Ok, so OpenAI says that ChatGPT is GPT-3.5, but with extensive fine-tuning applied, based on a complex multi-stage feedback process with human evaluators.
But at the same time, you can apparently just take the "raw" GPT-3.5, give it a prompt to behave like an assistant and get comparable results?
But at the same time, you can apparently just take the "raw" GPT-3.5, give it a prompt to behave like an assistant and get comparable results?
So was the whole RLHF process just cargo cult?