GPT-6 Astrathe new flagship model of OpenAImay have finally made a readable German military radio message which had resisted attempts at decipherment. The communication belongs to a group of transmissions intercepted in the last phase of First World War and in the weeks immediately following the armistice, some of which remained without a clear resolution for decades.
The person who proposes the possible reconstruction of the message is an author who signs himself Principalwhich the September 17, 2026 published the result obtained using AI. The content concerns some naval movements in Black Sea and several details are confirmed in the ship’s logbook HMS Canterburymaking the case particularly interesting.
What the German message from 1918 reconstructed by GPT-6 Astra says
The radiogram is composed of 170 symbols and it was broadcast on November 27, 1918just over two weeks after the armistice of November 11th. The message is part of the German radio traffic documented by the American James Rives Childs and also appears in a collection of encrypted communications with the system ADFGVX remained unsolved, with material provided by cryptanalyst George Lasry.
According to what was published by Prinz, the OpenAI model would have obtained a German phrase that refers to the arrival of an English cruiser in Sevastopol on the 4th of the month and an Allied squadron on the 26th. The first date does not emerge completely from the text: the character that should indicate the initial digit does not return a coherent number, therefore the model did not directly read “24 November”.
This is where historical verification comes into play. The logbook of HMS Canterbury, a light cruiser of the Royal Navy, records that the November 24, 1918 the ship docked in the port of Sevastopol at 10:20. Two days later, the November 26the same document reports the arrival of an “Allied Squadron”, i.e. an Allied naval team, at 11:30. The two pieces of information therefore correspond very well to the meaning of the reconstructed text.
This coincidence makes the solution plausible, but it is not enough in itself to demonstrate that each step of the decipherment is correct. Prinz’s work is not a peer-reviewed scientific study and, at this time, it is not accompanied by an independent cryptographic verification made public.
How the ADFGVX cipher works and how AI managed to crack it
To understand what GPT-6 Astra would have done, you must first see, in a simple way, how ADFGVX worked. The system was introduced by the German army in 1918 and takes its name from the only six letters used in the ciphertext: A, D, F, G, V and X. The ADFGVX version was an evolution of the previous ADFGX. The addition of the V allowed us to move to a 6×6 grid and also include the digits. The choice was not random. The respective Morse code signals were different enough from each other to reduce the risk of errors during radio transmissions. It was a manual technique but rather sophisticated for the time, because it combined two different steps of the encryptionor a substitution and a transposition.
In the first step letters and numbers occupied the boxes of this grid. Each character of the original content was transformed into a pair of two ADFGVX symbols, one to indicate the row and one for the column. At that point the sequence obtained was further shuffled by arranging it into columns and changing the order based on a keyword. To return to the readable form it was therefore necessary to identify both the layout of the grid and the way in which the columns had been reordered. The combination of the two steps made the message more difficult to reconstruct than a simple replacement, because not only the symbols used changed, but also their position in the sequence.
For this radiogram, Prinz reports that the model applied the German word TRUPPENVERSCHIEBUNGroughly translatable as “troop movement”. This is a 19-letter key that was not invented by the model or derived from scratch by analyzing the ciphertext alone. It was already documented in historical sources on the ADFGVX system.
The peculiarity is another. In the documentation cited by Prinz that word is associated with communications starting from December 9, 1918while the radiogram is dated November 27, twelve days earlier. Applying it anyway, the model would reconstruct the order of the columns and then convert the ADFGVX pairs until the German sentence was obtained. It is unclear why a key attributed to a later period works with that text. It may have been employed earlier than reported, the historical timeline may be incomplete, or there may be another explanation.
The interesting fact, therefore, is not that GPT-6 Astra has demonstrated that it can break modern cryptography. ADFGVX is a manual system of the time, already extensively studied, and many other messages encrypted with this method have been decrypted. For this reason it is not comparable to the algorithms used today to protect communications, transactions or sensitive data. In this episode the model seems to have had above all the role of connecting scattered information, putting together a still unsolved radiogram, an already known key, the rules of the cipher and naval documents with which to check the result.
All this then suggests a possible use of artificial intelligence also in historical and cryptographic researchwhere it could help formulate and test hypotheses by combining large amounts of information without replacing checking sources.
