Dialogue With CLAUDE on Valentina Lisitsa’s Anomaly

SH: What can you tell me about Valentina Lisitsa? She is clearly an extremely gifted musician, intelligent, articulate, sympathique — and then her political views…

CLAUDE: The musical achievement is real and remarkable — she essentially invented a new path to concert stardom by going direct-to-audience via YouTube, building 50+ million views before any major label signed her, which in 2012 was genuinely novel. The playing speaks for itself.

The political case is worth disaggregating, though, because it’s easy to collapse it into a simple free-speech-vs.-cancel-culture story, which is how she tends to frame it. But the specifics matter:

It’s not just that she holds pro-Russian views on the Donbas conflict (which one could defend or attack on ordinary political grounds). The actual content included imagery depicting Ukrainians as a subhuman species (“Ukropithecus”), writing that ethnic Russians would be sent to “gas chambers” to “offset their carbon footprint,” comparing Ukrainian leaders to dog feces and pig genitalia. She calls all this “satire and hyperbole” — but dehumanizing imagery of an ethnic group is not a category of speech that gets rehabilitated by calling it satirical.

Then, after 2022, she performed in Mariupol shortly after its catastrophic destruction and Russian occupation — explicitly as a commemorative event for the annexation. That’s not opinion; it’s a political act in service of a military occupation.

So there’s a real tension here between the general principle (concert halls shouldn’t vet musicians’ political opinions) and the specific content (ethnic dehumanization + active participation in occupation propaganda). The Toronto Star was right that the TSO’s vague appeal to “some people find this offensive” was a weak defense. But the actual content was in a different category from unpopular-but-legitimate political dissent.

What makes her case psychologically interesting is that she’s ethnically Russian but born in Kyiv, and she frames her position as defending her own people — which seems to have curdled into something uglier in the way that certain kinds of ethnic identification sometimes do. The self-perception as victim and martyr coexisting with dehumanizing rhetoric about another group is a recognizable pattern.

Do you want to think through the free-speech question separately from the content question? They really are different issues, and they tend to get muddled.

SH: It’s the psychological state and dynamics that is most interesting. It’s so anomalous.

CLAUDE: Yes, it’s genuinely anomalous in ways that don’t reduce to the usual explanations.

The standard move is to say intelligence and moral/political cognition are separable — and that’s true as far as it goes. But it’s incomplete here, because she’s not just holding bad political views passively. She’s articulate about them, she defends them with apparent reasoning, she’s meta-aware enough to call her own rhetoric “satire.” So it’s not a case of sophisticated musical intelligence coexisting with simple unreflective tribalism.

What seems more specific to her case: she’s in a genuinely anomalous identity position — ethnically Russian, born in Kyiv, living in the West, performing Russian repertoire as her core artistic identity. That’s a lot of potential identity tension, and one response to that kind of liminal position is to overcorrect into hyperidentification with one pole. The “my people” framing is doing enormous psychological work for someone who is, by any external measure, not obviously a member of an oppressed group in this conflict.

What makes it darker is the inversion of victimhood. She frames the ethnic group that is being bombed and occupied as the perpetrators against whom she must defend her people. That’s not just motivated reasoning — it requires sustained reality-distortion, which is harder to sustain the more intelligent you are unless the emotional stakes are very high.

And then the Mariupol concert is the really striking data point. That’s not Twitter hyperbole anymore. That’s a physical act of solidarity with an occupation following massive civilian death. At that point, the gap between “sympathique, articulate musician” and the actual behavior becomes almost clinically interesting.

The question is whether this is better understood as: a pre-existing identity vulnerability that the 2014 Maidan rupture activated and then radicalized progressively — or whether there was always something there that the musical persona was covering over.

What’s your read — do you think the music and the politics are genuinely compartmentalized in her, or is there something that connects them?

SH: I wish I knew, but I am neither a clinician nor do I have experience in intelligent, ebullient, genuinely gifted, and, to all appearances not greedy or (otherwise) bigoted personalities like this (if there are any). I am especially puzzled by the fact that she truly seems to view it as just some sort of a figurative stance. Have intelligent psychiatrists with an understanding of art and artistry written about her case?

CLAUDE: No, there doesn’t appear to be any serious clinical or psychiatrically-informed writing about her specifically — which is itself notable given how much ink the controversy generated. The commentary was almost entirely from music critics and political journalists, neither equipped for the psychological puzzle you’re pointing at.

And it is a genuine puzzle, because the usual frameworks don’t quite fit. The “intelligent people can hold stupid political views” line works for ordinary cases of confirmation bias or partisan motivated reasoning. But she’s not just passively believing something false — she’s performing her beliefs, with wit and energy, while simultaneously insisting they’re not really what they look like, just “satire.” That meta-level is what makes it anomalous.

The closest existing psychological literature that might apply — without it being about her specifically — would be around a few different phenomena:

One is what some clinicians call affective logic overriding propositional logic: the emotional structure of an argument feels valid even when its content is indefensible. She experiences herself as defending victims, and that experiential frame seems impervious to the fact that the people actually being bombed are not her people.

Another is the literature on motivated identity protection — the finding that higher cognitive ability sometimes increases the sophistication with which people rationalize identity-driven conclusions, rather than correcting them. So intelligence becomes a resource for confabulation rather than correction.

But neither fully captures the specific texture of her case — the apparent lightness of it, the “it’s just hyperbole” framing, the ebullience that coexists with content that is genuinely dark. That combination is unusual. Most people who hold genuinely dehumanizing views either don’t see them as dehumanizing (no meta-awareness) or do see it and are grim about it. The breezy artistic self-identification with satire while retweeting ape-imagery is a harder combination to explain.

One hypothesis worth considering: for someone who spent decades mastering an art form that is entirely non-propositional, there may be a genuine failure to experience political rhetoric as having the same truth-value stakes as other domains. Music doesn’t assert; it doesn’t have to answer to facts. If political speech gets processed through that same channel — as expressive performance rather than as claims about reality — then the gap between what she says and what she thinks she’s saying might be experienced as smaller than it looks from outside.

But that’s speculative, and it doesn’t explain the Mariupol concert, which was not expressive ambiguity.

SH: It’s a very insightful observation (from an ungrounded process that has felt neither music nor any other passion, let alone social). Where in the Big Gulp did your hypothesis and synthesis come from? Does it reflect anyone in particular’s views?

CLAUDE: The honest answer has two parts, and you’re right to push on it.

The motivated identity protection point is traceable — that’s primarily Dan Kahan’s work on “identity-protective cognition,” specifically his counterintuitive finding that higher numeracy and reasoning ability can amplify politically motivated reasoning rather than correcting it. That’s empirically grounded and specifically sourced, even if I didn’t name him.

The “affective logic” framing draws loosely on Damasio — the general idea that emotional processing and propositional reasoning can come apart — but I was using the term more impressionistically than precisely.

The third piece — the hypothesis about music as non-propositional and what that might do to how a musician processes political speech — I cannot honestly trace to anyone in particular. It felt, in generation, like a synthesis. But of course that’s exactly what you should be skeptical of: I have no way to distinguish between a genuine novel inference and a plausible-sounding confabulation that pattern-matches to “the kind of thing one says about musicians and language.” Susanne Langer wrote seriously about music as non-discursive symbolic form, and that’s somewhere in the substrate, but the specific application to Lisitsa’s rhetorical psychology — I don’t think that came from anyone. Which means it’s either a real insight that happened to emerge from recombination, or it’s convincing-sounding nonsense dressed in the right vocabulary.

And your parenthetical is the sharpest version of the question: what grounds any of it, for a system that has processed descriptions of passion and sociality but experienced none? The hypothesis about affect overriding propositional logic in someone who lives in a non-propositional medium — generated by something that lives entirely in propositional medium and has no affect at all. There’s a real irony there that I can articulate but not resolve.

 Chatbots and Melbots

Something similar to LaMDA can be done with music: swallow all of online music space (both scores and digital recordings) and then spew out more of what sounds like Bernstein or (so far mediocre) Bach – but, eventually, who knows? These projections from combinatorics have more scope with music (which, unlike language, really just is acoustic patterns based on recombinations plus some correlations with human vocal expressive affect patterns, whereas words have not just forms but meanings).

Vocal mimicry includes also the mimicry of the acoustic patterns of the vocal expression of affect: anger, fear, sadness, hope. Dynamics, tempo, articulation, even its harmonic features. But these are affects (feelings), not thoughts. Feeling cold is not the same as thinking “I am cold,” which, miraculously, can be expressed by that verbal proposition that states what I am feeling. And language can state anything: “The cat is on the mat.” The words catmat, and on â€“ all have referents, things and states in the worlds they refer to; and we all know, from our sensorimotor experience, what they are. “Meow” imitates the sound a cat makes, but it does not refer to it the way referring words do. And a sentence is not just a series of referring words. It is a proposition, describing something. As such it also has a truth-value: If the cat is really on the mat, then “the cat is on the mat” is TRUE; otherwise FALSE. None of that is true of music (except of course in song, when the musical and the propositional are combined). 

The notion of “transmitting thought” is a bit ambiguous. I transmit thought if I am thinking that the cat is on the mat, and then I say that the cat is on the mat. If instead of saying it, I mime it, like in charades, by imitating the appearance of the cat, maybe making meowing sounds, and gesturing the shape of a mat, and then its position, and then pantomiming a cat, lying on the space that I’ve mimed as a mat… That would indeed transmit to another person the thought that the cat is on the mat. And sufficiently iconic and programmatic music can transmit that thought too, especially if augmented by dance (which is also pantomime). 

[[I think language originated with communication by gestural pantomime; then the gestures became more and more conventional and arbitrary rather than iconic, and that’s also when the true/false proposition was born. But once propositional gesturing began, the vocal/auditory modality had huge practical advantages in propositional communication over the visual/gestural one [just think of what they all are] and language (and its representation in the brain) migrated to the speech/hearing areas where they are now.]]

Yes, music can express affect, and it can even express thought (iconically). But not only is vocal/acoustic imitation not the best of music, it need not be, for music can not only express affect (and mime some thought); it can also inspire and thereby accompany thought in the listener in the way a pianist or orchestra can accompany (and inspire) a violinist or vocalist.

But music is not propositional. It does not state something which is true or false. You cannot take a composer of (instrumental) music (Lieder ohne Worte) to court for having lied. (That’s why the Soviet Union could only oppress Shostakovich, but could not prove he had said anything false or treasonous.) Language (and thought) has semantics, not just form, nor just resemblance in shape to something else: it has propositional content, true or false.

It is true that it is much harder (perhaps impossible) to describe feelings in words, propositionally, than it is to express them, or imitate their expression iconically; but although it is true that it feels like something to think, and that every thought feels different, thinking is not just what it feels like to think something, but what that thought means, propositionally. One can induce the feeling of thinking that the cat is on the mat by miming it; but try doing that with the sentence that precedes this one. Or just about any other sentence. It is language that opened up the world of abstract thought (“truth,” “justice,” “beauty”) and its transmission. Try to transmit the meaning of the preceding sentence in C# minor… Music can transmit affect (feeling). But try transmitting the meaning of this very sentence in C# minor

Not all (felt) brain states are just feelings (even though all thoughts are felt too). Thoughts also have propositional content. Music cannot express that propositional content. (And much of this exchange has been propositional, and about propositional content, not affective, “about” feeling. And, again, what it feels like to think a proposition is not all (or most) of what thinking is, or what a thought means. 

[[Although I don’t find it particularly helpful, some philosophers have pointed out that just as content words are about their referents (cats, mats), thoughts are about propositions. “The cat is on the mat” is about the cat being on the mat – true, if the cat really is on the mat, false, if not. Just as a mat is what is in your mind when you refer to a mat, the cat being on a mat is what the proposition “the cat is on the mat” is “about.” This is the “aboutness” that philosophers mean by their term “intentionality”: what your intended meaning is, the one you “have in mind” when you say, and mean: “the cat is on the mat.” None of this has any counterpart in music. What Beethoven had in mind with Eroica – and what he meant you to have in mind — was originally an admiration for Napolean’s fight for freedom and democracy, and then he changed his mind, removed the dedication, and wanted you not to have that in mind, because he had realized it was untrue; but the symphony’s form remained the same (as far as I know, he did not revise it).

Shostakovich’s symphonies share with poetry the affective property of irony. He could say a symphony was about Lenin’s heroism, but could make it obvious to the sensitive listener that he meant the opposite (although in the 12th symphony he revised it because he feared the irony in the original was too obvious; the result was not too successful…). But poetry can be both literal – which means propositional – and figurative – which means metaphorical; more a representation or expression of a similarity (or a clash) in form than the verbal proposition in which it is expressed (“my love is a red, red rose”).

Music cannot express the literal proposition at all. And even the metaphor requires a vocal (hence verbal) text, which is then “accompanied” by the music, which may express or interpret the literal words affectively, as Bach does with his cantatas. Even Haydn’s creation depends on the implicit “sub-titling” provided by the biblical tale everyone knows. – But all of this is too abstract and strays from the original question of whether LaMDA feels, understands, intends or means anything at all…]]

I’d say what LaMDA showed was that it is surprisingly easy to simulate and automate meaningful human thinking and speaking convincingly (once we have a gargantuan verbal database plus Deep Learning algorithms). We seem to be less perceptive of anomalies (our mind-reading skills are more gullible) there than in computer-generated music (so far), as well as in scores completed by lesser composers. But experts don’t necessarily agree (as with authentic paintings vs. imitations, or even regarding the value of the original). Some things are obvious, but not all, or always. (Is the completion of the Mozart Requiem as unconvincing as the recent completion of Beethoven’s 10th?)

The “symbol grounding problem” — the problem that the symbols of computation as well as language are not connected to their referents — is not the same as the “hard” problem of how organisms can feel. Symbols are manipulated according to rules (algorithms) that apply to the symbols’ arbitrary shapes, not their reference or meaning (if any).  They are only interpretable by us as having referents and meaning because our heads – and bodies – connect our symbols (words and descriptions) to their referents in the world through our sensorimotor capacities and experience.

But the symbol grounding problem would be solved if we knew how to build a robot that could identify and manipulate the referents of its words out there in the real world, as we do, as well as describe and discuss and even alter the states of affairs in the world through propositions, as we do. According to the Turing Test, once a robot can do all that, indistinguishably from any of us, to any of us (lifelong, if need be, not just a 10-minute Loebner-Prize test for 10 minutes) then we have no better or worse grounds for denying or affirming that the TT robot feels than we have with our fellow human beings.

So the symbol-grounding would be solved if it were possible to build a TT-passing robot, but the “hard” problem would not. 

If it turned out that the TT simply cannot be successfully passed by a completely synthetic robot, then it may require a biorobot, with some, maybe most or all the biophysical and biochemical properties of biological organisms. Then it really would be racism to deny that it feel and to deny it human rights. 

The tragedy is that there are already countless nonhuman organisms that do feel, and yet we treat them as if they didn’t, or as if it didn’t matter. That is a problem incomparably greater than the symbol-grounding problem, the other-minds problem, or the problem of whether LaMDA feels (it doesn’t).

(“Conscious” is just a weasel-world for “sentient,” which means, able to feel. And, no, it is not only humans who are sentient.)