Monthly Archives: March 2026

The Savage Detectives VI: Reading with AI

Posted on by

As an experiment (and in preparation for an upcoming discussion of reading with AI, in the context of reading The Savage Detectives), I thought I would ask ChatGPT a few questions about the book, and see what it came up with. You can find the transcript of the resulting chat here: https://chatgpt.com/share/69c7928a-1ac0-832b-a01f-d991cb125134. Note that, because I am on the free tier of ChatGPT usage (i.e. I do not pay for it), I was only able to ask it ten questions. I may or may not continue the experiment later.

In sum, in some ways I was quite impressed with ChatGPT’s responses. On the whole, in general terms, it came up with some quite plausible readings… though I would emphasize that these are readings, plural, in that when pushed it would change its tune, albeit without fully acknowledging its shifts in interpretation. Moreover, the more detail I asked of it, the more it seemed likely to make mistakes, or to hallucinate. Again, while the overall sense it made of the book was often reasonable, and sometimes even revelatory, it still made several basic errors, and continued to make errors even when I tried to correct it. To put this another way (and drawing on Dan McQuillan’s description of AI as a “bullshit generator”; see also Harry Frankfurt’s On Bullshit): it came up with some quite high-quality bullshit that, as is generally the case with bullshit, had more than a kernel of plausibility or truth, but when pressed it tended to contradict itself or even to start to fall apart altogether.

Of course, in that (as we know) ChatGPT cannot “read” a text in anything like the conventional sense of reading, it draws its interpretation from what others have already said. So it was perhaps equally worrying that when, at the end of the chat, I asked it for its sources, its response was somewhat vague and evasive, even though at the same time it did provide some reasonable avenues for further study. But the worry is that, on taking up elements of ChatGPT’s proposed interpretation of Bolaño’s novel, I would be inadvertently plagiarizing the work of some other scholar, whose identity the AI bot could not help me to locate. At the end of the day, after all, LLM AI applications constitute the large-scale capture of intellectual, cognitive, and linguistic labor, whose origin they (necessarily) obfuscate.

It is possible that some of the less helpful or more worrisome aspects of the interaction with ChatGPT could be mitigated by better attention to the prompts I was giving it. For instance, if I continue this experiment in the future, I am tempted to ask it both for specific references to the text to support its claims, and for references to secondary criticism throughout the process. This might encourage a more grounded (and more transparent) interpretative process. Alternatively, rather than asking it directly about the text, one might begin at least with a review of the secondary literature on which it is drawing. That might keep it (and me, as a reader of ChatGPT’s “reading”) more honest.

Briefly to go through the questions I asked it…

First, I asked simply for it to provide me with the novel’s plot. It did a pretty good job of this, albeit that it had more to say about the book’s narrative structure than about the plot per se. The plot, after all, is not told linearly, and yet it kept to the order of the narration (the “discours” in Genette’s terms), rather than helping to reconstruct the story’s “histoire.” Having done this, it went further (beyond, indeed, what it had been asked) to advance some proposal’s as to the novel’s overall meaning. But in general, just about everything it said in response to this question was pretty much reasonable and defensible, and to some extent what I would even call insightful: the notion, for instance, that in the broadest terms the book’s plot involves a failed or futile search for origins, followed by “dispersal and disappearance.” Similarly, the summary of the novel’s themes as “literary ambition,” “friendship and exile,” and “the mythology of the avant-garde” makes sense, even if it is not necessarily the whole story–but then what summary is?

I did, however, feel it a little odd that this plot summary omitted the role of Amadeo Salvatierra, who is a recurrent voice in Part II of the novel, and who is important for the plot in that it is he who provides Ulises Lima and Arturo Belano with the information about Cesárea Tinajero that motivates and enables the road trip to Sonora around which the whole book revolves. So second, then, I asked ChatGPT about him…

In response, the chat implicitly recognized its error in omitting Salvatierra by saying that “he plays a crucial symbolic and structural role in The Savage Detectives” and that “he is actually the hinge between myth and history in the novel.” I was somewhat surprised, however, that ChatGPT should in fact spend more time on Salvatierra’s thematic or conceptual significance than on his function in the story. Indeed, the more that the chat edged towards concrete description, the more likely that it flirted with outright error. Hence, although its broad claims continued to be defensible and even perhaps enlightening (if not altogether unarguable), when for instance it states that “Amadeo possesses (or remembers) the only surviving work by Tinajero,” this is at best misleading: Amadeo very definitely possesses the surviving copy of the journal in which Tinajero’s poem is published. This is not simply a matter of memory: he shows it to Lima and Belano, so they can read it for themselves. More fundamentally, the chat is simply wrong with basic details when it claims that “Amadeo is an aging poet whom García Madero, Belano, and Lima visit early in the novel.” García Madero does not accompany Belano and Lima in this visit. And to say that it takes place “early in the novel” is again misleading: the account of the visit is threaded through Part II (and does not come to an end until page 588), although to be fair we can reasonably assume that it takes place at some point during the time period of Part I, the final weeks of 1975 as narrated by García Madero… but he never mentions the visit, presumably because he is most likely unaware of it.

I then asked for more information about the fates of the novel’s key characters.

ChatGPT’s response about García Madero was mostly to the point, albeit again somewhat misleading when it said that “García Madero is almost never mentioned” in Part II. In fact, he is mentioned precisely once… and it is surely important to describe that sole mention, not least because it comes when the so-called expert on visceral realism denies that anyone with that name had ever belonged to the movement.

What it had to say about Lupe was also OK, and even insightful. Again, it is notable (and surely somewhat surprising) how quick ChatGPT jumps to interpretation, rather than description. Perhaps this is because it is drawing above all on interpretations in the secondary criticism? But its conclusion about her fate is fair enough, albeit that this is surely a fate shared with (rather than opposed to that of) García Madero: “Not just absence from literary history, but from the kinds of stories that get told at all.” Eager to please, ChatGPT also offered to expand this discussion via a “compar[ison] to women in other Bolaño novels (like 2666), where this question of disappearance becomes even more central and more disturbing.” This in fact sounds like an interesting direction for further enquiry (and it’s perhaps intriguing that ChatGPT should offer to take me down that route), but here I was sticking with The Savage Detectives…

It was upon being asked about what ultimately happened to Lima and Belano that ChatGPT really started falling apart. Its top-level (i.e. “bullshit”) analysis remained for the most part quite impressive. For instance, the notion that these two characters become transformed into myth, and that there’s an irony in the failure of their mission to track down (what we find out is) the all too material and corporeal Cesárea in Part III, which may indeed lead to the conclusion that “to pursue literature absolutely may mean vanishing from it.” This was one of the ideas that ChatGPT gave me that I quite liked. And yet again, there was the sense that the chat was weak on description and detail. For example, when it says that “At one point, [Belano] travels to Africa and is possibly present during a conflict,” this is at best wishy-washy, almost as though it didn’t want to be pressed on what exactly happened. (In fact, after all, it’s not just “at one point” that Belano is in Africa, but this is where he is last seen. And more than being “possibly present during a conflict,” he is discovered in the thick of the Liberian Civil War.) If we were to anthropomorphize the machine (and it’s hard not to), we might say that this is the answer of a student who has only a hazy recollection of the text and wants to hedge their bets with their answers.

And indeed, when I pressed it further for answers, ChatGPT really started to struggle. Projecting its own confusion onto the text, for instance, the chat said that Belano “travels to Africa (often read as Liberia or Angola, though the novel is oblique).” In fact, however, there is nothing oblique about it: we are told quite clearly that he is in both Angola (Luanda, to be precise) and Liberia (a short distance from Monrovia). With Lima, things got still worse, and ChatGPT started to make multiple errors, even when I tried to zero in on them. 

It’s not necessarily worth detailing these errors, though it’s interesting, first, that the app’s tactic when pointed out its mistakes is to concede without fully giving ground. After I observed that it was wrong to a greater or lesser extent about the fates of both characters, it responded: “You’re right to push back—both of those ‘last sightings’ are more precise (and more interesting) than my previous answer suggested. Let me correct and sharpen things.” Yet it is not simply “more precise” to note that Lima is last seen not in Europe (as the chat had claimed) but in Mexico: it is right, where the chat was wrong. Second, moreover, as it made mistakes about the details it also started to make more obvious errors of general interpretation. For instance, in that Lima is located in Mexico City by our visceral realist expert at the end of Part II, it is simply not the case that “he simply fades out of the record altogether, more completely than anyone else in the novel.” There are plenty of other characters (most obviously perhaps, García Madero) who are more fully erased from the record… as indeed ChatGPT had already observed (when it said that, by contrast with Lima and Belano, he “undergoes a kind of negative initiation–into obscurity rather than legend”). The machine is by now contradicting itself, though unsurprisingly enough without acknowledging the fact.

After all, the chat’s tone remains consistent: it retains its aura of confident authority, so much more so that in reading it, one is tempted to doubt oneself… If I had not finished the novel only this week, I might easily have been more prepared to go along with its account, and to question my own memory rather than catching the app’s hallucinations.

For my next question (and by this time I was running out of my allocation), I returned to conceptual issues more than concrete details, in fact feeding it questions about length and endings that I had put to my students in class. Again I feel that its answers were illuminating even (if we can say this of a machine) “thoughtful.” These could definitely have been useful contributions to the discussion we had in class… I had a twinge of regret that perhaps I had missed a trick or two. Put it this way: if ChatGPT had been a student or (as a more likely scenario… and the worry of educators today) if a student had read out ChatGPT’s responses and presented them as their own, they would have been among the more insightful and valuable voices in class. I even like some of its turns of phrase. For instance, I like the notion that “If The Savage Detectives were shorter, it would be a story. If it were longer, it would be an archive.” This formulation is at the same time provocative and neat. Likewise with the notion that what we have here is “a myth of literature built out of fragments, ending exactly where it has to–at the moment when the search reveals that there was almost nothing to find.” In class, I said something similar, or at least similar enough–I put things differently, in that my suggestion was that at the end García Madero at least finds “nothing” in the more substantive sense that he touches and perhaps even falls (or jumps) into the void that lies beyond the “window” of representation. But still, there are some sentences and phrases in ChatGPT’s interpretation that I perhaps wish I had said or considered en route to my own conclusion, or which could usefully have been put to the students as alternative considerations. Could ChatGPT become a valued interlocutor in the classroom?

Yet by this point, seeing the chat’s weakness on points of concrete detail, to be honest I had started to lose faith or trust in ChatGPT altogether. Worse, this sense of distrust had become generalized: I no longer felt confident about either its reading or (to be even more honest) my own. After all, if my reading overlapped to some extent with that of a machine that had just shown some fundamental ignorance of basic issues of plot, then did that not cast shadow on my own interpretation, too?

So the last of my permitted questions was about its sources. I figured I would be better off looking to where ChatGPT was getting its “thoughts” than continuing to engage with the chat itself. Here, however, the app was both honest and unhelpful: “What I’ve given you is a synthesis drawn from general knowledge of The Savage Detectives, familiarity with Roberto Bolaño’s work, and the broad critical conversation around it.” In other words, the AI is drawing on a cloud of more or less established readings, without being able to pin down or lead me directly to who first established those readings, or what debates they had led to. It had, as it were, anonymized the critical conversation, obscuring the identities of those on whose intellectual labor it relies. To be fair, it did then provide some bibliographic references, and ended also with a note of caution that there are indeed “other strong readings that [it] ha[d]n’t foregrounded”… or even, if it were more truthful, mentioned at all. Its appropriation of intellectual labor, in other words, is selective and unequal. It’s notable, for instance, that it acknowledges that among the readings it had ignored were those inspired either by queer theory or by feminism. 

And perhaps it would have been helpful if at the very start it had stated upfront that what it was “giv[ing me] is not the interpretation, but a coherent, recognizable strand within Bolaño criticism.” Though of course it had done all it could to make this “recognizable strand” appear to be all its own work, appealing to our technological fetishism that attributes to the machine the qualities of agency and intellect that more properly belong to those who feed it… which is, in the end, you and me.

The Savage Detectives V: Was it Worth It?

Posted on by

And so, after some 450 pages, with Part III of The Savage Detectives we are back with García Madero, who along with Belano, Lima, and Belano is barreling along the highway in Quim Font’s borrowed Chevy Impala, heading north to Sonora, in search (we now know) of the forgotten avant-garde poet and original visceral realist, Cesárea Tinajero. An instant has passed, with the clock ticking over from 1975 to 1976. It turns out that the whole of Part II took place not only over the twenty years of Belano and Lima’s itinerant wanderings, nor even only over the eight to ten hours of late night drunken conversation with Amadeo Salvatierra, but in the seconds that separate the old year from the new.

If anything, the end of Part I and the beginning of Part III overlap, as García Madero explains in the his entry for January 1: “Today I realized that what I wrote yesterday, I really wrote today.” Time, indeed, seems to have gotten out of joint (almost as though we were back also in Auxilio Lacouture’s time-travelling bathroom reverie): “What I write today I’m really writing tomorrow, which more few will be today and yesterday, and also, in some sense, tomorrow: an invisible day” (591). By declaring this lapse of time to be insignificant or invisible, it is as though García Madero were unconsciously taking his revenge on his own invisibilization during the entirety of Part II.

For, after several hundred “interviews” in that “invisible day,” in conversation with over fifty informants, taking us from Mexico City to Paris, Austria, Israel, Africa, we are firmly back with García Madero as narrator, in a series of diary-style entries. Before long, we perhaps feel as claustrophobically ensconced with him, his thoughts, and his limited point of view, as if we were squished in the back seat of the car between him and Lupe.

Have we missed him? If we have, I suspect we very soon tire of him again, as he returns to the game (though no doubt he himself doesn’t see it as a game) with which he started the novel (way back on page four), of testing people on their knowledge of obscure rhetorical and poetic terms: “what is free verse? [. . .] a testrastich? [. . .] a sestina? [. . .] a hempiepes [. . .] a mimiambic [. . .] a zéjel” (591, 592). “Oh, Jesus,” says Lima (591). If this is García’s idea of fun, perhaps we’d rather he were banished from Part III, just as he was from Part II.

The others, however, get their own back (not that García Madero necessarily notices) by asking him in turn about his knowledge of street slang. Lupe starts turning the tables by asking “All right, Mr. Know-It-All, can you tell me what a prix is?” Belano instantly replies that it’s “a toke of weed,” but García Madero seems to be clueless. Similarly when he is asked for the definitions of “lurias” (“crazy”) “jincho” (“Indian”), “la grandiosa” (“jail”), and so on (597). We have a feeling that such terms are going to be of more use to this quartet than the arcane terminology of aesthetics that García Maduro has to offer them. 

For they are not only hunting a poet but also on the run from Alberto, Lupe’s enraged ex-pimp, and whatever reinforcement he has managed to bring with him. Phoning the Fonts back in Mexico City, they discover that, though they thought they had shaken him on the outskirts of the capital, he had gone back to Quim and got from him the name of their destination. The threat of violence hovers around their endeavours. Belano buys a knife. We may be in the last act rather than the first, but still the weapon is much like Chekhov’s famous gun: we know it will be wielded in anger sometime in the few pages that still lay ahead of us.

And so, behold, the book’s dénouement is indeed tragic–perhaps better, a tragicomedy of errors. In a dramatic confrontation on a dusty desert road, a confrontation ensues as Alberto and his policeman sidekick catch up with them now that Lima, Belano, et. al. have finally located the mythical (but ultimately, almost monstrously physical–visceral, if you like) Cesárea Tinajero. 

In a confused “blur” seen from García Madero’s limited perspective forever in the back seat (the only thing Tinajero ever says to him is “don’t move”), Lima and Belano end up killing both their aggressors and also Tinajero herself (641–42). García Madero overhears Belano telling Lima “that we’d fucked up, that we’d found Cesárea only to bring her death” (643). The two friends split from García Madero and Lupe, set to bury the bodies and head back down south. Perhaps it’s not now so far-fetched to think that their constant traveling, as documented in the novel’s Part II, is at least initially because they are on the run from the law–or, more likely still, from Arturo’s criminal associates if they ever got wind of why their buddy never returned from Sonora.

In the meantime: was it worth it? We can ask this question both of the book and also of the quest that has structured it. Lima and Belano get to meet and talk to Tinajero, but (seeing everything as we do from García Madero’s perspective), we have no idea what they may have said. Lupe, for now, has escaped her pursuers.

And García Madero’s final diary entries go from a list of placenames that presumably indicate ongoing peregrinations through remote towns in the desert north (“El Cuatro, Trincheras, La Ciénaga” [646]) to picture puzzles that remind us both of Tinajero’s sole published poem (“Sión”) and also the joke representations of “Mexicans” from above with which he had earlier passed the time with his companions. Either way, his earlier facility with language (or rather, with the meta-language of aesthetic terminology, as well as with the narcissistic self-reflection of the diary form) is replaced first by mere names, and second by line-drawn riddles.

“What’s outside the window?” are the last words of The Savage Dectectives (648). They are followed by a broken rectangle, or a rectangle of broken lines: a dissolving frame perhaps, an illusory or precarious dividing line between inside and outside, between the thing and what holds the thing in place. What’s outside the book? Well, at last this long one is at an end, so maybe we’ll find out.

2666 V: Narrative Necrosis

Posted on by

Drawing on narrative theory (Genette, Barthes, Todorov, Culler, etc.) Bede Scott argues that the fourth part of 2666, “The Part of the Crimes,” induces what he calls “‘narrative necrosis,’ whereby the tissue of the narrative itself undergoes a process of decomposition” such that “this necrosis fatally compromises the narrativity of Part Four, if not the entire novel, and thus serves as a discursive correlative for the decomposing bodies it describes” (“Roberto Bolaño’s 2666: Serial Murder and Narrative Necrosis” 309, 316). Bolaño’s repetitive, relentless catalogue of the discovery of murder victims in and around the city of Santa Teresa, whose cases are closed almost as soon as they are opened, puts an end to any attempt to craft a story out of the events it registers.

Part Four takes us from 1993 to 1997, and describes 110 murders (strictly, 109 murders and one suicide), of which only 10% are resolved. Moreover, as the text breaks off, there is no end in sight. We are told that the “The last case of 1997” involves a body found “by the dirt road that runs along the border and then forks and vanishes when it reaches the first mountains and steep passes. The victim, according to the medical examiners, had been dead for a long time. She was about eighteen, five foot two and a half or three. [. . .] Both this case and the previous case were closed after three days of generally halfhearted investigations” (632, 633). And yet life continues: The Christmas holidays in Santa Teresa were celebrated in the usual fashion” (633). As Scott puts it, by the time we reach this point, we may have “the (perfectly justified) impression” that between this case and the first documented one, back in 1993:

there has been no transformation whatsoever in the intervening four years and 280 pages. At the end of the section, the various detective figures—who scarcely require individuating—are either dead or no closer to solving the crimes than they were at the beginning. The women themselves are still being raped and murdered with the same metronomic regularity. [. . .] And this is also why we have an ending that merely replicates the beginning—because the dialectic of resemblance and difference that makes a genuine conclusion possible has been destroyed; because this is a narrative in which closure uncloses and nothing comes to anything; and because both the beginning and the end of Part Four are ultimately arbitrary, neither inaugurating nor concluding the “narrative” they ostensibly frame. (315)

It is no surprise therefore that the Part simply stops, rather abruptly. Life goes on in Santa Teresa, but so does the series of murders and deaths. We should not expect any satisfactory resolution. In so far as the causes of the femicide are social (and even this is not exactly a case that is conclusively made), Mexico remains the same: all the conditions that enable and give rise to the crimes (machismo, migration, maquiladoras, drug traffic) are still in place. Resolution was always destined to elude the police and other state authorities–even granted that they put their full effort into investigating the crimes, which to be fair they sometimes do. The frustrated investigation into the case of Kelly Rivera Parker (whose body in fact never turns up), instigated and funded by her childhood friend, who is now a congresswoman, shows that not even political clout or money can make much headway in providing clarity or identifying those who are responsible. We learn more about Rivera Parker’s secret life (organizing orgies at isolated ranches owned by cartel kingpins), but information in itself is no solution. Indeed, we hardly lack for information over the course of what are almost 300 pages in which we are simply deluged with it. What we lack are the tools to determine what is significant or not. This, of course, has been a problem to which the book has been pointing since page one.

So the crimes continue into an indeterminable future. What then can put an end to this catalogue if not the author’s own death? Here, the knowledge that 2666 is a posthumous book (a fact to which a brief prelude, a “Note from the Author’s Heirs,” has alerted us to at the outset) puts the body of the author at the center of this (non)narrative. Alongside the women’s bodies that the text describes, as well as the body of the text (as Scott argues), there is the ailing body of Roberto Bolaño, writing in the “realiz[ation] that death might be near.” No doubt we have this sense of authorial mortality in reading any posthumously published text, but perhaps especially so here. The prefatory note establishes that the novel has not been published exactly as Bolaño himself intended (above all, in that it has been published as a single volume, rather than five), but does not tell us much more about the state of (in)completion in which the author might have left the manuscript. Perhaps he pretty much wrapped everything up in time. Perhaps there were further editorial interventions by his family or his publisher. Still, it is only death (the very literal death of the author) that puts an end to a catalogue of deaths that otherwise knows no end. 

The Savage Detectives IV: A Chill Descends from the North Pole

Posted on by

Part Two of Bolaño’s novel ranges far and wide, both temporally and geographically. As its subtitle indicates, it covers the period from 1976 to 1996. And it takes us from Mexico to Europe (France, Spain, Austria…), the Middle East, and then Africa (Angola, Rwanda, Liberia).

Yet in another sense, all this is encompassed in a single night in a Mexico City apartment, sometime presumably in November or December, 1975, in which Amadeo Salvatierra talks to the “boys,” Ulises Lima and Arturo Belano, about the forgotten poet, Cesárea Tinajero. Part Two opens with Salvatierra’s account (apparently recorded in January 1976): “My dear boys, I said to them, I’m so glad to see you, come right in, make yourselves at home” (143). We also periodically but consistently return to their conversation as Part Two continues, breaking what is otherwise the chronological order of events and interviews. And it ends back in Salvatierra’s apartment, with the dawn breaking and the streets outside the windows beginning to fill up with people, with one of the boys (we do not know which) leafing through the magazine containing Tinajero’s sole published poem, and the other asleep or half-asleep on the sofa but still somehow responding to Amadeo’s query as to why they want to find Tinajero now: “we’re doing it for Mexico, for Latin America, for the Third World, for our girlfriends, because we feel like doing it. [. . .] we’re going to find Cesárea Tinajero and we’re going to find the Complete Works of Cesárea Tinajero” (587–88). This, however, elicits a “shiver” from Salvatierra, and the sense, as one of the boys puts it, that “the North Pole had descended on Mexico City” (588). Part Two ends with a chill, perhaps a blast of cold air sweeping over the boys’ youthful ambitions. Or are those ambitions themselves the source of the chill that seeps into Salvatierra’s apartment? Or is it that the aged Salvatierra, looking around the wreckage not only of one drunken night but also of a lifetime (“my books, my photographs, the stains on the ceiling”) knows that the path Lima and Belano are taking will lead them only to failure and disillusion?

The book is not yet over (we still have Part Three to come), but Lima and Belano’s stories are now done by the time Part Three ends. Their fates, and that of the other visceral realist group, are briefly summarized by one Ernesto García Grajales, who claims to be “the foremost scholar in the field, the definitive authority” but also “the only person who cares” (584). Not that García Grajales seems to care all that much: all this is merely fodder for a “little book” that he hopes “will do well” (585). And so he goes down the list: “María Font lives in Mexico City. [. . .] Shte writes, but she doesn’t publish. Ernesto San Epifanio died. [. . .] Ulises Lima still lives in Mexico City. [. . .] About Arturo Belano I know nothing” (594–85). And of course, of our voluble narrator from Part One of the novel: “García Madero? No the name doesn’t ring a bell. He never belonged to the group. Of course I’m sure. Man, if I tell you so as the reigning expert on the subject, it’s because that’s the way it is” (585). So much for expertise, of course. (We know otherwise, and better.) But also so much for García Madero, so full of hope and expectation when we last caught sight of him, over 400 pages ago, but who has been completely lost to memory, either official or unofficial, almost as though he had never existed.

What mark does our passage through this world leave? What impact do we have on those around us, or even on fate or destiny? What remains of us when our story comes to an end? Who will tell our story when we are gone? These, I think, are some of the questions Bolaño asks us, and his answers may sometimes leave us chilled.