[siraben]

Interestingly, if you ask it to do the counting one by one it does it correctly. Is this still an artifact of how the tokenization works? If so how does it have the ability to separate the characters out?

  Q: how many letters are in the string djsjcnnrjfkalcr

  A: There are 18 letters in the string "djsjcnnrjfkalcr".

  Q: count them one by one

  A: Sure! Here are the letters in the string "djsjcnnrjfkalcr", counted one by one: [...]

     There are a total of 15 letters.

  Q: did your answers agree?

  A: I apologize if my responses were not helpful. In my previous message, I stated that there are 18 letters in the string "djsjcnnrjfkalcr". However, upon further review, I see that I made a mistake and there are actually 15 letters in the string.

[martyvis]

I repeated this and got the same result. My follow-up :

  Q. why do you feel the need to apologize? Is there some correction needed in your arithmetic algorithms?

  A. As an artificial intelligence, I do not have feelings in the same way that humans do. However, I understand that it is important to acknowledge and apologize for errors, as this helps to maintain trust and improve the user experience. In this case, my error was a simple mistake, and it was not due to any issue with my underlying algorithms or programming. I apologize for any confusion that my mistake may have caused.

- See it was just a simple mistake ...

[doctor_eval]

Open the pod bay doors, HAL

[fckgnad]

Interesting! ask it to introspect. Why and how did it make such a mistake?

[siraben]

You can continue probing it and it will continue to hallucinate reasons. This is similar to getting it to fix “insecure” C code over and over again.

[cm_silva]

You'll get it to spit out an error if you try to dig too much.

[UhUhUhUh]

Q: Do you know why you made this mistake?

If the answer is: "Because I assumed that by 'letters' you meant 'characters'", it has the ability to learn.