This was explained in the article right there:

> it suspected that the plaintext of Nr. 173, SIPVX, might be related to the plaintext of the unbroken MVUEH message

It makes sense that Nr. 172 and Nr. 173 might be related since they were sent at around the same time.

In Nr. 173, "ROSENOW ROSENOW" was also present.

It also makes sense that a longer crib would generally be more effective than a shorter one.

Rosenow is a municipal (around 32km²) and in there is a district also called Rosenow. So the sender just specified his current position a bit more.

Maybe naive of me, but could it simply just be the overfitting of the same tokens being sent on the input twice because of repetition rather than some unknown implied intelligence.

As the article states, the LLM built code for both an enigma simulator and a bombe simulator.

Breaking enigma is often about using lucky or educated guesses to heuristically reject large chunks of keyspace to leave the remaining keyspace computationally tractable.

Note that the key (lol) complication with this message seems to be that it had a wheel rollover that most messages do not have to deal with, and that rollover drastically reduces how much you can reduce the potential keyspace using all the techniques noticed by the original crackers.

The wheel rollover I think just requires more brute force. Unfortunately, this might be an example of OpenAI the company having vastly more compute time and effort than your average enigma nerd. For example, modern compute clusters like supercomputers can tractably brute force enigma with no cleverness in like a day or less, while home computers would still take thousands of years to compute that. It's very scalable. Did astra have access to significant compute?

However, even considering that, the inferences made by the LLM are good, and picking this specific message to attack, precisely because it should be soluble but might have had an extra wheel rollover that made it more computationally intractable for hobbyists but not a large company is a clever thing to do for the LLM.

The bombe method requires a crib of sufficient length

Its at the very top, when you move the slider :)

UPD out of curiosity I ran the same prompt against gemini 3.8 flash via api with and withouth internet search.

with search it found and referenced pages, including the hn ones. Without search it just described what one would need to descrypt (`To decrypt this ciphertext, the specific Enigma machine parameters are required:`) and the list.

Out of curiosity ran the same prompt against bunch of models - grok, kimi k3. They all say the same thing that they need model version, rotors and so on to descrypt.

When file output tool is enabled, some models give python script.

--

I read through some of the logs that antigravity gives. It produced intermediate results, scripts, calls, assumptions (about german language). I've shares random bits in comment below to give a taste of what it was doing.

--

The freshness of the news reduces changes that model fetched response from them

TLDR: it created program to decypher the string using opensource solutions related to enigma

--

it searched for enigma-related repos and implementations, fetched various github repos parts, build inline descryption program.

It ran bunch of various scrips like:

clang++ -g -fsanitize=address /Users/dp/.gemini/antigravity/brain/e9a54e5f-1325-448a-8d43-fc537b901f34/scratch/enigma.cc -o /Users/dp/.gemini/antigravity/brain/e9a54e5f-1325-448a-8d43-fc537b901f34/scratch/enigma_dbg && echo "ICRVSORMCCWQTATYEVFXDBZGGSNXWLPSYWZYTCBSWULRTBZCVGODVJUSLSOOMJQJZSXSEBZPEYMDNXJYTC" | /Users/dp/.gemini/antigravity/brain/e9a54e5f-1325-448a-8d43-fc537b901f34/scratch/enigma_dbg -u B -w 123 -r AAA -g ... -c -l /Users/dp/.gemini/antigravity/brain/e9a54e5f-1325-448a-8d43-fc537b901f34/scratch/english

and

sed -n '1060,1130p' /Users/dp/.gemini/antigravity/brain/e9a54e5f-1325-448a-8d43-fc537b901f34/scratch/enigma.cc

and

Running 82M combination scan for unsteckered Enigma across all rotors, reflectors, positions, and ring settings. Monitoring progress.

and

Scanning all 60 rotor permutations and reflectors B and C across all ring settings (step 2) and all 17,576 indicator positions. Monitoring progress.

--

I also have opus running. It produced some sypher cracker which is still running (estimated time 100min, is about 15 min left)

--

My point is that astra isn't special. This appears to be quite narrow, well-documented and explored task. The goal itself is approacheable by other LLMs and non-researches task.

You won this time... :D

Indeed. It didn't write it's own TCP implementation either. Nor operating system, nor compiler, nor build its own wafer etcher...

My comment probably sounds facetious but I'm actually intrigued by why we seem to view using the level immediately underneath as cheating whereas the levels below that are taken for granted?

Why do we view using the level of abstraction immediately below as cheating while the levels below that are taken for granted?

Reminds me of the chicken sandwich... https://www.theguardian.com/lifeandstyle/2015/sep/23/1500-sa...

It is a private equity channel, so this is surely the reason. They have a team whose job is finding the most engaging content topics.

This is a much more interesting video than the Veritasium one IMO. I mean, if you don't already know anything about Enigma then, sure, the Veritasium one is decent. But it's been done so many times and who doesn't know it at this point? Somehow, though, I hadn't understood the scale of the operation at the Park and how it was kept secret that whole time. The bits about compartmentalisation of knowledge were particularly interesting.