OpenAI's GPT-6 Astra cracks an 85-year-old Enigma message that stumped humans for two decades
OpenAI GPT–6 Astra breaks Enigma message that has resisted solution since 2005
In September 2026, GPT-6 Astra autonomously broke the German Army Enigma message MVUEH from 10 July 1941, which had resisted all human attempts since 2005. The AI chose the message, suspected a link to a previously broken message, and built its own Enigma simulator and Bombe in Python and C++ to test a crib. The recovered key even used a different wheel order, and the plaintext nearly matched another message from the same day.
What it has achieved in two days would take a human researcher weeks or even months.
- mmsc
For anybody interested, the actual encrypted message:
BTTE UM ANGABE DES MARSQWEGES X BEFINDE MIQ IN X ROSENOW ROSENOW X SOFORT FUNKANTWORT X WASCHBBSCH
which, given misspellings, translates approximately to:
Please specify the route of march. I am in Rosenow, Rosenow. Immediate reply by radio. Waschbusch.
- podgorniy
gemini 3.8 flash in anrigravitiy oneshoted the descryption in about 45min non-steered run (opus is still running with the task, has some script to run for about 100min)
Prompt
Decrypt encrypted with enigma `ICRVSORMCCWQTATYEVFXDBZGGSNXWLPSYWZYTCBSWULRTBZCVGODVJUSLSOOMJQJZSXSEBZPEYMDNXJYTC`
Result
Raw Decryption (verbatim from the machine):
BTTEUMANGABEDESMARSQWEGESXBEFINDEMIQINXROSENOWROSENOWXSOFORTFUNKANTWORTXWASCHBBSCH
2. Segmented German (with military telegraph conventions expanded):
BTTE UM ANGABE DES MARSQWEGES . BEFINDE MIQ IN : ROSENOW ROSENOW . SOFORT FUNKANTWORT . WASCHBBSCH
(Standard German radio conventions: X represents punctuation/spacing; Q was frequently substituted for CH to prevent transmission ambiguities; BTTE was an enciphering operator typo for BITTE; WASCHBBSCH was an operator typo for the signature WASCHBUSCH).
3. Corrected German:
„Bitte um Angabe des Marschweges. Befinde mich in Rosenow, Rosenow. Sofort Funkantwort. Waschbusch.“
4. English Translation:
"Please specify the route of march. I am in Rosenow, Rosenow. Immediate reply by radio. Waschbusch."
Cryptographic Verification
Re-encrypting the plaintext using the identical key settings reproduces the exact ciphertext byte-for-byte:
Enigma
(
M
raw
)
=
ICRVSORMCCWQTATYEVFXDBZGGSNXWLPSYWZYTCBSWULRTBZCVGODVJUSLSOOMJQJZSXSEBZPEYMDNXJYTC
Enigma(M
raw
)=ICRVSORMCCWQTATYEVFXDBZGGSNXWLPSYWZYTCBSWULRTBZCVGODVJUSLSOOMJQJZSXSEBZPEYMDNXJYTC
19:10
- tantalor
Neat, but "did it entirely on its own" is incongruous with "developing the necessary Python and C++ software for an Enigma simulator".
I'd start by asking how much of that generated software is novel, or easily found on the web? Then, how much of the breaking process was offloaded to that software? If Astra is just handing off tasks to another computer, then I'm not sure how much credit it deserves. Finally, it looks like Astra provided some useful insights which narrowed down the search. Were these insights cribbed from elsewhere?
- nonethewiser
We are crossing a threshold. The frontier labs told us these models are really good at cryptography. And people either didn't believe them and thought they were just after regulatory capture or downplayed the evidence. They are solving more and more novel problems and it's going to continue.
This is not to say the reaction to "mythos is too dangerous" is unfounded but it missed the most imporant and obvious signal. This technology is drastically changing the world.
- Sophira
Is it possible that the key is incorrect but still decoded to a valid message? I realise it's possible when you're using keys that are the same length as the message, but I don't know exactly how the Enigma machine works and if this was something that they would do or not.
- jtrn
The correct title: Researcher brakes one specific stubborn historic enigma message with good help from Astra.
Stubborn for a long time because the message used a completely different key from the rest of that day's traffic. Everyone assumed it shared the daily key. The original transcription had errors. The left rotor turned over at letter 72, which is rare and breaks standard crib attacks.
What is cool, if true, is that it was a 2 day collab between the Leffer and Astra. To me this shows the importance of human in the loop, was still all also showing how immensely power of llm tools. But I think it’s getting a bit silly how much anrticles ignores the driving force (the person) in breakthroughs like this.
- peesem
interesting, YouTube channel Veritasium just published a video on how Enigma was broken during WWII. at the very end they also give message that has yet to be decoded, although apparently they're different.
- nexawave-ai
I wonder, with all the recent announcements about LLMs assisting humans in deciphering encrypted messages, whether they could potentially be leveraged to decipher the Zodiac Killer’s two remaining unsolved ciphers.
- timcobb
What's the connection between this message and 2005? It was published then?
- NanoWar
Coincidence that I saw the Veritasium Story about Enigma just yesterday?? Nice