A deep dive into the inner workings of ChatGPT, and why it stops responding or replies weird or creepy things to seemingly simple requests.
Unspeakable tokens
https://www.lesswrong.com/posts/aPeJE8bSo6rAFoLqg/solidgoldmagikarp-plus-prompt-generation
https://www.lesswrong.com/posts/aPeJE8bSo6rAFoLqg/solidgoldmagikarp-plus-prompt-generation
A deep dive into the inner workings of ChatGPT, and why it stops responding or replies weird or creepy things to seemingly simple requests.
3 Comments
chonkybirb@programming.dev · 3 pts · 3y
Shout out to the computerphile video that introduced me to this concept.
sisyphean@programming.dev · 1 pts · 3y
This was a great video, thanks! It’s so great actually that it deserves its own post. Would you like to post it to !auai@programming.dev ?