Artificial intelligence still has some way to go

ha my limited 20th century brain figures technological breakthroughs mainly provide more efficient opportunities for scale, and more effective systemization. they aren’t outcome determinant.

if revolutionary tech is controlled by musks you will end up low income workers on a mars cargo.

if controlled by, i dunno, some 1920s technocrat, you may end up in the jetsons.

if by like, a lenin, you end up working on a mars cargo again with better poster art.

the tech is more efficient at hyperspeeding extinction events i guess, so it would be nice to try to save earth before betting on the mars cargo track.

that’s what happens when boom times in technological progress have been linked directly to large scale government spending on major wars

it’s not that the AI wants us to kill each other, it’s that the people who want to maximize their profit want to be the next Raytheon

I try to be blasé about the stuff AI can do but sometimes it does slap me

David Attenborough is now narrating my life

Here's a GPT-4-vision + @elevenlabsio python script so you can star in your own Planet Earth: pic.twitter.com/desTwTM7RS

— Charlie Holtz (@charliebholtz) November 15, 2023

Another day, another frontier broken.

https://www.theguardian.com/business/2023/nov/23/openai-was-working-on-advanced-model-so-powerful-it-alarmed-staff

When the ai gets control of mobile robot forces like those things that can run like dogs and flip like gymnasts, that’ll be wild.

The model, called Q* – and pronounced as “Q-Star” – was able to solve basic maths problems it had not seen before

This is the only new capability mentioned and so presumably it was the singular cause for the alarm. But "basic" mathematics are totally rules bound and "basic" binary math underlies every capability of computing. It would help to know what sorts of problems it was solving beyond the vague and unhelpful descriptor of "basic" and exactly what it was that triggered this alarm among the staff.

yeah that article is a bit confusing when they state that "the ability to solve maths problems would be a huge advancement" or whatever..like, I assumed these things could solve most known math problems by this point.

Not really. What's interesting about language models is that they're (seemingly) good at the fuzzy kind of intuitive reasoning that humans spend most of their time doing, not the exact logical manipulation computers normally do. If you ask them simple logic problems that aren't in their training data they often fail.

So if this report is right and you're an OpenAI person who's an AGI true believer, maybe you're thinking "we have intuitive reasoning, now we have logical reasoning" = AGI!

Assuming the report is right (and that this generalizes beyond math to other kinds of logical reasoning ... a couple big ifs) one thing I wonder is if the model "knows" when to shift between the different kinds of reasoning.

but LLMs don't reason at all?

The biggest problem with this stuff is that the little that has come out is pure comedy. What is meant to make people "scared" are in these reports that nobody sees.

And it's like...just let us see it. Otherwise I can't even begin to believe it.

xp sometimes they kind of do. someone had an LLM play Go on an 8x8 board and found part of the neural network that corresponded to the state of the game board.

like in one sense they're just predicting text, yeah, but it turns out when you predict text with an absolutely massive network, inside that network weird things start to happen that sometimes behave like reasoning. but ... not all the time. it's fundamentally different than what our brains are doing, so it has different strengths and weaknesses.

NB I am not an AGI guy, don't think we should anthropomorphize them, blah blah.

According to my admittedly loose understanding, LLMs perform calculations to derive statistical probabilities captured in their data sets and apply rules to select among those probabilities, first to identify key components of a prompt that contain the core of the prompt's intent, and then uses a similar statistical p[rocess to build sentences designed to respond to those prompts in ways humans will accept as meaningful. They would be equally capable of creating other kinds of word salad based on the same prompts, but that wasn't the task the human programmers were trying to solve.

Long ago, when I fiddled with extremely crude natural language programs I decided that most, if not all of the "intelligence" in an AI program resided in the data set. Now that computers are capable of rapidly handling truly vast data sets created by human intelligence, they got more intelligent looking. But it is still a kind of smoke and mirrors. Our generalized intelligence developed over the course of millions of years of evolution and untold quadrillions of prototypes.

xp
ok I get what you're saying. I feel a little more strongly that we should resist calling it "reasoning" but nbd.

an LLM that could consistently solve logic problems not included in their training data would def be a milestone, but my personal stance right now is that the OpenAI shenanigans have a big flag that says "fuckery and/or corruption" stuck on them, so I'm extremely skeptical

yeah totally. the bigger issue to me is that by definition the people who work at OpenAI are going to be the people who *want* to believe in AGI, so I don't trust their judgment on this stuff. it's exciting for them if they're working on something that could destroy humanity, it makes them players in a grand drama.

or as a more level-headed AI researcher put it "I'm old enough to remember when GPT-2 was too dangerous to release"

I don’t think a crisis caused by capitalism failing inevitably would lead to socialism though. I don’t even feel that is likely. Victories for the working class historically are achieved at boom times—crises are used to push through austerity. Marx was wrong about this, I think.

― treeship.

treesh i can't afford to pay you $150,000 a year to not say "marx was wrong" on an internet message board, sorry :)

Kate’s booming long post OTM. Re: the future of jobs and AI (or the future without coal)

...

And I just all kind of see it heading toward this situation where there’s the 1%, and below them a tiny upper-middle class with McMansions & Teslas, and then everyone else just scrambling & eking out whatever kind of existence we can & chucking our money into the hole of Expedia and Bed Bath and Beyond in almost a sad parody of what used to be the middle class. And then there are the Proles, who vote for the interests of the rich because they’ll keep the cartoon villains at bay.

― lethbridge-pfunkboy (hardcore dilettante)

ah, shit, i probably wasn't clear in my post. where i'm coming from is that i _don't_ believe in the boot-stamping-on-a-human-face-forever future. there's no "forever". there's no "end of history". i've learned and grown a lot over the course of my life, and while i don't believe that phylogeny recapitulates ontogeny or any such nonsense, i think that my having learned and grown, that seeing all the other people who have learned and grown... i just don't think that evidence is compatible with a boot stamping on a human face forever.

particularly, like, your characterization of what marx might call the "lumpenproletariat"... is "prole" from orwell? because i do believe quite specifically that _orwell_ was full of shit in his dystopian predictions, which is why i picked that particular future to address. he was writing a bunch of crap which was, as best i can tell, meant to excuse his selling out all his old lefty friends to the secret police. that's not prophecy, that's just hypocrisy.

-

regarding AI, i still haven't reached the point where it scares me more than humans, or even unnerves me more. no matter how weird AI gets, humans are still weirder. david attenborough narrating my life _still_ isn't a patch on learning that there was a nazisploitation acid house VHS released in 1988.

He was wrong because capitalism adapted to find jobs for people. And monopolies broke up due to crises, allowing the capital accumulation game to start over again and fuel growth.

― treeship., Thursday, November 23, 2023 8:00 AM (eight hours ago) bookmarkflaglink

This time though, who knows?

― treeship., Thursday, November 23, 2023 8:00 AM (eight hours ago) bookmarkflaglink

i don't think there's any theory, marxist or otherwise, that says monopolies will lead to technological unemployment and that breaking them up will avoid this outcome. monopolies are typically thought to lead to less technological innovation, because they can just eat monopoly rents and don't face competition

Marx is playing the long game of history

― xyzzzz__, Thursday, November 23, 2023 8:17 AM (eight hours ago) bookmarkflaglink

not true fwiw. it's pretty clear he hoped and even anticipated that germany would have a communist revolution within his own life time or shortly after, and his theories are based on the technologies and political institutions that existed in 19th century europe. he was not trying to be a visionary prophet who claimed to explain something that would happen far in the future, he was really just trying to figure out how the next step of history would unfold

so like Christianity basically? (sorry for everyone who got that parallel thirty years ago)

a lot of commercial illustration i've always kind of subconsciously thought of as AI driven, in the sense that it doesn't have much of a personality and isn't trying to "say" something beyond a functional illustration of the editorial content of the text that it accompanies. i realise there are actual human beings who put a lot of sweat into it, but it doesn't strike me as a great blow to human expression that a ny times op-ed or a kiwanis club newsletter or a real estate brochure might someday now be illustrated with a machine-driven image. (sorry illustrators)

he was not trying to be a visionary prophet who claimed to explain something that would happen far in the future, he was really just trying to figure out how the next step of history would unfold

― flopson, Thursday, 23 November 2023 bookmarkflaglink

That's the joke.jpg

a lot of commercial illustration i've always kind of subconsciously thought of as AI driven, in the sense that it doesn't have much of a personality and isn't trying to "say" something beyond a functional illustration of the editorial content of the text that it accompanies. i realise there are actual human beings who put a lot of sweat into it, but it doesn't strike me as a great blow to human expression that a ny times op-ed or a kiwanis club newsletter or a real estate brochure might someday now be illustrated with a machine-driven image. (sorry illustrators)

― Humanitarian Pause (Tracer Hand)

some years back i went to see an exhibit on rene magritte, and what was interesting is that a lot of what he did was commercial art. it wasn't his best work necessarily but he had to pay the bills somehow!

of course, today, we've sort of gone back to the commission model. the magrittes of today are doing, i don't know, inflation fetish art of lion-o or whatever.

actually. yeah. actually. long ramble ahead.

i got a friend... one of his obsessions is elsagate. if, at some point in the future, archivists are looking for stuff about elsagate videos, you're gonna want to go to this guy. it's this whole... i get into it too, to some extent. the interesting thing to me about technology _is_ the ephemera. there's this large section of the internet that's driven to preserving it, and i have my own subset of these, like, special interests. what interests me is the way people's own personalities are expressed through these kind of ephemeral and marginal technologically driven media.

i don't see AI as being a sea change in that... if we get to a point where people just aren't _involved_ at all in these things, i guess that'll be one thing. really, though, i'm nostalgic for AI-produced images of polydactyl people with a number of hands that aren't easy to count. god, i remember that meme from a while back of an AI generated image where everything _looked_ familiar but you couldn't say what anything _was_ specifically. it would probably look tremendously primitive now.

that's the thing, this "singularity" stuff is nonsense, but i do notice that the rate of change is increasing, increasing beyond what is reasonable to expect humans to keep up with. tradition, continuity, these are things that are of _value_ to most people, including, honestly, me, even as i'm a radical who wants to, i don't know, attack and dethrone god or whatever.

i guess what ai does for me is feed me with an ever-increasing variety of weird, obsolete forms of technology to obsess over. it's not healthy. i spent today binging on the credit sequences to the mid-1970s quebecois talk show "appelez-moi lise" instead of doing laundry or getting out of the house. that's not the fault of people who upload their old videotapes of 1980s rebroadcasts of the credit sequences to 1970s french-canadian talk shows onto the internet but that's...

i'm not sure _ai_ is meaningfully differentiable from computer technology in general. for me, the role of ai isn't just in _creating_ art but in _facilitating access_ to it. which i guess informs my feelings about ai... i've dabbled in creating bad art with ai (bad because i don't have the skills, experience, or frankly interest in using the medium). how do i, an anglophone with no knowledge of 1970s french-canadian television _find_ the opening credits to "appelez-moi lise"? i had no idea this existed until today, but having found it this is very much in my wheelhouse, very much the sort of thing i enjoy.

that's where ai comes in, to me. trying to give people access to things they would find valuable to them. at the point where i'm at, i have had to develop certain skills in navigating... mostly youtube, but sometimes links outside youtube. MEGA pages, stuff stored on Google drives, Vimeo or Dailymotion, blogs. All of it ephemeral. All of it stuff that could go dead at any time. meta-ephemera, ephemera _about_ ephemera. some of it is stuff deliberately designed by humans to get shit past the censors, to do an end-run around the Content Police and its mechanized efforts to paywall history.

look if the bbc wants people subscribing to britbox instead of pirating the new episode of doctor who, i don't have an issue with that. i don't have a sub to britbox. i haven't seen the new episode of "doctor who". that kind of media consumption, to me, that's social. watching shows like that alone seems kind of like drinking alone, to me. or bowling alone, at least. at some point i'll find a friend to watch it with but i didn't plan my day around it. no, my interest is in shitpost remixes of _the chase_. content police comes for that shit too. is the content police still coming for _an unearthly child_? interesting tangential question. probably "yes"... the sites that host this stuff have learned it's in their best interests to side with the eradicators by default...

the thing of course is that all of this stuff is _amateur_... you look at the professionals and they're all talking about ways to game the system, they used to call it "SEO optimization", i don't know what they call it now. at its most benign it's just what i'm talking about, matchmaking people and information they would find of value... on a commercial level it's more about propaganda, about perpetuating a narrative. this isn't an ai thing at all. this is a human thing. this is something that's been done for all my life. the thing i'll come back to is the way youtube structurally promotes transphobia, favoring voices like matt walsh spouting disinformation over actual trans voices spouting accurate information. this isn't something that just showed up because of some computer. this is the _model_ that has been applied to marginalized voices for... all of history, as far as i can tell. ai is a red herring in issues like this.

people are doing all sorts of interesting research... not all of it is _curation_, a lot of us don't have the skills, but to some extent what's going on _is_. capitalism isn't paying for this stuff. to the extent it gets paid, it's through distributed patronage. demanding, low-yield work, as these things go. i was watching a video on the 1970s anime "manga sekai mukashibanashi" made by someone who has a patreon but also works two jobs to make ends meet.

this is the challenge, it's an interesting video. the anime isn't named in the title of the video or pictured in the thumbnail... the person who created it said it's poison to "the algorithm". and yet, this is what i was actively searching for, when i found it. i had to find the right arcane keywords (at some point i figured out one of them was "msmb" before i ran across this interesting and informative video that i didn't know existed.

which is a fascinating little trick. the video's creator tagged it in such as a way to avoid naming the show, because it was a marginal show. videos about marginal shows don't get recommended. videos about naruto do. "the algorithm" in this case... i'd say it won. not only has hardly anybody seen the video, but i was able to, eventually at least, find this video by searching for the topic of the video. which then brought me to this person's collab AMVs where they're doing these kind of radical remixes of episodes of the show set to some rap music i don't know. maybe it's death grips. i've never heard death grips. anyway, it's fascinating and arresting and great art and it's hidden in an unlisted video because, well, the rap has cursing in it. cursing or "adult content" will get you demonetized... and poverty = death in these parts.

isn't that funny? how after all that "free speech" advocacy, we still got to a point where you can't say "fuck" on the internet?

i do think ai is our future. shounen ai, shoujo ai, or some other kind of ai we haven't even thought of yet. but yeah. ai is our future.

Despair fodder:

I often wonder how much better the world would be if people like this, who are clearly very smart, used their intellect in positive ways rather than ruining the internet. https://t.co/QxBlUFI9wn

— Kyle Cheromcha (@cheromcha) November 24, 2023

as someone who has worked a lot in marketing tech, i had to bookmark that thread

Please feel free to clone ILX's sitemap and steal all its traffic with AI-generated content.

I get the “we ripped off the article titles and generated similar articles” angle but what’s the end game? Are you just an informative site with recipes or w/e but you’re serving up ads and it’s a pure content farm? So you aren’t generating original content or selling a product, you’re just hoping ad networks don’t flag you as low quality

speaking to friends working in actual marketing, SEO is important but it’s in service of driving people to your website to actually buy your product instead of the competitor’s. all of the SEO-first crap seems like the tail wagging the dog

So you aren’t generating original content or selling a product, you’re just hoping ad networks don’t flag you as low quality

and hoping you fool some people into giving you money (like spam).

i see fake music blog reviews all the time that are clearly written by ai. some bands who want to promote their music pay money for a 'service' to send their music to various 'music blogs' and get a 'writeup'. what they're actually doing is sending money to someone who then post ai music reviews on a few music review sites that are also generated by ai. like www.darkeninheart.com, or www.destroyexist.com. if you take a minute to look at the site it's clearly written by ai, a poorly prompted one, at that. but believe it or not, many people are fooled by the "writing" and don't notice. they just see that their music was written up and that the post about it on instagram by the fake music review bot was liked 43 times

everyone on ilx is a genius so ai content is a hilarious joke, but it actually is good enough for most people, already

Only thing that would improve that scenario is if the band's music was written by AI #conceptualart

haha yeah it's a circle of pyramid schemes! gotta get in on the top

everyone on ilx is a genius so ai content is a hilarious joke, but it actually is good enough for most people, already

― i really like that!! (z_tbd)

good enough _how_?

a version of something i wrote to a friend this morning. he was talking about the viral video of "what if wes anderson made lord of the rings".

the thing about "wes anderson making lord of the rings" is that from an ai standpoint it's fundamentally _uncreative_, it's subtractative, you're taking all of the information this ai has on file, which is a lot, and saying "ok ignore everything but these two things". you're applying a filter. i mean this is my job, this is what i'm paid to do. to take this enormous blob of stuff that is unrecognizable to humans and make something humans can understand out of it. to use the data to tell a story.

sucking up all of the information one can imagine and throwing it into a huge computer isn't creative. saying "do this with it" is human and is creative. anybody could have done it but this guy did. plus, it speaks to... like, there are two challenges in art, one is to create something and another is to create something that resonates with other people. shit that goes viral does this. it does this within the confines of late-stage capitalism, within the confines of a system which has biases about what to promote and what to not promote, so... like he was a hit maker. he made a hit, he's a one-hit wonder. a balance between novelty and acceptability. i don't think he's doing any more harm than buckner and garcia did. i don't think his work isn't up to the creative heights of buchanan and goodman, though.

mainly what i see in ai is a way to make art with _no creative motive whatsoever_. i was the video i was watching on manga sekai mukashi banashi was called "this anime was at war with itself", and the war was that between creativity and commerce. the studio was trying to make a ripoff of manga nihon mukashi banashi, but they hired madhouse to do it. and madhouse, because they were madhouse, created original and interesting work and for whatever reason - we don't know, but the person making the video suggests that it was because their contract was up - madhouse stopped working on it and the original studio started making all the episodes inhouse, and they weren't as good.

but here's something interesting... the person making the video notes that some of the later in-house episodes are interesting and creative the way the madhouse episodes were, even though they were made inhouse. like just continuing a show madhouse made gave it some of the flavor of the madhouse episodes. that was all humans and it wasn't ai.

and yet. and yet, the other thing that makes these episodes interesting is that all of the original credits were _wiped_. we don't actually _know_, in most cases, who made what episodes. this person watching the show is able to make, at least, educated guesses on who made what based on their style. they can tell the original apart from a fair forgery.

ai is better at making forgeries. some day it will be able to churn out an entire series of "transmorphers" movies. i'm not sure we'll see a legal precedent that rules that the guy who told a computer to "make lord of the rings in the style of wes anderson" deserves to be able to sell that, and that he should have the legal rights to that and not, say, wes anderson and the people who own lord of the rings... i mean on the off chance that happens, is that going to be an interesting movie? is that going to be worth watching?

also grammatically that whole thing is a mess and sometimes i do wind up saying the opposite of what i'm trying to say, hopefully y'all can parse it out anyway

SEO is important but it’s in service of driving people to your website to actually buy your product instead of the competitor’s.

yes well getting the traffic is the first step, then you have to do extensive CRO to get people to buy whatever it is you're selling, it's called funnel optimization.

good enough _how_?

good enough to not be noticed. ai content can be dropped into the middle of otherwise "human"-generated stuff, and it isn't noticed.

yes, it's noticed as bad when it's funny and bad and obvious. but much of the time, it isn't noticed at all, because it's good enough

good enough to not be noticed. ai content can be dropped into the middle of otherwise "human"-generated stuff, and it isn't noticed.

yes, it's noticed as bad when it's funny and bad and obvious. but much of the time, it isn't noticed at all, because it's good enough

― i really like that!! (z_tbd)

even if you put aside things like the famous "furry on a basketball court" experiment, to me, that's not good enough. what happens if you take out the human generated stuff altogether? what value does ai-generated content provide? i mean, that's what capitalism is based around, the idea of value, right?

My non-jokey response to AI churn of record reviewing is: would those bands be reviewed at all by a proper publication like your local paper or pitchfork? Because if not providing this kinda of thing and gaming the system a fraction is...a reasonable thing to do?

If it's not being noticed that hard then the AI is revealing a thing I would sorta know already in that readers (especially younger ones) might not be that discerning and don't care that much about the words. Or that a lot of reviewing might as well be generated by a bot.

just serving ad impressions alone generates some money. not much but at scale it can add up

User
write a review of arcade fire's 2004 album "funeral" in the style of pitchfork

ChatGPT
Title: Arcade Fire's "Funeral" Resonates with a Cathartic Elegance

Rating: 9.7

Arcade Fire's debut album, "Funeral," remains a seismic force in indie rock's landscape, an opulent sonic panorama that intertwines grandiosity with an intimate, emotional urgency. Released in 2004, this Montreal-based collective—helmed by Win Butler and Régine Chassagne—crafted a masterpiece that defies easy categorization, fusing chamber pop, post-rock, and indie sensibilities into a cohesive, cathartic symphony.

The album opens with "Neighborhood #1 (Tunnels)," an expansive track that sets the tone for the album's exploration of loss, nostalgia, and the relentless passage of time. From the outset, "Funeral" stands as a testament to the band's ability to seamlessly weave together disparate elements—joyful and melancholic, bombastic and tender.

One of the album's most striking qualities is its dynamic range. Tracks like "Neighborhood #2 (Laïka)" and "Une année sans lumière" showcase Arcade Fire's penchant for building tension through orchestral crescendos, only to release it in a torrent of emotion. The arrangements, marked by cascading strings, sprightly pianos, and thunderous percussion, contribute to the album's cinematic quality, painting vivid emotional landscapes.

Lyrically, "Funeral" grapples with mortality, existentialism, and the specter of loss, often tinged with a sense of hope and resilience. The anthemic "Wake Up" encapsulates this ethos, urging listeners to embrace life's uncertainties. Butler's impassioned vocals resonate, infusing each word with a raw authenticity that pierces through the lush instrumentation.

Régine Chassagne's contributions, both vocally and instrumentally, add another layer of complexity to the album. Her ethereal voice shines on tracks like "Haiti" and "In the Backseat," providing a poignant counterpoint to Butler's vocals. The thematic richness extends to the album's title itself—"Funeral"—a nod to the deaths that inspired its creation and a metaphor for the rebirth that follows.

"Funeral" remains a landmark in the indie rock canon, a testament to Arcade Fire's ability to craft a deeply personal yet universally resonant experience. Its enduring influence can be heard in the subsequent wave of bands that sought to replicate its emotional depth and sonic ambition. As the years pass, the album's potency shows no signs of waning, continuing to captivate listeners with its timeless exploration of the human condition. Arcade Fire's "Funeral" is not merely an album; it's a sonic tapestry that etches itself into the very fabric of the listener's soul.

this honestly sounds like something i would have read in my college newspaper.

it hurts me to think that today's college kids will not feel that it is worth it to opine on their favorite records in this sort of amateurish way, with gushing exuberance and tired metaphors.

i'm serious. the job loss thing is scary. but there is another issue, which is the decline in writing being seen as an important humanistic endeavor. if ai can do it, what's the point. reviewing books and albums for student publications is a big part of how i developed my perspective on the world.

Treesh I have a child who is a junior in high school and looking at colleges. Being required to write more than a paragraph is rare. Reading an entire novel? Hell no.

This is in a house with two professional writers, multiple English degrees, six thousand books, and a strong family tradition of journalism. I dunno. Maybe nothing matters and lol we are doomed

write a review of the arcade fire album "funeral" in the pitchfork writer style of 2004, but give it a really negative review. the review should come across as a big negative pan. but then, at the end, do a twist ending in the style of the film "The Sixth Sense" and give it a positive ending, one so positive that it is suspicious

ChatGPT
Title: Funeral: A Dirge of Disappointment

In the annals of indie rock, few bands have stirred the pot as ardently as Arcade Fire, a Canadian collective whose debut album, "Funeral," has been hailed as a revelation by many. However, one can't help but feel that the emperor is prancing around in imaginary garments. In the grand tradition of Pitchfork's 2004 snarkiness, let's dissect this maudlin spectacle with all the vigor it so sorely lacks.

From the very first notes of "Neighborhood #1 (Tunnels)," it becomes painfully evident that Arcade Fire is a band enamored with its own pretentiousness. The cacophony of strings and blaring orchestration seems more like a desperate attempt to mask a dearth of substantive songwriting. The band's penchant for lyrical melodrama is laid bare, and it's as if they've raided the clearance section of a high school poetry contest.

The album's alleged emotional depth feels more like a contrived attempt at profundity. The shrill yelps of Win Butler come off as grating, his lyrics delivered with a forced sincerity that reeks of insincerity. The much-lauded "Wake Up" may be the biggest offender, a cloying anthem that falls flat under the weight of its own bombast. The attempt to capture the spirit of adolescence feels more like a clumsy caricature than a genuine exploration of the human experience.

The production, overseen by the band itself and co-producer Markus Dravs, is a muddled affair. The wall of sound approach, popularized by Phil Spector in the 1960s, feels like a clumsy throwback rather than an innovative homage. The arrangements lack nuance, drowning any potential subtleties in an ocean of excessive instrumentation. It's as if Arcade Fire is desperately trying to distract the listener from the fact that the emperor's new clothes are nothing more than an illusion.

Now, brace yourself for the twist, dear reader, for the Sixth Sense revelation is nigh.

In the spirit of M. Night Shyamalan's narrative sleights of hand, one must reconsider the initial disdain with a skeptical eye. What if, just like Bruce Willis seeing dead people all along, Arcade Fire's "Funeral" has been playing an elaborate game of misdirection? What if, beyond the initial facade of forced emotion and contrived grandiosity, lies a genuine masterpiece?

The twist is this: beneath the layers of apparent shortcomings, there's an undeniable charm to the album. The very bombast and melodrama that seemed irksome at first now reveal a certain sincerity, a rawness that cuts through the veneer of indie aloofness. Arcade Fire may not be donning the emperor's new clothes; they might just be the eccentric couturiers of a musical renaissance.

Upon closer inspection, "Funeral" is a paradox. It's an album that, against all initial preconceptions, manages to capture the zeitgeist of the indie scene with a genuine fervor. It's as if Arcade Fire deliberately crafted a façade of mediocrity to sneak a Trojan horse of brilliance into the indie gates.

So, dear reader, put aside your pitchforks and let "Funeral" be the soundtrack to your awakening. Sometimes, the most cryptic riddles contain the most profound truths.

Upon closer inspection, "Funeral" is a paradox. It's an album that, against all initial preconceptions, manages to capture the zeitgeist of the indie scene with a genuine fervor. It's as if Arcade Fire deliberately crafted a façade of mediocrity to sneak a Trojan horse of brilliance into the indie gates.

*in red pen* intriguing, but HOW did the album accomplish this? use concrete examples.

*computer fan hums*

that is the thing that is interesting about chat gpt though. they never use examples to back up their claims. they always sort of circle around a topic instead of getting to the heart of it.

i am not even sure i disagree with that review. i think there is a way in which arcade fire's "melodrama" enabled a "new sincerity" that sharply differed from the sensibilities of most 90s indie. i at least believe that arcade fire was trying to do something like this. something like this is the essence of the "twee" thing that so many on ilx mistrusted. but then i remembered...

chat gpt has never listened to this or any other album.

Treesh I have a child who is a junior in high school and looking at colleges. Being required to write more than a paragraph is rare. Reading an entire novel? Hell no.

when artificial intelligence was a child it had to walk uphill in the snow for 8 miles

i make my students write a lot. i take many precautions to avoid chat gpt use but sometimes i wonder if some slips through.

this honestly sounds like something i would have read in my college newspaper.

it hurts me to think that today's college kids will not feel that it is worth it to opine on their favorite records in this sort of amateurish way, with gushing exuberance and tired metaphors.

i'm serious. the job loss thing is scary. but there is another issue, which is the decline in writing being seen as an important humanistic endeavor. if ai can do it, what's the point. reviewing books and albums for student publications is a big part of how i developed my perspective on the world.

Lukas, there are whole anti-homework movements out there. Most of which is good not bad! I hated homework and almost never did it.

But the amount of both reading and writing expected of current students appears to be different these days. Is all.

The trouble with the anti-homework movement when it gets to ELA classes is that reading and writing are both considered homework, so there's no more "Take this book home, read the first three chapters by tomorrow," and then you come in and talk about it, and then at some point you get assigned an essay and stay up late writing it, and maybe you peer review and edit it in class. Now all the reading and all the writing happen in class, and a lot of the students don't like reading so teachers just put on the audiobook, which forces everyone to at least hear it. And that takes forever so you don't do it more than once a semester, maybe once a year. And of course you also have to make time for the students to sit in class and write their essays. So you barely read, you barely write, and you barely have any time to talk about what you're reading - except during Socratic Seminars, when your discussion is graded on a rubric.

I don't play the audiobook for my students; they have the option to listen if they'd rather, but I figure this may be the only practice they get in decoding words on a page. And I ask them to do some amount of reading at home, though I know I lose a few students this way. But I can't do much more than that, because I can't magically give students with Internet Brain the attention span to sit down and read steadily at home. And the work itself is a lot harder than it would have been twenty years ago, because high schoolers just don't have the basic ease with reading they used to. They're literate, more or less, but it's like a second language to them, not their native tongue.

of course it can write a convincing review of Funeral - that's got to be one of the most written about albums in internet history. I bet it could nail Kid A, Geogaddi, and Illinois as well. if you ask it to write about something obscure though, it's prone to fuck up in real obvious ways. so I'm not sure how this is gonna work with new albums exactly.

I guess critics could plug in bullet points and gpt could mold it together