Read the following text.
What is the function of PPO in training ChatGPT?
- It helps the model learn from human feedback
- It helps the model optimise its performance
- It helps the model generate coherent and fluent text
- It helps the model interact in a conversational way
Answer as written by the student:
The correct answer is B. It helps the model optimise its performance.
Step-by-step explanation of the answer:
The rest of the post is locked. Join Teachoo Black to see the full post.