![Checkout](https://naologiccom.imgix.net/website-update/general/checkout.png?auto=compress&w=64&fm=png)
Start free trial
Take Naologic for a spin today, no credit card needed and no obligations.
Start free trial Question
Rlhf - Did ChatGPT use reinforcement learning?
Answer
Conversational GPT and Instructional GPT both employ RLHF (Reinforcement Learning from Human Feedback) for model tuning.