John Schulman and Barret Zoph | ChatGPT and the Art of Post Training
HAI Seminar with John Schulman & Barret Zoph
Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.
Sign Up For Latest News
HAI Seminar with John Schulman & Barret Zoph
Open to Stanford community members! We are hosting an interactive orientation featuring faculty insights, networking, and opportunities to explore AI and data science research, programs, and resources across Stanford.
Open to Stanford community members! We are hosting an interactive orientation featuring faculty insights, networking, and opportunities to explore AI and data science research, programs, and resources across Stanford.
As AI moves beyond language into systems that can perceive, understand, and act in the physical world, a new frontier is emerging: world models—AI systems that build and maintain working representations of real environments to predict how they change in response to action.

As AI moves beyond language into systems that can perceive, understand, and act in the physical world, a new frontier is emerging: world models—AI systems that build and maintain working representations of real environments to predict how they change in response to action.
Sessions run Wednesdays from 4:30–5:30 PM in CoDa E160. Each session features a different Stanford speaker; talk titles are announced by the organizers.

Sessions run Wednesdays from 4:30–5:30 PM in CoDa E160. Each session features a different Stanford speaker; talk titles are announced by the organizers.
Abstract:
At this seminar, we’ll talk about the history and development process of ChatGPT, tracing its journey from initial prototypes to becoming a large-scale product and research effort. We’ll delve into the technical and operational challenges involved in post-training, including fine-tuning for conversational behavior, addressing alignment issues, and optimizing for large-scale deployment. Additionally, we’ll highlight some of the innovative solutions developed to tackle these challenges. To conclude, we’ll explore a set of open problems in the field, including ethical considerations, maintaining factual accuracy, and advancing the contextual understanding of conversational AI.

