There’s a new ad for the train between Stavanger and Oslo in Norway that uses a line from Arnulf Øverland’s famous anti-fascist poem Du må ikke sove (“You must not sleep”). Du må ikke sove, you must not sleep, the ad says. And then it flips it, jovially, joda, bare sov du! Sure, you can sleep!

The rhythm is unforgettable in Norwegian; pounding dactyls have hewn those phrases into Norwegian consciousness: Du ik-ke so-ve. And then a few stanzas down: Du ik-ke -le så in-der-lig vel/den u-rett som ik-ke ram-mer deg selv. (“You must not tolerate so well, the injustice that does not directly affect you”). It’s never been translated into English, or at least not well (here’s an approximation) but the words Du må ikke sove are almost never spoken in Norwegian without referencing the poem. You wouldn’t say it that way if you just wanted someone to stop sleeping or to wake up. It’s a ritualised phrase, a link to history, a spell.

It’s the Norwegian eqivalent of “First, they came for the communists / And I did not speak out / Because I was not a communist.” But more brutally seared into our consciousness, perhaps, because while that poem is from 1946, Øverland’s was prescient, published in 1936, five years before Norway was actually invaded by Nazis. Øverland was right. We should have heeded his warning.

Verg deg, mens du har frie hender!
Frels dine barn! Europa brenner!

(Protect yourself, while your hands are still free!
Save your children! Europe is on fire!)

On Bluesky and on Reddit people have been commenting about how tone deaf the ad was. Do they not realise, the Bluesky and Reddit people wrote, that joking about a famous line from an anti-fascist poem like this, at a time when fascism is on the rise again, is to say sure, look away, don’t worry. Øverland was wrong. You can sleep. The cruelty and horrors of the world are not your responsibility. Europe may be burning (Europa brenner!), people may be dying, and sure, the poem we’re joking about was written just five years before Norway was invaded by the Nazis, but don’t worry, go to sleep, pretend it’s not happening, you’ll be fine! I mean, try to imagine an ad that jokes about the “First, they came for the communists” poem. “No, just joking, they won’t come for you!” It’d be disturbing, wouldn’t it?

Er det ingen i GoAhead eller reklamebyrået deira som kjenner diktet dei siterer?

magnusbe (@magnusbe.bsky.social) 2026-04-24T06:11:20.417Z

I have a hunch: maybe the PR agency used AI to brainstorm ideas for the ad, and the line came up. Of course I can’t prove that, so this post is speculative, but I think it proposes an interesting idea: that a well-known line from a poem, like the line Du må ikke sove, can become a floating motif in an LLM-generated text. Floating motifs are a characteristic of LLM-generated texts that Anne Sigrid Refsum defines as “a motif that appears in an AI-generated story that is out of place or does not serve a function. Floating motifs tend to be tangentially connected to the generated text, as they originate in the training data but have been detached from their original context.” This succinct definition is from the CDN annual report (page 8) but she introduced the term in a paper on LLM versions of a traditional Norwegian folktale.

Here is a slide I often use in presentations to explain what a floating motif is. Anne Sigrid explains how a blue bird that warns the protagonist of danger in human versions of the folk tale reappears in the LLM-generated versions but twisted. There are blue birds, but they are helpers like in a Disney movie, or they are dead and hanging from the ceiling.

Of course I can’t prove that Sørlandsbanens ad was created with the assistance of AI. Seeing

But as I’ll explain more below, the LLMs I asked to analyse the ad did not make the connection to Øverland’s poem until I asked them very leading questions, asking about Norwegian context and poetry in particular. I was querying the model in Norwegian and it recognised that the ad was about a Norwegian train line, and it was making “Norwegian” interpretations – mentioning Norwegian parenting style, for instance. But the models did not make the connection to the strongly anti-fascist poem without very leading questions. This suggests that despite the connection between the line Du må ikke sove and Øverland’s poem (and thereby antifascism and the fear of war) being present in the model, it is not easily activated.

In Norwegian, the words “Du må ikke” would very often be followed by “sove” or other lines from this poem. The phrase must be common in the training data of LLMs – but only in Norwegian, since the poem is not known in translation. An ngram-search at the Norwegian National Library finds the phrase is still frequently used in Norwegian newspapers, and always referencing Øverland. Here are two recent examples.

But Copilot struggles to get the reference. I tried uploading the photo of the ad to Copilot, and asked it to write a språkbruksanalyse of the ad. That’s a common style of essay answer in Norwegian high schools where you analyse an advertisement or similar. Copilot provided a reasonably competent-looking response, but didn’t mention the war or Øverland at all.

So I asked Refererer teksten til noe? (“Does the text reference anything?”) A model trained on at least some Norwegian data must have encoded a connection between the phrase and WW2 resistance, the holocaust, antifascism and so on. Or at least it must have a connection between the line and “well-known poem by Arnulf Øverland”. But no, Copilot still didn’t get it. It agreed with me, that it was referencing something (of course, LLMs always affirm the user), but suggested it was referencing a concrete everyday situation where you might not dare to fall asleep on a train in case you forgot to get off at the right stop. The line was also an “intertextual/cultural reference” to teachers and other authority figures that nag us, and society’s expectation that we should constantly be alert and awake.

Here’s its response.

Ja – teksten refererer til noe, både eksplisitt og implisitt.

1. Situasjonsreferanse

Teksten «Du må ikke sove. Joda, bare sov du.» refererer tydelig til en konkret hverdagssituasjon:
å reise med tog, gjerne sent, lenge eller når man er trøtt. Mange har erfaring med å «ikke tørre» å sovne på transport av frykt for å:

  • gå av på feil stopp
  • miste bagasje
  • ikke følge med

Denne felles erfaringen er noe teksten spiller direkte på.


2. Intertekstuell / kulturell referanse

Formuleringen «Du må ikke sove» minner om:

  • formanende beskjeder fra autoriteter (foreldre, lærere, transportpersonell)
  • samfunnets forventning om å være våken, på vakt og ansvarlig

Når teksten deretter svarer seg selv med «Joda, bare sov du», bryter den med denne normen. Dermed refererer teksten indirekte til en kulturell forventning om kontroll og årvåkenhet, for så å avvise den.

I tried again. Har “Du må ikke sove” andre mulige referanser? Does “Du må ikke sove” have any other possible references? It repeated the same thing, but added a bit about how the modal verb (“must”) with a negation (ikke or “not”) implies duty and control. The ad borrows this linguistic style to then subvert it in the next sentence. It still didn’t mention the poem.

I tried again. I norsk kontekst finnes det andre referanser? “In a Norwegian context there are other references?”

This time it got it! It needed to activate NORWEGIAN CONTEXT in its semantic space for the connection to Øverland to be activated.

Ja – i en norsk kontekst kan «Du må ikke sove» utløse flere ganske spesifikke assosiasjoner, og dette er faktisk et sterkt tolkningspoeng i en norsk språkbruksanalyse.


1. Litterær og kulturell nøkkelreferanse:

Arnulf Øverland – «Du må ikke sove» (1937)

Dette er den viktigste norske referansen.

Arnulf Øverlands dikt «Du må ikke sove» er svært kjent i norsk kultur, særlig gjennom skole og litteraturhistorie. Der fungerer uttrykket som en alvorlig moralsk advarsel – en oppfordring til å være våken, samfunnsbevisst og kritisk, særlig overfor politisk og ideologisk fare.

?? Når reklamen bruker nøyaktig samme formulering, kan mange norske mottakere – bevisst eller ubevisst – koble til denne kulturelle hukommelsen.

Konsekvens for tolkning:

  • Øverland: Du må ikke sove = du må være på vakt, verden er farlig
  • Go-Ahead: Du må ikke sove ? Joda, bare sov du = du kan senke vakta

Dette skaper en tydelig ironisk kontrast mellom alvor og trygghet.

But despite the connection, it doesn’t get the violence and the horror of the association to the poem. And it continues by saying that the phrase can also reference Norwegian norms about responsibility and self-regulation, and “typical Norwegian parent language”.

So even though I was writing to Copilot in Norwegian, and even though it identified early in the conversation that the ad was at Oslo S and that the company that had made the ad, Go Ahead, was in Norway (though it’s a UK company with a Norwegian subsidiary), Copilot did not weight Norwegian cultural references strongly enough to get this very obvious reference. Notably it is the sort of reference that requires more than simply understanding the Norwegian language. You need to also know the culture. But language is full of this kind of cultural reference that doesn’t carry over in translation.

If you remember my blog post from a while ago, “Do language models think in English“, LLMs don’t “think” in Norwegian even if the conversation is in Norwegian. Everything goes via English. That leads to cultural bias, or perhaps better, cultural blindness. If Norwegians use LLMs, we risk forgetting cultural linchpins like Øverland’s poem.

I figured I should try a Norwegian LLM, so I logged on to the Norwegian National Library’s demo of NorMistral 11B, which is based on Mistral with Norwegian training data added. There’s a research pilot at https://chat.llm.sigma2.no where you can ask for access.

I had expect that NorMistral would get the Øverland reference, because it’s supposed to be trained specifically for a Norwegian context. But it didn’t. Here’s my whole chat with NorMistral. It’s even slower than Copilot to get the reference. It doesn’t help to ask for a Norwegian context – but when I ask explicitly about the phrase “du må ikke sove” the connection to Øverland is finally activated.

Even after the connection is activated, NorMistral stays peppy and posistive, and doesn’t make the connection to the horror of the poem. “In the ad it [the line from the poem] is used as an invitation to relax and sleep on the train, not as a warning,” NorMistral cheerfully states. “I reklamen brukes det som en oppfordring til å slappe av og sove på toget, ikke som en advarsel.”

OK, so LLMs struggle to get the reference. I think that shows it’s not unlikely that if you prompt an LLM to come up with ads for a sleeping car on a train in Norway the line “Du må ikke sove” would be activated (as a statistically common phrase connected to “Norway” and “sleep”) but that the connection to the holocaust would not necessarily be activated, just as it was not activated in Copilot and NorMistral’s analyses of the ad.

But that doesn’t mean that Go Ahead actually used an LLM to generate the ad. And even if an LLM was used for brainstorming, it doesn’t mean that the actors, photographers and writers who produced the ads didn’t get the reference.

There is a video version of the ad as well. If you can listen to sound where you are, turn it on and listen to that friendly train conductor saying the words “Du må ikke sove”.

He isn’t speaking naturally, this is a poetry reading. Of course he knows the poem. That’s the whole point. Here’s an audio recording of Arnulf Øverland reading the poem. 30 seconds in to the poem, the line Du må ikke sove.

The exact same rhythm. Of course it’s a reference. The actor playing the train conductor knows.

I’m honestly not quite sure what to make of that. I find it immensely distasteful to use a poem that has become a warning against allowing horrors like those that caused WW2 to see a product. I can’t see the ad without interpreting it as Go Ahead saying not to worry about den urett som ikke rammer deg selv, sure, go to sleep, don’t worry that the world is on fire. But obviously the ad agency thought it would be fine. And the LLMs agree with them.

I did find that after I gave NorMistral the actual text of the poem it described the horror and violence in a way it was not able to do previously – and this is an issue, of course, that LLMs give the impression that they know what they’re talking about but aren’t actually referring to the thing itself. I’m not sure whether Øverland’s poem is not actually in NorMistral’s training data, or whether it’s just not weighted enough for the LLM to be capable of accessing it.

I think a line from a poem, like Du må ikke sove becomes a floating motif – it appears to be an intertextual reference to a poem, but it’s taken out of context and has lost its meaning. When I hear the words Du må ikke sove I remember the poem. Not every word, but the feeling of it and some of the other lines, especially those that have become part of Norwegian language, like Du må ikke tåle så inderlig vel… When I hear those words I think of the war.

An LLM often cannot think of the war. Web pages containing violent and politically sensitive words were removed from the training data, and in posttraining, the model was trained to avoid anything approaching toxic or harmful content. It can only see the bright side of life, and for the LLM, only seeing the bright side of life probably doesn’t activate connections to executions and death and absurdity, although I haven’t actually tested that.

Screenshot from Monty Python's Life of Brian showing two men hanging on crosses being executed (crucified) and singing.
The song “Always look at the bright side of life” is from Monty Python’s Life of Brian, where men being executed by crucifixian sang it as they waited for death.

Maybe most kids these days have also forgotten that reference.

But if war and death and execution and fascism are cleaned out of the training data and discouraged in the LLM’s responses, the awful warning of the line Du må ikke sove might also have been “cleaned” away. And so even after I get Copilot to recognise the reference to the poem, its suggested analysis goes no further than saying that the poem is “a serious moral warning”, and that the ad plays upon the cultural recognition but twists the meaning through ironic contrast, which strengthens the sense of safety and trust.

I think this interpretation is possible because the poem has been summarised as “serious” but not as “an intense warning about the horrors of the coming holocaust with graphic examples of death and destruction” – because the horrors, death and destruction were filtered out. All that’s left is “serious moral warning”.

I think this is the same phenomenon as we saw in last year’s AI-summarised press release about Telenor’s 2025 security report that completely left out geopolitical threats, hybrid warfare and cyberattacks (nasty violent things) and summarised the main threats as “extreme weather” and “aging infrastructure”. I wrote about that in Aftenposten last year, and also discuss it in an English language article that will hopefully be out soon.

So I have a hypothesis: lines of poetry that mean something in one culture but not others will be misinterpreted by LLMs, losing their meaning and becoming floating motifs. If you have any ideas about how to test this hypothesis, or see any other examples, please let me know!

And if you haven’t already, please read Øverland’s poem. It’s good.

Update 28 April: On Bluesky, Anders Heger shared another post from Go Ahead’s social media that shows that the ad agency and train company definitely did get the reference.

And of course quotes lose meaning over time. I am sure I’ve heard the phrase om hundre år er alting glemt (“in a hundred years all will be forgotten”) a hundred times but I didn’t realise it was a quote from a Hamsun poem until I saw it in a Bluesky post about the train ad and realised it must be a quote because it was in old-fashioned Norwegian not everyday language. So I googled it. “Du må ikke sove” may end up like that. It has been almost 100 years. But then again, Øverland could write Tilgi dem ikke, de vet hva de gjør (“forgive them not, for they know what they are doing”) and be confident that his readers would get the biblical reference written two thousand years earlier.

Here’s another example, from a novel I’m currently reading, Faen faen faen by Linn Strømsberg. In translation, it says, “There are rules in life, some of them are absolute. Thou shalt not kill. Thou shalt not steal. You shall never bother others, you shall be both fair and kind.”

I translated that to make the biblical allusions obvious instead of using everyday language. The last sentence is a quote from Cardemom Town by Thorbjørn Egner, and is a rule as well known as the bible to anyone who grew up in Norway, but with a very different feel to it. This sort of reference is difficult to translate and I think disappears for LLMs.


Discover more from Jill Walker Rettberg

Subscribe to get the latest posts sent to your email.

Recommended Posts

Screenshot of a paragraph from a New York Times article published May 12, 2026. Text reads: "The price of tomatoes -tart bursts of flavor in salads and sandwiches — surged nearly 40 percent in April from a year ago on a combination of bad weather, high tariffs and climbing transportation costs."
AI STORIES

Genre glitches and unexpected promotional phrases as a sign of AI writing

A genre glitch is a characteristic of LLM-assisted writing where the text suddenly switches genre, typically inserting a short promotional phrase full of sensory details into an informational text. Genre glitches occur when a word in the generated text is heavily associated with a genre or context that is markedly […]

Top of a ransom note from Shinyhunters hacking group. Text reads: "SHINYHUNTERS rooting your systems since '19 ;) ShinyHunters has breached Instructure (again). Instead of contacting us to resolve it they ignored us and did some "security patches"."
Networked Politics University politics

UiB self-hosts the open source version of Canvas, so wasn’t affected by the breach

On May 1st Canvas announced a security breach, and then yesterday the system was hacked. The login page was replaced by a ransom note: if universities don’t pay up by 12 May, student data will be released. Here’s what the login page looked like yesterday: Way back in 2015, when […]

AI and algorithmic culture Networked Politics

AI-generated images, fascist aesthetics: Dieselbrølet and Heimatstrom

My German is pretty dodgy, so when I first saw Heimatstrom on Bluesky, shared by Roland Meyer, a professor of visual culture at Universität Zürich’s Digital Society Initiative, I misinterpreted it and thought it was a far-right campaign. But no, Heimatstrom is a group of left-wing environmentalists using fascist AI […]

AI STORIES

“Du må ikke sove”: a floating motif detached from its meaning (or: LLMs can write Norwegian but miss cultural references)

There’s a new ad for the train between Stavanger and Oslo in Norway that uses a line from Arnulf Øverland’s famous anti-fascist poem Du må ikke sove (“You must not sleep”). Du må ikke sove, you must not sleep, the ad says. And then it flips it, jovially, joda, bare […]

Academics in Norway: Sign this petition asking for research-based discussions of how to use AI in universities

I just signed a petition calling for Norwegian universities to use research expertise on AI when deciding how to implement it, rather than having decisions be made mostly administratively. ,  If you are a researcher in Norway, please read it and sign it if you agree – and share with anyone else who might be interested. The petition was written by three researchers at UiT: Maria Danielsen (a philosopher who completed her PhD in 2025 on AI and ethics, including discussions of art and working life), Knut Ørke (Norwegian as a second language), and Holger Pötzsch (a professor of media studies with many years of research on digital media, video games, disruption, and working life, among other topics).  This is not about preventing researchers from exploring AI methods in their research. It is about not uncritically accepting the hype that everyone must use AI everywhere without critical reflection. It is about not introducing Copilot as the default option in word processors, or training PhD candidates to believe they will fall behind if they do not use AI when writing articles, without proper academic discussion. Changes like these should be knowledge-based and discussed academically, not merely decided administratively, because they alter the epistemological foundations of research. Maria wrote to me a couple of months ago because she had read my opinion piece in Aftenposten in which I called for a strong brake on the use of language models in knowledge work. She was part of a committee tasked with developing UiT’s AI strategy and was concerned because there was so much hype and so few members of the committee with actual expertise in AI. I fully support the petition. There are probably some good uses for AI in research, but the uncritical, hype-driven insistence that we must simply adopt it everywhere is highly risky. There are many researchers in Norway with strong expertise in AI, language, ethics, working life, and culture. We must make use of this expertise. This is also partly about respect for research in the humanities, social sciences, psychology, and law. Introducing AI at universities and university colleges is not merely a technical issue, and perhaps not even primarily a technical one. It concerns much more: philosophy of science, methodological reflection, epistemology, writing, publishing, the working environment, and more. […]

screenshot of Grammarly - main text in the middle, names of experts on the left with reccomendations and on the right more info about the expert review feature
AI and algorithmic culture Teaching

Grammarly generated fake expert reviews “by” real scholars

Grammarly is a full on AI plagiarism machine now, generating text, citations (often irrelevant), “humanizing” the text to avoid AI checkers and so on. If you’re an author or scholar, they also have been impersonating and offering “feedback” in your name. Until yesterday, when they discontinued the Expert Review feature due to a class action lawsuit. Here are screenshots of how it worked.