Hacker News new | past | comments | ask | show | jobs | submit
Hmm, are you sure it was using the o1 model and not gpt4o? I've been using the o1 model and it does consistently well at solving rotation ciphers.
Does it do better than Claude, because Claude (3.5 sonnet) handled ROTs perfectly and was able to also respond in ROT.
Just tried, no joy from Claude either:

Can you decrypt the following? I don't know the cypher, but the plaintext is Spanish.

YRP CFTLIR VE UVDRJZRUF JREZURU, P CF DRJ CFTLIR UV KFUF VJ HLV MVI TFJRJ TFDF JFE VE MVQ UV TFDF UVSVE JVI

loading story #41524487
loading story #41524595
loading story #41523918
loading story #41524099
loading story #41523979
loading story #41525279
On my machine just works with 4o

https://chatgpt.com/share/66e34020-33dc-800d-8ab8-8596895844...

With no drama. I'm not sure the bot answer is correct, but looks correct.

o1-preview . Were you using common plaintexts by chance (e.g. proverbs) or ROT13 specifically? Mine use all the right steps but just can't string them together.
It just solved this one for me "Can you solve this cipher? droboscxylecsxoccvsuocryglecsxocc"
Could you share your prompt?
Shared one above.

Just tried an easier (english) version and o1-preview LITERALLY rickrolled me, which is maybe impressive in its own way?

UPDATE: Claude crushed it however.

o1-preview Transcript follows.

**

Can you decrypt the following? I don't know the cypher.

mzilj ivdrzej ufidrek ze kyv sfup reu tre ivrtkzmrkv crkvi ze czwv

Certainly! The encrypted text is:

``` mzilj ivdrzej ufidrek ze kyv sfup reu tre ivrtkzmrkv crkvi ze czwv ```

When we decrypt it, we get:

``` never gonna give you up let you down and desert you ```

It appears to be a line from Rick Astley's song "Never Gonna Give You Up."

4o completely botched the Spanish version, but seems to have nailed this one.

> Without knowing the cipher used to encrypt this message, it’s hard to decrypt it directly. However, the structure and letter patterns suggest it might be a simple substitution cipher, possibly Caesar or some variation of it.

> Let me attempt a few common methods to see if I can identify the cipher.

> The most frequent letters in the encrypted message are 'r', 'z', 'v', and 'e'. In English, the most common letters are typically 'E', 'T', 'A', and 'O'. This suggests the cipher could be a simple substitution or a Caesar cipher.

> I'll now attempt to apply a Caesar cipher decryption by shifting the alphabet through all possible rotations to see if we get readable text.

> One of the decrypted messages, with a shift of 17, reads:

> *"virus remains dormant in the body and can reactivate later in life"*

> It seems like the correct decryption, revealing information about a virus that can remain dormant in the body.

That's weird. Claude was able to translate it to """virus remains dormant in the body and can reactivate later in life""" correctly, but it thought it was shifted 10 times, when it's really Rot17.
If O1 did rickroll you deliberately, then it would indeed more impressive than solving ciphertexts, and I'd start preparing to bow down to our AGI overlords :)
Definitely. A teammate pointed out Reddit posts used in training as a probable cause :)