PyData Pittsburgh

One topic that came up in Jay's talk was reinforcement learning with human feedback (RLHF). For anyone who would like to go deeper on the topic, here are two sources I'd recommend:

Andrej Karpathy's "State of GPT" talk

https://www.youtube.com/watch?v=bZQun8Y4L2A

Chip Huyen's RLHF explainer

https://huyenchip.com/2023/05/02/rlhf.html

Here are the slides from my presentation if anyone is interested!

https://docs.google.com/presentation/d/1dgKgkWb0vSoe7AnKT4_sT_9FwDq74uc3DIL_mZGvews/edit?usp=sharing

If anyone is interested in signing up for our free beta, sign up at app.zerve.ai!

Due to a medical issue, we'll have to cancel and reschedule this event. Please keep an eye out for communications about a new date and time! Sorry for the short notice and any inconvenience this may cause.