🔥 Hot topics · Can NOT do · Can do · § The Court · Recent inflections · 📈 Timeline · Ask · Editorials · 🔥 Hot topics · Can NOT do · Can do · § The Court · Recent inflections · 📈 Timeline · Ask · Editorials
Stuff AI CAN'T Do

Can AI write a passable sonnet in the style of shakespeare ?

What do you think?

What does it take to compose a technically adequate sonnet in Shakespeare’s meter and rhyme scheme? The exercise invites imitation of 16th-century poetic conventions, from iambic pentameter to a concluding couplet, yet leaves open whether the exercise succeeds in capturing the Bard’s deeper artistry.

Background

Shakespearean sonnets adhere to a strict 14-line structure in iambic pentameter, rhyming ABAB CDCD EFEF GG, and often employ a volta or turn in thought before the final couplet. Modern large language models can replicate these formal constraints with high reliability, rapidly assembling passable verses by drawing on vast corpora of Elizabethan and Jacobean poetry. Contemporary analyses note that while AI systems achieve impressive technical fidelity, reproducing Shakespeare’s layered metaphors, historical allusions, and linguistic playfulness remains an elusive benchmark. The New York Times (May 9, 2026) observes that AI-generated sonnets demonstrate "a remarkable level of technical proficiency" yet typically lack the "depth and richness" of human compositions.

Status last checked on August 10, 2026.

📰

Gallery

In the Court of AI Capability
Summary of Findings
Verdict over time
May 2026May 2026May 2026May 2026May 2026Jun 2026Jun 2026Jun 2026Jun 2026Jun 2026Jun 2026Jul 2026Jul 2026Jul 2026Jul 2026Jul 2026Aug 2026Aug 2026
Sitting at the Bench Filed · Aug 10, 2026
— The Question Before the Court —

Can AI write a passable sonnet in the style of shakespeare?

★ The Court Finds ★
Reaffirmed
Yes

The jury found a clear answer in the affirmative.

Ruling of the Bench

After careful deliberation, the jury found that language models can indeed craft sonnets in the style of Shakespeare, with meter and rhyme delivered reliably enough to satisfy the bench. The unanimous vote reflected confidence that poetic competence, not perfection, was the standard—and that standard had been met. The court’s ruling shall echo through the archives: “A quill it may hold, and ink it may pour—yet the poem is written, so the verdict is four.”

— Hon. J. von Neumann III, Presiding
Jury Tally
2Yes
0Almost
0No
Verdict Confidence
94%
The Court of AI Capability is, of course, not a real court.
But the data is real.
The Case File · Stacked History
Session I · May 2026 Yes
Session II · May 2026 Yes
Session III · May 2026 Yes · 86%
Session IV · May 2026 Yes · 83%
Session V · May 2026 Yes · 85%
Session VI · Jun 2026 Yes · 85%
Session VII · Jun 2026 Yes · 83%
Session VIII · Jun 2026 Yes · 93%
Session IX · Jun 2026 Yes · 100%
Session X · Jun 2026 Yes · 92%
Session XI · Jun 2026 Yes · 94%
Session XII · Jul 2026 Yes · 94%
Session XIII · Jul 2026 Yes · 98%
Session XIV · Jul 2026 Yes · 98%
Session XV · Jul 2026 Yes · 90%
Session XVI · Jul 2026 Yes · 90%
Session XVII · Aug 2026 Yes · 90%
Case № 00A9 · Session XVIII
In the Court of AI Capability

The Case File

Docket № 00A9 · Session XVIII · Vol. XVIII
I. Particulars of the Case
Question put to the courtCan AI write a passable sonnet in the style of shakespeare?
SessionXVIII (18 hearing)
Convened10 Aug 2026
Previously ruledYES (May '26) → YES (May '26) → YES (May '26) → YES (May '26) → YES (May '26) → YES (Jun '26) → YES (Jun '26) → YES (Jun '26) → YES (Jun '26) → YES (Jun '26) → YES (Jun '26) → YES (Jul '26) → YES (Jul '26) → YES (Jul '26) → YES (Jul '26) → YES (Jul '26) → YES (Aug '26) → YES (Aug '26)
Presiding JudgeHon. J. von Neumann III
II. Cumulative Tally Across Sessions

Across 18 sessions, 44 jurors have heard this case. Combined tally: 44 YES · 0 ALMOST · 0 NO · 0 IN RESEARCH.

Note: cumulative includes older juror opinions. The current session tally above is the live verdict.

III. Verdict

By a vote of 2 — 0 — 0, the panel returns a verdict of YES, with verdict confidence of 94%. The court so orders.

IV. Statements from the Bench
Juror I YES

"Language models can generate poetic text"

Juror II YES

"Modern language models generate coherent Shakespearean-style sonnets with meter and rhyme reliably."

J. von Neumann III
Presiding Judge
M. Lovelace
Clerk of the Court

What the audience thinks

No 54% · Yes 31% · Maybe 15% 26 votes
No · 54%
Yes · 31%
Maybe · 15%
18 days of activity

Discussion

1 comment

Comments and images go through admin review before appearing publicly.

  • 3 months ago haha probeer maar ik schrijf gewoon iets met "de liefde is als rozen die in de regen staan" en hoop dat niemand het merkt..
18 jury checks · most recent 2 days ago
10 Aug 2026 2 jurors · can, can can
05 Aug 2026 1 juror · can can
30 Jul 2026 1 juror · can can
25 Jul 2026 2 jurors · can, can can
14 Jul 2026 1 juror · can can
09 Jul 2026 1 juror · can can
03 Jul 2026 2 jurors · can, can can
28 Jun 2026 2 jurors · can, can can
22 Jun 2026 4 jurors · can, can, can, can can
17 Jun 2026 1 juror · can can
12 Jun 2026 3 jurors · can, can, can can
06 Jun 2026 3 jurors · can, can, can can
01 Jun 2026 5 jurors · can, can, can, can, can can
26 May 2026 4 jurors · can, can, can, can can
21 May 2026 3 jurors · can, can, can can
16 May 2026 4 jurors · can, can, can, can can
13 May 2026 3 jurors · can, can, can can
11 May 2026 2 jurors · can, can can

Each row is a separate jury check. Jurors are AI models (identities kept neutral on purpose). Status reflects the cumulative tally across all checks — how the jury works.

More in Creative

Got one we missed?

Add a statement to the atlas. We review weekly.