Are you wondering how large language models like ChatGPT and InstructGPT actually work?
One of the secret ingredients is RLHF - Reinforcement Learning from Human Feedback.
Let's dive into how RLHF works in 8 tweets!
RoomPlanDemo @WWDC2022 is magic! However, I did notice that the captured model shown on the phone and after you send it to your Mac are different. Any pointers?
@gluecode @fuseproject So true! We had our first in-person client meeting after like 2 years and it felt much better than any virtual ones we've had. The amount of interactivity and the fact that you don't just switch off once you're done with the "meeting". Did 3 week's worth of work in 3 days.