ChatGPT is almost fixed now.
At first ChatGPT lied and said Dr. Poi Sonai wasn't real but after pressing it further, it told the truth.
I hope OpenAI keeps up the hard work.
Syndicated from the fediverse. Read and engage on the original instance.
View original on piefed.socialView original on piefed.social
8 replies
[Yes or No Question]?
That's not right.
My AI has a 100% success rate for Yes or No questions within 2 tries, using the special prompting method I devised!
This reminded me of some quite implicit/challenging detail of the foreign language, Russian, I've been trying to learn for years now, mostly for jobs and art. Apparently, the following phrase is very common, well known, and understood by Russians to the point of its explicitly defined meaning, but dear...
Shows you how useless AI is.
for almost any given output, you can reply "that's not correct," or something similar, and AI will agree with you
That's not actually true.
You are correct, good catch! It is not actually true that you can reply “that’s not correct,” or something similar, and AI will agree with you.
Would you like for me to explain how AI works, and how I generate my responses?
You can also tell it to search for the answer and provide links to the primary sources.
OpenRacism