153: ChatGPT
Programming Throwdown
00:00
How Do Human Raiders Can Improve Your GPT Results?
Dolly, you have the query text and an image generation. And that GPT, the thing they did there that is really interesting is this idea called reinforcement learning with human factors or RLHF. All of these models are variational, which means that in addition to passing in the query, you also pass in a random set of numbers. So every time you make a query, you're going to get a different answer for that query. They'll take like five answers for the same query from GPT three. They give it to a human and they ask the human to rank the five answers based on their own personal preference.
Transcript
Play full episode
