ChatGPT and InstructGPT: Aligning Language Models to Human Intention
Deep Papers
00:00
Is There a Future for Machine Learning?
There's still like gaps in reliability and scurability. We're exploring a variety of things, including using models to help this process which are super interesting. One of the things I'm particularly interested in is moving beyond the framework of you know you have essentially like aligning to the average labeler. And so navigating that is going to be challenging and involves both kind of like machine learning interventions but also from a broader socio technical perspective.
Transcript
Play full episode
