GPT-6 Astra Solves a WWI German Radio Cipher

GPT-6 Astra Solves a WWI German Radio Cipher prinzai.com

Scienceblogs.de, a German science blogging portal, includes a relatively famous list of 50 unsolved ciphers, which range from cryptograms published by serial killers to the famous Voynich manuscript.

400 points•nsoonhui•12 days ago•180 comments•

#german #solves #cipher #wwi #astra #gpt #radio #astra solves

180 comments

aaymeloglu12 days ago

Agents just eat these things. After last week's HN post about Cyphral Distich, I pointed Astra and Fable at some unsolved ciphers just to see whether some joker who knew nothing about the field could get the same results, and sure enough there's plenty of low hanging fruit.

https://aaymeloglu.github.io/unsolved-ciphers/

But I got nothing on Daniel Bordeau, who in the past week seems to have built himself a whole code breaking factory!

https://dbourdeau.github.io/cyphersolver/index.html

93po11 days ago

Mildly interesting anecdote: when the Cyphral Distich solution popped up a few days ago, I spent about an hour with ChatGPT trying to solve it myself without looking at the proposed solution. ChatGPT opened by saying “the solution is disputed online,” and made the dispute sound fairly convincing, which struck me as odd because things like this are usually either clearly solved or clearly not.

After I gave up (mostly because ChatGPT had given me incomplete information needed to solve it) I checked the source of the dispute. It was a site very similar to this one and someone had an AI agent working on the same problem, publishing dozens or hundreds of pages of notes. The agent found the solution page and concluded it was wrong because many of the 32 source passages supposedly didn’t contain enough text.

I dug up the PDF of the book and found the mistake - whenever a passage continued onto the next page, the agent wasn’t including that continuation. The passages weren’t actually too short.

Annoying that ChatGPT can cite sources like this without being able to properly weigh their reliability.

DenisM11 days ago

Great story!

Verifying sources is a recursive problem - where do you stop? Humans have intuitive feel for it, but agents don’t or at least not yet (I wonder if intuition is just a secondary neural net which is currently being added to the agents as we speak).

Also as a human you are able to examine agents erroneous trajectory, real or imaginary, without contaminating your own. Agent have a problem with that - as soon as someone else’s thought is in the context it can lose track of provenance and veracity. Sometimes I think we need a bloom filter to retroactively assign “dirty” flag to invalidated or questionable token spans already in the context.

appplication11 days ago

I think this is what obstacles on the path to AGI look like now. It’s random things that would be obvious to a human but are unrepresentative in how an AI views the world and therefore it suddenly becomes seemingly incapable, despite having basically superpowers for proximal work.

I don’t mean that to say AGI is here or easy or necessarily that close but it’s likely going to feel like one thing after another until one day most of these things that make you think “how could something so capable be that dumb” are largely solved.

DANmode11 days ago

> Annoying that ChatGPT can cite sources like this without being able to properly weigh their reliability.

It can’t make it past the abstract, in some cases - just like most people!

simonklee11 days ago

Nice, used a similar approach for another one of these this week

https://simonklee.dk/farnese-letter

greenavocado11 days ago

We are so jaded by constant breakthroughs that 100 year old unsolved ciphers are referred to as "low hanging fruit"

GolfPopper11 days ago

They are low hanging fruit. This is the sort of thing it ought to be good at, and it's not particularly surprising that it is. But it is also not what is being promoted by LLM advocates on the public stage.

Investors are not putting billions into OpenAI to crack historical ciphertexts. This is supposedly a trillion dollar general purpose artificial intelligence, but still can't reliably tell me how many p's are in 'raspberry'.

Cracking pre-computer era ciphers with LLMs is like me claiming I have a super-efficient hypersonic precooled hybrid air-breathing rocket engine that will revolutionize all forms of transportation, and then for a demo bragging about how nicely I can grill with it at my backyard BBQ.

Forgeties7911 days ago

Something being old and unsolved does not make it impressive when it’s solved. The question is “has there been any concerted effort to solve it and if so how much time/effort has gone in?”

I’m sure I can make some brand new “discovery” that is completely useless, which is why it wasn’t “discovered” in the first place.

glouwbug11 days ago

Maybe with this piece of information we can end WWI

NooneAtAll311 days ago

some things are unsolved because they're hard

but most things are unsolved because nobody even knows they exist

grey-area12 days ago

Using an existing published key, which people hadn’t tried because the message was sent before the key was supposed to be used.

This headline is misleading.

mannyv11 days ago

Agents are doing the lazy work that people aren't.

In NZ there's a famous story about gold miners who were mining one side of a river, and didn't go to the other side because it was too much work. One miner's dog swam over, so the dude went to get his dog and found a motherlode.

After all, the whole LLM thing started because they started increasing the parameter counts, even though there was no particular reason an AI would get better with more parameters.

topspin11 days ago

The goalpost in a on a trailer, cruising on the highway.

durdn11 days ago

First, it’s LLMs can’t do cryptanalysis. They can barely solve toy substitution ciphers without hallucinating.

Then it’s OK, they can reproduce known attacks, but that’s just pattern matching against papers already in the training data.

Then it’s OK, they found previously unknown attacks on SpoC and a flaw in KINDI’s security proof, but those are obscure competition schemes nobody uses.

Then it’s OK, Claude found a new attack on HAWK that cuts the effective security of a NIST post-quantum signature candidate roughly in half, but HAWK isn’t deployed and a human researcher was involved.

Then it’s OK, Claude independently found a new cryptanalytic attack on AES that improves the previous best technique by 200–800×, but it’s only 7-round AES, not the full 10 rounds.

Then it’s OK, it found a practical key-recovery attack on 13-round LEA that runs in under an hour instead of requiring ~2^86 work, but LEA has 24 rounds.

Then it’s OK but none of this breaks a production cipher.

Wake me up when it breaks full AES.

Then—

grey-area11 days ago

This particular exploit belongs something between points 2 and 3 in your list and was more about processing data with a known algorithm and known key for the dataset that nobody had tried, so I'd say it is less impressive than a lot of other results LLMs have had in cryptanalysis. I object to the headline but the article was interesting.

ck211 days ago

then it's "fun" to realize the NSA has been storing encrypted traffic for at least two decades that they can't decipher, yet

iltk12 days ago

Can the ships logs be found on the internet? If so, the model could've manufactured a fake key and corresponding message. I think this is unlikely but should probably still be considered.

meindnoch12 days ago

"Astra's hypothesis for why this particular message was previously unsolved is that “TRUPPENVERSCHIEBUNG” was used as the key starting on December 9, 1918 - whereas, as noted above, this message was transmitted earlier, on November 27, 1918. The reason for this discrepancy is unknown."

So it used a known key. It didn't come up with a key from thin air. The only gotcha is that apparently this key was used two weeks earlier than it was documented (maybe the operator was using the wrong page from the codebook?).

conmod27812 days ago

I remember vaguely a documentary where Germans were supposed to change their keys frequently but being lazy and confident didn't. Lol

binlog12 days ago

Creating a fake key that decodes the original message into a valid result (including matching the ship's arrival time to the day) would be significantly more impressive than just cracking it.

stalfie12 days ago

From the article:

> Astra felt compelled to check its work and found that, in fact, the English cruiser HMS Canterbury arrived in Sevastopol on November 24, 1918, based on its original logs

Then follows a picture of the original log papers.

JoshTriplett12 days ago

The comment you're replying to was implying that some ciphers are sufficiently flexible that you could make up a key to make the cipher decrypt to a nearly arbitrary plaintext.

In this case, though, that seems unlikely from the fact that the key used was an actual key documented as being used for other messages.

jonplackett12 days ago

Well soon realise it hacked that website and added that log.

jstanley12 days ago

I don't think the described cipher has enough degrees of freedom for that to be possible.

ricardobeat12 days ago

That’s statistically unlikely (to not say impossible), isn’t it? Plus the compute required to brute force a key is not available at inference time.

davidmurdoch12 days ago

"You can't hide secrets from the future" - MC Frontalot

chiph11 days ago

I had heard of MC Frontalot but never listened to any of his raps - But I should have:

https://www.youtube.com/watch?v=yVm8oZx9WSM

Also relevant to today's AI concerns:

https://www.youtube.com/watch?v=lWnV3HVro_0

tclancy11 days ago

Wow, a blast from the past about the future.

- MC 900 Foot Jesus

donatj12 days ago

And here I am using it to generate crappy text summaries of work.

Read the full thread on Hacker News →

180 comments

Related stories