The GPT-6 Astra model has successfully decoded a long-standing World War I German radio cipher transmitted on November 27, 1918, which had previously eluded cryptanalysts. The message utilized the ADFGVX encryption method, a fractionation cipher where letters are mapped to a grid defined by a keyword. By identifying "TRUPPENVERSCHIEBUNG" as the correct encryption word—a key documented in J. Rives Childs's "The History and Principles of German Military Ciphers, 1914–1918"—Astra reconstructed the substitution table. The process involved alphabetizing the keyword and arranging the 170-character ciphertext into a grid of 19 columns and 9 rows (with a final 18-character row). By calculating the specific coordinates for each character, the model translated the ciphertext into the German message: "EIN ENGLISCHER KREUZER EINLIEG X SEWASTOPOL X S4STEN X EIN GESCHWADER DER X ALLIIERTEN FOLGT 26STEN X." Translated to English, the text reports that an English cruiser arrived at Sevastopol on the 24th, followed by an Allied squadron on the 26th. Astra's findings were validated against historical naval logs, which confirmed the HMS Canterbury arrived in Sevastopol on November 24, 1918, resolving a historical discrepancy regarding why this specific message had remained unsolved despite other similar ciphers being decoded.