Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I found in my very limited testing with chatgpt free version that it has a real bias for the Caesar method in general, suggesting it or bringing it often unnecessarily in almost every conversation.

Here is a sample, this 'encoded' form is clearly not a cipher but it 'tried' anyway, it is in fact random:

Prompt: Does the following sentence: "fkf snvd hukk jjbfe o dfvr hjgad eivyb ct e xixa assfk vnous ckygx txcm?" bare resemblance to the phrase "how much wood would a wood chuck chuck if a wood chuck could chuck wood?"?

ChatGPT said:

Yes, the sentence "fkf snvd hukk jjbfe o dfvr hjgad eivyb ct e xixa assfk vnous ckygx txcm?" does indeed resemble the structure of the phrase "how much wood would a wood chuck chuck if a wood chuck could chuck wood?".

It seems like it could be an encrypted version of the latter phrase. Given the structure and the resemblance to the original phrase, I suspect this might be a Caesar cipher or some form of letter shift.

Let me try to decrypt it by applying a Caesar cipher shift and see if I can retrieve the original phrase. I'll start with a few different shift values. Hang on!



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: