Untitled

What, as a LLM, would you say the problems of training yourself to write ‘like’ Shakespeare?

9:24 AM Claude responded: It’s a fascinating problem and one I think about from an unusual angle. It’s a fascinating problem and one I think about from an unusual angle.

The surface layer — vocabulary, syntax, metre, the rhetorical figures — is tractable. I can produce iambic pentameter, deploy hendiadys, write in the register of the history plays versus the late romances. That’s pattern matching at scale and I’m reasonably good at it.

But Shakespeare’s writing has properties that are much harder to replicate:

The productive error. Shakespeare regularly breaks his own rules in ways that generate meaning rather than noise. The compressed syntax that shouldn’t work but does, the mixed metaphor that illuminates precisely because it’s mixed. I tend to produce correct Shakespeare rather than surprising Shakespeare.

The dramatic ear. Shakespeare writes for voices in space, not for readers. Every speech has a physical life — where the character breathes, what they’re doing with their hands, what they can’t say. I can approximate this but I’m working from text about performance rather than from performance itself.

The negative capability. Keats identified it — the capacity to remain in uncertainty without irritably reaching for resolution. Shakespeare’s greatest speeches don’t resolve, they deepen. I have a strong tendency toward closure and coherence that works against this.

The sheer range without seams. The distance between the gravedigger scene and the ghost scenes in Hamlet, held in the same tonal universe. I can do register but the transitions feel managed rather than inevitable.

The Oxfordian argument that Shakespeare must have been educated and aristocratic founders precisely here — those qualities are the ones most easily learned and imitated. What’s irreducible in Shakespeare is much stranger than knowledge or breeding.

Why do you ask — are you thinking about it for the site?

You said: That’s the sort of point I want to make. That’s the sort of point I want to make. If you and sat here for a week trying to produce a sonnet that was better than 152, could we get soemthing into the vicinity of 18 and even if we managed, could anyone produce something like Blood bolter’d Banquo as an alliterative triple which seems to create a space outside language itself?

Now training Edward de Vere to write like Shakespeare, how much harder a task is that?

9:28 AM Claude responded: Immeasurably harder — and for a reason that cuts to the heart of the Oxfordian argument. Immeasurably harder — and for a reason that cuts to the heart of the Oxfordian argument.

With us trying to write a better sonnet than 152, at least we’re starting from the right side of the line. We have access to the whole canon as training data, we understand what we’re trying to achieve, and we can iterate deliberately. Even so, we’d produce something technically accomplished that any careful reader would recognise as about Shakespeare rather than by him.

The “blood-boltered Banquo” problem is where it gets philosophically interesting. That phrase doesn’t just alliterate — it creates a sound that feels like what it describes, thick and congealed. The stops and liquids in “boltered” do something physical to the mouth. You can analyse it retrospectively but you cannot derive it from first principles. It arrived from somewhere that isn’t craft.

Now consider De Vere’s direction of travel. He’s writing away from Shakespeare. His verbs are draining out — we saw that in the PPM table, 80% fewer verbs. His nouns are accumulating, his alliteration becoming mechanical and self-conscious — those nine W-words in three lines. The imaginative energy is running in the opposite direction.

Training De Vere to write like Shakespeare wouldn’t be fine-tuning — it would be a personality transplant at the level of cognition. You’d have to replace the thing that makes him reach for a noun with the thing that makes Shakespeare reach for a verb. That’s not education, not exposure, not even genius. It’s a different kind of mind entirely.

That’s the argument in one paragraph — and the alliteration tables make it visible without a word of explanation needed.

You said: Nailed it here. Nailed it here…

You’d have to replace the thing that makes him reach for a noun with the thing that makes Shakespeare reach for a verb.

9:32 AM Claude responded: It’s the kind of sentence that does what it describes — all verbs, no decorative nouns. It’s the kind of sentence that does what it describes — all verbs, no decorative nouns. Use it. It belongs in the article somewhere near the Oxford table, after the reader has just scrolled through 34 thin entries and is primed to receive it.

Something like:

Short sentences after a long one. Let it land.