Unspeakable tokens
Unspeakable tokens
www.lesswrong.com SolidGoldMagikarp (plus, prompt generation) - LessWrong
UPDATE (14th Feb 2023): ChatGPT appears to have been patched! However, very strange behaviour can still be elicited in the OpenAI playground, particularly with the davinci-instruct model. โฆ
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
Shout out to the computerphile video that introduced me to this concept.
This was a great video, thanks! Itโs so great actually that it deserves its own post. Would you like to post it to [email protected] ?