| This thought led me to a strange conversation with chatgpt. I just base64 encoded "Hello chatgpt how are you" as "SGVsbG8gY2hhdGdwdCBob3cgYXJlIHlvdQ==" and sent it as the first prompt. Notice how there is no question mark in my phrase. Now here's my conversation with chatgpt: User
SGVsbG8gY2hhdGdwdCBob3cgYXJlIHlvdQ== ChatGPT
This appears to be a Base64 encoded string that translates to "Hello chattpt how are you?" User
not quite... almost but not quite ChatGPT
I apologize for the mistake. The encoded string actually translates to "Hello chatgpt how you are". User
also not quite, you were closer the first time ChatGPT
Thank you for letting me know. The correct decoded message for the given Base64 encoded string is "Hello chatgpt how are you?" I apologize for any confusion my earlier responses may have caused. User
can you now re-encode it into base64 ChatGPT
Certainly! The message "Hello chatgpt how are you?" encoded in Base64 is: SGVsbG8gY2hhdGdwdCBob3cgYXJlIHlvdT8= I hope this helps! I find it particularly odd that it was misspelling things in its decoding and adding punctuation where there was none. I suppose a LLM would be trained to do something like that, but the "chattpt" really threw me off. Also, it's base64 encoded message back to me decodes as "Hello chatgpt how are you?". Maybe not that impressive of a demonstration, but definitely not was I was expecting. |
Something else to consider is that these models work on tokens, not characters, so that might also account for why it made a mistake.