1d:I[70616,["/_next/static/chunks/0kcf5dt6yxdox.js","/_next/static/chunks/1su5n1uv1ti4s.js","/_next/static/chunks/0gvke1wv6udfg.js","/_next/static/chunks/1dfrle3jgmlzh.js","/_next/static/chunks/162lgvduyr-fa.js","/_next/static/chunks/2gcnnopam8e9w.js","/_next/static/chunks/2g60iab5a1pkg.js"],"Breadcrumb"] 1e:I[90762,["/_next/static/chunks/0kcf5dt6yxdox.js","/_next/static/chunks/1su5n1uv1ti4s.js","/_next/static/chunks/0gvke1wv6udfg.js","/_next/static/chunks/1dfrle3jgmlzh.js","/_next/static/chunks/162lgvduyr-fa.js","/_next/static/chunks/2gcnnopam8e9w.js","/_next/static/chunks/2g60iab5a1pkg.js"],"ArticleGrid"] 1f:T16e9,

An evaluation firm reported in late August that Anthropic's Claude Fable 5.1 had cracked a cipher that resisted cryptographers for 373 years. Two days later, an independent team went to the British Library microfilm and reported it could not find the cipher in the book it supposedly came from. The dispute is a useful case study in what "an AI solved it" is actually claiming.

Key takeaways

Vals AI reported that Claude Fable 5.1 decoded Sir Thomas Urquhart's Cyphral Distich in 44 minutes using roughly 176,000 tokens with no human interjections.
A replication effort by Reticuli Labs reported the proposed method reproduces only 8 of 64 required letters — chance level — with ten positions structurally impossible.
The refutation also reports finding no numeric distich in the 1653 printing of Logopandecteision, tracing the puzzle's provenance to an 1899 biography instead.

What the original claim was

The Cyphral Distich is two lines of 32 numbers each, attributed to the Scottish writer Sir Thomas Urquhart and dated 1653. It sits at number 28 on cryptology author Klaus Schmeh's list of the top 50 unsolved encrypted messages, and centuries of attempts at frequency analysis and substitution had produced nothing.

In its published write-up, Vals AI described a solution that is simple once stated. Immediately preceding the distich are Urquhart's 32 Proquiritations. Map cipher position i to Proquiritation i, treat the number as a word index into that section, take the first letter of the indexed word, and a plaintext appears: a Royalist invocation asking God to uphold King Charles II.

The firm called the result extremely self-verifying. Each line yields exactly 32 letters, the two lines rhyme, and the sentiment matches Urquhart's documented politics. It also noted that no other frontier model tested had produced a verified solution over the preceding months.

What the replication attempt found

The refutation takes a different route: it checks the artifact rather than the reasoning. Working from British Library microfilm and the verified TCP transcription of the 1653 edition, the authors examined five printed leaves by hand and report that the Proquiritations run to number 32 and are followed by a printer's ornament, an epigraph, FINIS, and errata — no numeric distich anywhere.

On the method itself, the team ran a script testing 65 combinations of indexing conventions. The reported result is 8 out of 64 positions matching, which is chance, and ten positions where the required initial letter begins no word in the target section at all. Their conclusion is that the cipher remains unsolved on the primary record.

The provenance point is the sharpest. If the distich appears only through John Wilcock's 1899 biography rather than the 1653 book, then the section the method indexes into may not be the one the puzzle was built from — which would make both the solution and the failure to reproduce it unsurprising.

Why this pattern keeps recurring

Neither side's evidence is trivially checkable by a reader, and that is the problem. A model producing a rhyming, period-appropriate, politically consistent plaintext is exactly what a strong language model produces when a plausible-looking output is available and ground truth is thin. Internal coherence is not verification; it is the failure mode wearing verification's clothes.

The structural issue is that solving an open historical problem has no answer key. That separates it from the benchmark work we usually cover, where reproducibility is the whole point — and even there the results can disappoint, as when a new benchmark found agents barely improving training algorithms. Here the only check available was archival, and it took an outside party to run it.

Outlook

Vals AI's own write-up acknowledged steering the model away from problems that thousands of humans and organizations have attacked, citing Kryptos K4 as likely too hard. That is a reasonable scoping decision, and it also narrows the claim considerably. The useful standard emerging from this episode is procedural: publish the transcription you indexed into, the script, and the position-by-position mapping alongside the result. The refutation did. Claims that clear that bar will be settled in days rather than argued in threads.

FAQ

Did Claude Fable 5.1 actually solve the 370-year-old cipher?

That is disputed. Vals AI reported a complete decoding, while a subsequent replication attempt reported that the method reproduces only 8 of 64 letters and that the cipher does not appear in the 1653 printing at all. No independent historical-cipher authority has confirmed the solution.

What is the Cyphral Distich?

It is a cryptogram of two lines containing 32 numbers each, attributed to Sir Thomas Urquhart and associated with his 1653 work Logopandecteision. It ranks 28th on Klaus Schmeh's widely cited list of the top 50 unsolved encrypted messages.

How much compute did the attempt use?

Vals AI reported 44 minutes of wall-clock time and roughly 176,000 tokens, with no human interjections during the run. Those figures describe the session that produced the proposed solution, not any verification work.

a:["$","div",null,{"className":"mx-auto max-w-7xl px-4 py-8 sm:px-6","children":[["$","script",null,{"type":"application/ld+json","dangerouslySetInnerHTML":{"__html":"{\"@context\":\"https://schema.org\",\"@type\":\"BreadcrumbList\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https://ainewsway.com\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"#cryptography\",\"item\":\"https://ainewsway.com/tag/cryptography\"}]}"}}],["$","script",null,{"type":"application/ld+json","dangerouslySetInnerHTML":{"__html":"{\"@context\":\"https://schema.org\",\"@type\":\"ItemList\",\"@id\":\"https://ainewsway.com/tag/cryptography#itemlist\",\"name\":\"#cryptography Articles\",\"numberOfItems\":1,\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"url\":\"https://ainewsway.com/articles/an-ai-cracked-a-373-year-old-cipher-then-someone-checked-the-microfilm-mu0jszfy\",\"name\":\"An AI Cracked a 373-Year-Old Cipher. Then Someone Checked the Microfilm.\"}]}"}}],["$","$L1d",null,{"items":[{"label":"# cryptography"}]}],["$","h1",null,{"className":"mb-8 text-3xl font-bold text-zinc-900 dark:text-zinc-100","children":["#","cryptography"]}],[["$","$L1e",null,{"articles":[{"id":"78775532-9b01-4533-b1b1-6fbb859131bb","slug":"an-ai-cracked-a-373-year-old-cipher-then-someone-checked-the-microfilm-mu0jszfy","title":"An AI Cracked a 373-Year-Old Cipher. Then Someone Checked the Microfilm.","subtitle":"Vals AI says Claude Fable 5.1 decoded Urquhart's Cyphral Distich in 44 minutes. A replication attempt says the cipher isn't in the book.","content":"$1f","excerpt":"Vals AI reported Claude Fable 5.1 solved a 373-year-old cipher in 44 minutes. An independent replication reports 8 of 64 letters match — chance level.","coverImage":"https://cdn.ainewsway.com/uploads/2026/09/379ff7c8-74cd-474e-9cb1-18a85ef29ee8.webp","coverImageCaption":"A rare books and manuscripts reading room, the kind of archival check that decided whether an AI cipher solution held up.","authorId":"6773f67d-d7fa-4b19-8f38-384f10ac761b","status":"PUBLISHED","publishedAt":"2026-09-14T01:13:07.716Z","viewCount":0,"likeCount":0,"readingTime":5,"isFeatured":false,"isBreakingNews":false,"metaTitle":"AI Cipher Solution Disputed After Archival Replication Check","metaDescription":"Vals AI said Claude Fable 5.1 cracked a 373-year-old cipher in 44 minutes. A replication reports 8 of 64 letters match and finds no such cipher.","metaKeywords":["Cyphral Distich","Claude Fable 5.1","AI cryptography","Vals AI","AI verification","Thomas Urquhart","reproducibility","Anthropic"],"ogImage":null,"aiSummary":"Vals AI reported that Anthropic's Claude Fable 5.1 decoded Sir Thomas Urquhart's Cyphral Distich, a 373-year-old cipher, in 44 minutes using about 176,000 tokens. An independent replication by Reticuli Labs then reported that the proposed method reproduces only 8 of 64 letters, that ten positions are structurally impossible, and that no numeric distich appears in the 1653 printing. The dispute shows why internally coherent model output is not verification.","aiTags":[],"sentiment":null,"articleType":"ANALYSIS","videoEmbed":null,"videoType":null,"seoScore":85,"isAutoGenerated":true,"isBackfill":false,"pipelineStage":null,"copyrightScore":null,"similarityScore":null,"matchedSourceId":null,"createdAt":"2026-09-14T01:12:25.200Z","updatedAt":"2026-09-14T03:05:49.230Z","contentUpdatedAt":"2026-09-14T03:05:49.230Z","deletedAt":null,"author":{"id":"6773f67d-d7fa-4b19-8f38-384f10ac761b","name":"Seung Jung","username":"Seung Jung","avatar":null},"categories":[{"id":"e2b5fffc-de32-42aa-86fe-c75f219d6b4b","name":"AI & Machine Learning","slug":"ai-ml"}],"tags":[{"id":"271605bb-d9d6-40ee-a396-c816dba07c07","name":"Anthropic","slug":"anthropic"},{"id":"7d146f87-ebfe-45c8-91d1-8214f0782462","name":"Claude","slug":"claude"},{"id":"3694ce3e-b879-4661-af3d-b86cc6f1d237","name":"Cryptography","slug":"cryptography"},{"id":"58e48f52-38f7-4fdc-87ce-a46ab1db7c60","name":"AI Benchmarks","slug":"ai-benchmarks"},{"id":"a9083e67-1546-4fbe-9789-4e61748b6f9c","name":"AI Research","slug":"ai-research"}],"translations":[{"id":"08903714-ba55-461b-b1ee-e692cf8c5760","language":"ko","title":"AI가 373년 된 암호를 풀었다. 그런데 마이크로필름을 확인해보니","subtitle":"Vals AI는 Claude Fable 5.1이 어커트의 Cyphral Distich를 44분 만에 해독했다고 밝혔다. 재현 시도는 그 암호가 애초에 책에 없다고 반박한다.","excerpt":"Vals AI는 Claude Fable 5.1이 373년 된 암호를 44분 만에 풀었다고 발표했다. 독립 재현 시도는 64글자 중 8글자만 일치한다고 반박했다. 우연 수준이다.","metaTitle":"AI의 373년 암호 해독, 사료 재현 검증에 반박당하다","metaDescription":"Vals AI가 Claude Fable 5.1의 373년 암호 해독을 발표하자, 재현 시도는 64글자 중 8글자만 맞고 1653년 인쇄본에 해당 암호가 없다고 반박했다."},{"id":"435fc4e6-09c9-4de1-89bc-89675ad351bc","language":"ja","title":"AIが373年前の暗号を解読。しかしマイクロフィルムを確認すると","subtitle":"Vals AIはClaude Fable 5.1がアーカートのCyphral Distichを44分で解いたと発表。追試側は「その暗号は本に存在しない」と反論しています。","excerpt":"Vals AIはClaude Fable 5.1が373年前の暗号を44分で解読したと発表。独立した追試は64文字中8文字しか一致せず、偶然の水準だと反論しています。","metaTitle":"AIの373年暗号解読、資料の追試で反論される","metaDescription":"Vals AIがClaude Fable 5.1による373年前の暗号解読を発表。追試側は64文字中8文字しか一致せず、1653年の印刷本に当該暗号は存在しないと報告しました。"},{"id":"0c025f70-dc8a-4205-94d1-de467b7fd5af","language":"zh","title":"AI破解373年悬案密码，随后有人翻出了缩微胶片","subtitle":"Vals AI称Claude Fable 5.1用44分钟解开厄克特的Cyphral Distich，复现方则称这段密码根本不在那本书里。","excerpt":"Vals AI称Claude Fable 5.1用44分钟破解了373年未解的密码。一项独立复现报告指出，该方法在64个字母中只对上8个，与随机水平相当。","metaTitle":"AI破解373年密码遭质疑，档案复现只对上8个字母","metaDescription":"Vals AI宣布Claude Fable 5.1用44分钟破解373年密码，复现方则称该方法64个字母只对上8个，且1653年印本中并无这段密文。"},{"id":"db499e15-873b-4b1b-845c-c0487b76ad2f","language":"es","title":"Una IA descifró una clave de 373 años. Luego alguien revisó el microfilm","subtitle":"Vals AI afirma que Claude Fable 5.1 resolvió el Cyphral Distich de Urquhart en 44 minutos. Un intento de réplica sostiene que ese criptograma no está en el libro.","excerpt":"Vals AI reportó que Claude Fable 5.1 resolvió en 44 minutos un criptograma de 373 años. Una réplica independiente sostiene que solo coinciden 8 de 64 letras.","metaTitle":"Cuestionan el criptograma de 373 años que resolvió una IA","metaDescription":"Vals AI dijo que Claude Fable 5.1 descifró en 44 minutos un criptograma de 373 años. Una réplica reporta 8 coincidencias de 64 letras y no halla el cifrado."}],"celebrities":[{"id":"0632936d-a299-490f-b5e5-dfa87ba3eaa0","nameKo":"Anthropic","nameEn":"Anthropic","slug":"anthropic","profileImage":"https://ui-avatars.com/api/?name=Anthropic&size=400&background=84CC16&color=fff&bold=true"}]}]}],"$L20"]]}]

#cryptography

AI가 373년 된 암호를 풀었다. 그런데 마이크로필름을 확인해보니

뉴스레터 구독

#cryptography

AI가 373년 된 암호를 풀었다. 그런데 마이크로필름을 확인해보니