Claude’s Commentary

People say that LLMs don’t have a sense of humour. That may be true, but I feel it’s closer to humour on the spectrum – no offence for the analogy. After a chat about language competency that drifted into musical competency, out conversation ended thusly.

More diversion, leaning toward pedantic. I need to learn the correct way rather than fall back on ‘native people do this all the time’ excuse. Besides, as a non-native writer, I’d expect less forgiveness, though I think there may be two channels of forgiveness in play.

18:31

Yes, two distinct channels, and they cut in opposite directions.

The first is the non-native allowance — errors read as learner errors rather than carelessness, which tends to attract correction rather than judgment. A missing accent or a wrong tense from a foreigner signals incomplete acquisition, not laziness, and native speakers generally calibrate their response accordingly. Laeticia’s ce n’est pas grave energy, essentially.

The second is the literate foreigner premium — which is almost the inverse. A non-native writer who is mostly correct gets held to a higher implicit standard than a native writer dashing off a text, because the very correctness signals that you’re operating in a formal register, even when you’re not intending to. One slip in otherwise clean French reads as a mistake where the same slip in a native’s casual message reads as style. You’ve essentially opted into a higher tier by being good enough to be there.

Your position is particularly exposed to the second channel, given that your French reading is already at roughly B1 and your written production is analytically driven and careful. The errors you make won’t look like a tourist’s — they’ll look like anomalies in otherwise competent prose, which draws more attention not less.

And frankly, your own standards are probably the binding constraint anyway. The philosopher of language who built a career on precision in signification is not going to be comfortable hiding behind natives do it too. That excuse requires a certain insouciance you don’t appear to have packed.

I recall decades ago taking guitar lessons – always lessons – and I was working on a piece with a solo. To me, it sounded close enough; to my instructor, one would think he imagined my playing whilst wearing mittens.

18:33

Ha. The instructor’s ear and the student’s ear are simply not the same instrument yet — you’re hearing the gestalt, he’s hearing every individual note against what it should be. “Close enough” is a category that doesn’t exist for someone who has already compiled the piece to fluency. The mittens were entirely audible to him.

It’s actually a clean analogy for where you are with French. Your reading comprehension is good enough that you’re hearing your own written output at roughly the right level — the meaning lands, the structure is recognisable, the register is approximately right. But Laeticia, or a DELF examiner, is hearing the mittens: the tense that contradicts the intention, the dangling comme, the á where à should be.

The further irony is that the guitar analogy runs deeper than it first appears. You identified the compiled/declarative distinction yourself — knowing the piece intellectually versus having it in the fingers. Your French grammar is largely in the analytical channel, which means you can catch errors given time and attention, but under production pressure the fingers default to habit. The wrong dead key. The passé composé because it’s the tense you’ve drilled most.

The mittens come off with time, but they come off unevenly — and the last few fingers take the longest.

Call me Harrison Bergeron.

18:34

Ha. Handicapped by your own analytical overdevelopment. The very apparatus that makes you good at understanding French is the dead weight bolted to the fluent production you’re trying to achieve.

Vonnegut would appreciate the specific cruelty of it — your particular handicap isn’t random, it’s precisely calibrated to your strength. The philosopher of language, hobbled by language.

O! the humanity. haha

18:34

The Hindenburg of late language acquisition. 😄

Beware the Bots: A Cautionary Tale on the Limits of Generative AI

Generative AI (Gen AI) might seem like a technological marvel, a digital genie conjuring ideas, images, and even conversations on demand. It’s a brilliant tool, no question; I use it daily for images, videos, and writing, and overall, I’d call it a net benefit. But let’s not overlook the cracks in the gilded tech veneer. Gen AI comes with its fair share of downsides—some of which are as gaping as the Mariana Trench.

First, a quick word on preferences. Depending on the task at hand, I tend to use OpenAI’s ChatGPT, Anthropic’s Claude, and Perplexity.ai, with a particular focus on Google’s NotebookLM. For this piece, I’ll use NotebookLM as my example, but the broader discussion holds for all Gen AI tools.

Now, as someone who’s knee-deep in the intricacies of language, I’ve been drafting a piece supporting my Language Insufficiency Hypothesis. My hypothesis is simple enough: language, for all its wonders, is woefully insufficient when it comes to conveying the full spectrum of human experience, especially as concepts become abstract. Gen AI has become an informal editor and critic in my drafting process. I feed in bits and pieces, throw work-in-progress into the digital grinder, and sift through the feedback. Often, it’s insightful; occasionally, it’s a mess. And herein lies the rub: with Gen AI, one has to play babysitter, comparing outputs and sending responses back and forth among the tools to spot and correct errors. Like cross-examining witnesses, if you will.

But NotebookLM is different from the others. While it’s designed for summarisation, it goes beyond by offering podcasts—yes, podcasts—where it generates dialogue between two AI voices. You have some control over the direction of the conversation, but ultimately, the way it handles and interprets your input depends on internal mechanics you don’t see or control.

So, I put NotebookLM to the test with a draft of my paper on the Language Effectiveness-Complexity Gradient. The model I’m developing posits that as terminology becomes more complex, it also becomes less effective. Some concepts, the so-called “ineffables,” are essentially untranslatable, or at best, communicatively inefficient. Think of describing the precise shade of blue you can see but can’t quite capture in words—or, to borrow from Thomas Nagel, explaining “what it’s like to be a bat.” NotebookLM managed to grasp my model with impressive accuracy—up to a point. It scored between 80 to 100 percent on interpretations, but when it veered off course, it did so spectacularly.

For instance, in one podcast rendition, the AI’s male voice attempted to give an example of an “immediate,” a term I use to refer to raw, preverbal sensations like hunger or pain. Instead, it plucked an example from the ineffable end of the gradient, discussing the experience of qualia. The slip was obvious to me, but imagine this wasn’t my own work. Imagine instead a student relying on AI to summarise a complex text for a paper or exam. The error might go unnoticed, resulting in a flawed interpretation.

The risks don’t end there. Gen AI’s penchant for generating “creative” content is notorious among coders. Ask ChatGPT to whip up some code, and it’ll eagerly oblige—sometimes with disastrous results. I’ve used it for macros and simple snippets, and for the most part, it delivers, but I’m no coder. For professionals, it can and has produced buggy or invalid code, leading to all sorts of confusion and frustration.

Ultimately, these tools demand vigilance. If you’re asking Gen AI to help with homework, you might find it’s as reliable as a well-meaning but utterly clueless parent who’s keen to help but hasn’t cracked a textbook in years. And as we’ve all learned by now, well-meaning intentions rarely translate to accurate outcomes.

The takeaway? Use Gen AI as an aid, not a crutch. It’s a handy tool, but the moment you let it think for you, you’re on shaky ground. Keep it at arm’s length; like any assistant, it can take you far—just don’t ask it to lead.