When OpenAI makes an improved model, do they just correct its “wrong answers” till it spits out more correct-ness?

350 viewsOtherTechnology

When OpenAI makes an improved model, do they just correct its “wrong answers” till it spits out more correct-ness?

In: Technology

5 Answers

Anonymous 0 Comments

It’s less about right and wrong and more about getting it to understand what is being asked. Providing better pathways for word association and context means that the model can interpret the query and can work out from context what it is being asked to provide.

You are viewing 1 out of 5 answers, click here to view all answers.