
ChatGPT goes prime time!
Practical AI
How Chat GPT Was Trained
Chat GPT was trained using a reinforcement learning approach, and other models using this same approach are also pretrained language models./nThe first reward model is trained to take in a prompt and a response and score it like a human would score it according to preference./nThe second reward model is trained to take in a prompt and a response and output a prediction of what a human preference might be on this output.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.