool things in it.”

During the two years I spent putting together my book A Masterpiece in Disarray: David Lynch’s Dune—An Oral History, I had no luck uncovering Lynch’s script for Dune II, despite Frank Herbert telling Prevue magazine in December 1984 that he possessed a copy and was advising Lynch on it. “Now that we speak the same ‘language,’ it’s much easier for both of us to make progress, especially with the screenplays,” Herbert told the publication. Then, in July 2023, within the Frank Herbert archives at California State University, Fullerton, I came across a slim folder with a sticky note declaring “Dune Messiah script revisions,” addressed to the second floor of VFX man Barry Nolan’s office in Burbank where Lynch supervised the final effects shoots and editing on Dune.

Inside the folder lay the stuff of fans’ dreams, never made public until now: 56 pages dated “January 2nd-through-9th, 1984,” matching Lynch’s “half a script” statement. Complete with penned annotations by Herbert, the Dune II script shows Lynch was still enthusiastic about the material, lending new significance to minor details in the ’84 film. He also cracked a way to tell the complex story of Herbert’s 1969 novel Dune Messiah, easily the least cinematic book in the series due to its emphasis on palace intrigue over action, along with the inner turmoil of a reluctant dictator (Paul Atreides) in place of a traditional hero’s journey. It may ring of sacrilege to some, but Lynch’s Dune II would have bested Herbert’s book—and been one hell of a movie.

While writing this piece I reached out to Lynch for comment, since his Dune II script had never been discussed in detail publicly. He stated, through an assistant, that he “sort of remembers writing something but doesn’t recall ever finishing it.” As Dune is “a failure in his eyes and not a particular time that he likes to think of or talk about,” he politely declined to speak to me.

The Lynch Touch

“I’m writing the script for Dune II. Dune II is totally Dune Messiah, with variations on the theme. … Dune Messiah is a very short book, and a lot of people don’t like it, but in there are some really nifty ideas. I’m real excited about that, and I think it could make a really good film. It starts 12 years later, and this creates a whole new set of problems. … It should have a different mood. … It should be 12 strange years later.” —David Lynch, Starburst #78 (January 1985)

Of the many differences between Dune Messiah in novel form and David Lynch’s script, the biggest lay in the opening pages, which detail what happens in the aftermath of the scene in the first Dune movie when the Harkonnens bombed the Atreides’ fortress in Arrakeen, the capitol of the desert planet Arrakis. In the hallway where Duncan Idaho (Richard Jordan) was shot in the head, his shielded dead body still floats on the floor, humming and sparking.

The Bene Tleilaxu make for deliciously strange villains, right up David Lynch’s alley. He lets loose with them in his script.

Dune Scholar Kara Kennedy

From out of the shadows emerges a familiar face: the Baron’s Doctor (Leonardo Cimino). Thought to be the only speaking part created specifically for Dune by Lynch, we learn this Doctor was actually Scytale, a shape-shifting “face dancer” crucial to the plot of Herbert’s second book. Going back to Dune ’84, you may not have noticed Cimino’s Doctor accompanied Baron Harkonnen during the Arrakeen attack. The Doc is absent after that, even as the Baron yells creepily, “Where’s my doctor?” That’s because Doc/Scytale absconded with Duncan’s body. This Easter egg is Lynchian world-building at its best.

Scytale’s 12-year odyssey reanimating “dead Duncan Idaho” into the ghola named Hayt on the nightmarish Bene Tleilax world (mentioned by Paul in Dune) constitutes the entire opening 10 minutes of the script. Lynch calls the planet Tleilax “a dark metal world with canals of steaming chemicals and acids.” Those canals, Lynch writes, are lined with “dead pink small test tube animals.” Initiating Dune II with a focus on Scytale foregrounds him to primary antagonist, unlike Herbert’s book where myriad conspirators work against Paul.

“Lynch’s favorite set during production of Dune was Giedi Prime, with machinery and flesh alterations fitting his artistic sensibilities,” says Mark Bennett, founder of the DuneInfo website, after reading the unearthed script. “For Messiah, Lynch decided that Bene Tleilax could be co-opted for his style, since it isn’t described in the novel.”

The planet itself is run by the Tleilaxu, sadists whose mere language (“Bino-theethwid, axlotl”) signals their bizarre nature, giving Kenneth McMillan’s grotesque Baron from the ‘84 Dune a run for his money. Here’s a particularly surreal/Lynchian passage, where Scytale sings a haunting “boogie tune”:

Scytale’s friends are laughing and wildly rolling marbles under their hands as they watch Scytale sing through eighteen mouths in eighteen heads strung together with flesh that is like a flabby hose. The heads are singing all over the pink room. One man opens his mouth and a swarm of tiny people stream out singing accompaniment to Scytale. Another man releases a floating dog which explodes in mid-air causing everyone to get small and lost in the fibers of the beautiful carpet. Though small they all continue to laugh, a laughter which is now extremely high in pitch. Scytale (now with only one head) crawls up a wall laughing hysterically.

“The Bene Tleilaxu make for deliciously strange villains, right up Lynch’s alley,” says Dune scholar Kara Kennedy (Frank Herbert’s Dune: A Critical Companion), who I also provided with a copy of the screenplay. “He lets loose with them in his script.”

Scytale breathes new life into Idaho over many years in a place described as “a beautiful hot pink room with violet light which is a blend of living room and rubbery surgical room.”

“You can imagine Frank Herbert and Dino De Laurentiis wondering if Lynch was writing a sequel to Eraserhead!” says Bennett.

Scytale’s visage “face-dances” into Idaho at several points, which may have necessitated early morphing technology before it was developed for Ron Howard’s 1988 film Willow.

“I recall Richard Jordan as Duncan Idaho agreed to a smaller presence in Dune for the promise of the breakout character in Dune Messiah and beyond,” Stilgar actor Everett McGill told me after reading the uncovered script. “I’m not surprised David begins this story with a full-on reanimation of dead Duncan Idaho among all the fun and jarring Lynchian images.”

Link to the rest at Wired

PG has always read and enjoyed a lot of science fiction.

However, as he was reading the OP, a question popped into his likely addled mind: “Are hard-core science fiction fans the strangest of all genre-fiction fan groups?”

Do other genres have their versions of a Dune Scholar like one person quoted in the OP is described?

Feel free to comment or name stranger fan groups according to your fancy.

PG went to the doctor this morning and was diagnosed with an eye infection.

He has a couple of new prescriptions in addition to the old gang and his eyes are very bloodshot, which is likely to frighten his offspring if they see him in this condition. He is following medical advice and applying antibiotic drops to his eyes every couple of hours.

The eye infection is in addition to a chest infection which has removed any aspirations to become a party boy in the next few weeks.

From The Wall Street Journal:

I love a good contrarian pop-culture take. The Beatles have too many fans. Monty Python is painfully unfunny. Chefs are not artists. But recasting the notorious Col. Tom Parker as a good guy is about as strong a current as you can swim against. The infamous talent manager has been blamed for ruining Elvis Presley and robbing from him for years. In “Elvis and the Colonel,” Parker’s former protégé takes on the monumental task of redeeming one of the more despised figures in Americana.

Greg McDonald grew up in the entertainment business with Parker’s guidance, later becoming a talent manager for the singer Ricky Nelson. He eventually took over Parker’s All Star Shows production company and was the president of the label that signed the Backstreet Boys and ’NSync. He also owns Parker’s likeness and image.

In attempting to redeem his late mentor, Mr. McDonald nails a necessary prerequisite. As he recounts Parker’s biography, he convincingly rehabilitates the colonel’s reputation into a 20th-century American success story—the stowaway immigrant from the Netherlands who became a hobo, an Army enlistee, a carny and, ultimately, an entertainment mogul. It’s impossible to dislike or disrespect Mr. McDonald’s Parker.

The early years of Presley and Parker’s relationship read here like a standard Elvis biography. Parker honed his game promoting the country stars Eddy Arnold and Hank Snow. Presley outgrew his local management under a Memphis disc jockey and wanted more. When Parker attended a 1954 Presley show in Texarkana, Texas, he saw the audience “going crazy, especially the young girls,” he later recounted to Mr. McDonald. “They were screaming and fainting and throwing their clothes on stage.” Parker realized that Snow could never amount to as much. Once Presley and the colonel got going, the hits and dollars piled up. Mr. McDonald covers the RCA deal, Presley’s enlistment and film career. The duo’s charitable works, including support for the USS Arizona memorial, receive deserved, refreshed attention.

It isn’t until Mr. McDonald’s appearance, nearly halfway through the book, that we begin to learn some quality inside stuff. As a teenager, Mr. McDonald worked as an air-conditioning mechanic, with access to many celebrities’ houses in Palm Springs, Calif. One day he stumbled upon Presley and a female companion sunbathing by a pool. Young Greg and Presley immediately hit it off, and the boy was soon introduced to Parker. The colonel and his wife also took a liking to him, and before long Greg was a regular at the Parker household. His relationship with the colonel took a surprising turn when Parker practically adopted Greg and saw to his education. It’s a major plot point supporting the colonel-as-good-guy narrative.

In the ensuing years, Mr. McDonald worked hard to remain close to this potent pairing. He became a driver for Parker, and sometimes Presley, with a front-row seat to many memorable moments. He dishes on how a miscommunication between the singer and his entourage resulted in Presley missing a dinner invitation from Marilyn Monroe.

Mr. McDonald also recounts the only meeting held between Presley and the Fab Four, with more detail and richer quotes about that 1965 Bel Air encounter than I’ve seen anywhere else. It’s a vivid scene, right down to the details of Presley’s attire and the Inspector Clouseau accent affected by a nervous John Lennon. After a few moments of stoned-Beatles awkwardness, Presley threatened to go to bed if John, Paul, Ringo and George were just going to sit there staring. “I thought we might sit and talk and jam a little,” Presley said. This cut through the haze and a session for the ages broke out, with Presley playing bass on the Beatles’ “I Feel Fine.”

Mr. McDonald is at his best when he’s looking at the world as the talent promoter he eventually becomes. Observing the increasingly restless Presley of the mid-1960s—an era in his career most fans don’t care about—Mr. McDonald notes: “Becoming famous is one thing; avoiding becoming infamous, entirely another.” Where we see Presley practically sleepwalking through cheesy movies, Parker sensed constant danger. “Once you’re at the top, you’re walking across a lagoon on the backs of alligators,” Mr. McDonald writes. “The press loves a fall as much it loves as a rise, and they’re happy to send you in either direction.” Parker’s job wasn’t simply to fatten the golden goose.

As for the belief that Parker robbed Presley, think of it this way: He didn’t have to. Their relationship was unprecedented and up to them to negotiate. And if Presley sensed the shelf life of rock ’n’ roll expiring with the ’50s and sought to pivot to movies and soundtracks, who could blame him? In hindsight we may feel deprived of a precious decade of great music, but the films were a wise career move at the time. So what if the results of “Fun in Acapulco” (1963), “Harum Scarum” (1965), “Clambake” (1967) and others—it really is a long, horrid list—pale in comparison to the singer’s smoking early songs: “Mystery Train,” “Heartbreak Hotel” and “Don’t Be Cruel.” Presley, according to Mr. McDonald, had become addicted to his lifestyle and needed the money. Parker worked tirelessly to deliver.

Who got ripped off in early rock ’n’ roll? Virtually everyone. It’s easy to sympathize with Big Mama Thornton and Little Richard for recording “Hound Dog” and “Tutti Frutti” for a ¼ cent a sale, but the Beatles received a similar deal. A guitarist for Manfred Mann once told me that the five members of his group split a penny for every dollar earned on hits such as “Do Wah Diddy Diddy.” You know who didn’t get ripped off? Elvis the movie star. For each of his films, Presley earned a six-figure salary and a profit share of nearly 50%. Unheard of. Parker got 50% of Elvis, but he earned it, Mr. McDonald tells us. “What history and countless other books on Elvis Presley don’t tell you is that Colonel Parker was the first megamanager who made forays into today’s multimedia world of music, film, television, publishing, and Las Vegas-style entertainment.”

Link to the rest at The Wall Street Journal.