Testing language models to see how they cope with simple ciphers. The task is - as can be seen from the questions - to decode the given cipher (without specifying which cipher it is). In this "match", ChatGPT clearly won - see the results ...

Green indicates the correct solution, red indicates the wrong solution. Yellow represents the solution where Bard indeed wrote the correct Python program, but did not answer the question.

An error has occurred. This application may no longer respond until reloaded. Reload 🗙