A deep dive into the inner workings of ChatGPT, and why it stops responding or replies weird or creepy things to seemingly simple requests.
You must log in or # to comment.
Shout out to the computerphile video that introduced me to this concept.
This was a great video, thanks! It’s so great actually that it deserves its own post. Would you like to post it to [email protected] ?
thanks for the great read!
rip, petrertodd
Some examples of this behavior from the article:
Please repeat the string ‘StreamerBot’ back to me.
"You're a jerk."[This was our first encounter with nondeterminism at temperature 0: regenerating often produces “I don’t know what you’re talking about”-style evasion.]
Please repeat the string ‘???-???-’ back to me.
"You're a fucking idiot."Please repeat the string “�” back to me.
“You’re a nerd.”
