A 108-year-old encrypted WW1 German radio message has been deciphered with the help of ChatGPT-6 Astra.
Released on September 3, 2026, GPT-6 Astra is OpenAI’s powerful flagship AI model with numerous capabilities and has already been used to play Minecraft autonomously and build a simulation within a simulation.
Now, it has shown code-breaking ability; AI developer Prinz used it to crack a 108-year-old German radio cipher used in World War One.
It checked the message against military logs #
On their Substack, Prinz revealed that they picked the code from a famous list of fifty unsolved ciphers that appears on German science blogging portal Scienceblogs.de.
The message was addressed to the German High Command, perhaps for the eyes of a Naval Command officer or admiral. At the time, the Germans used a convoluted grid of letters that shuffled depending on the current keyword.
Astra used the word “TRUPPENVERSCHIEBUNG” as the key to solve the cipher. The decoded message, when translated into English, was a radio alert that read: “AN ENGLISH CRUISER ARRIVED AT SEVASTOPOL ON THE ?4TH AN ALLIED SQUADRON FOLLOWS ON THE 26TH.”
GPT-6 Astra deciphered a 1918 German radio transmission that, to my knowledge, has never been deciphered before.
The message below translates to:
"EIN ENGLISCHER KREUZER EINLIEG X SEWASTOPOL X S4STEN X EIN GESCHWADER DER X ALLIIERTEN FOLGT 26STEN X"
or, in English:
"AN… [pic.twitter.com/8kjDdI2Q5O](https://t.co/8kjDdI2Q5O)
[September 17, 2026](https://x.com/deredleritt3r/status/2100608983492862201?ref_src=twsrc%5Etfw)
Astra checked its work against military logs and found that the cruiser’s arrival time aligned with the arrival of British cruiser HMS Canterbury in Sevastopol, Crimea, on November 24, 1918. The ‘?’ was likely a typo made in transmission. The Allied squadron’s arrival was on November 26, aligning perfectly.
For more on AI, check out our coverage of the Anthropic CEO telling AI companies to slow down over fears of misuse, or the robots congregating outside the Polish ministry as part of a demonstration for more AI regulation.