Bakz T. Future
Could GPT-3 be used for basic information retrieval tasks like n-gram generation? I made a video to find out!
—
► Remember to Like, Comment, and Subscribe!
—
Connect with me:
Twitter – http://www.twitter.com/bakztfuture
Instagram – http://www.instagram.com/bakztfuture
Github – http://www.github.com/bakztfuture
Feel free to send me an email or just say hello:
bakztfuture@gmail.com
"Bakz, do you love me?"
It’s neat that non coders can now “code” so much simpler.
Awesome video
Nice! 🙂
intro music??????
You are wrong with your arguments at the end. You should read "The Wisdoms Of Crowds" by James Surowiecki. So the idea is, of course you can have bad writers. But the crowd minimize the error. You think that's crazy? George Hotz, the CEO of the comma ai, the self driving car project. Often have been asked, "You collecting bad data, so you collecting also bad driver data" And his response was allways, most people are damn good drivers. So also here the crowd intelligence minimize the error. You have also examples on chess.com The world agains GMs. The crowd is smart enough not to beat the Grandmaster but to be as good as a Grandmaster level
Can you have gpt3 fixing gpt3 outputs
Does GPT-3 understand your sample simply by performing the task of extending whatever you have written — or is there more to the instruction process?
Is boldfaced text different from unbolded text to GPT-3?
Maybe gpt4 will be able to do it