Sharon Zhou

Co-founder and CEO
Lamini

Presentation Title:

Building trustworthy domain-specific AI agents

Presentation Summary:

Atom icon for The AI Conference 2023, a groundbreaking two-day event on AGI, LLMs, Infrastructure, Alignment, AI Startups, and Neural Architectures.

LLMs are powerful but their non-deterministic nature makes steering them toward accuracy a challenge.

Brain icon for The AI Conference 2023, a groundbreaking two-day event on AGI, LLMs, Infrastructure, Alignment, AI Startups, and Neural Architectures.​In this session, we’ll provide a blueprint for building trustworthy domain-specific AI agents that breaks down each of the following components:

  • Generating high-quality synthetic training datasets
  • Leveraging different LLM adaption techniques based on your domain and use case
  • Creating agentic evaluation pipelines
  • Iterating to higher levels of accuracy and complexity
REGISTER NOW
Picture of About | Sharon Zhou

About | Sharon Zhou

Dr. Sharon Zhou is the co-founder and CEO of Lamini, which has won this year’s VentureBeat Gen AI Startup Award and has been recognized as a Forbes Cloud 100 Rising Star. As a former faculty member at Stanford, she led a 50+ person Generative AI research group and published award-winning papers in generative AI. Sharon teaches some of the most popular AI courses on Coursera, including Fine-tuning LLMs, reaching millions of professionals.

She earned her PhD in AI from Stanford, where she was advised by Dr. Andrew Ng. Before her PhD, she worked as an AI product manager at Google. She received her bachelor's degree in computer science and Classics from Harvard. Additionally, Sharon has served as an AI advisor in Washington, D.C., and has been featured in MIT Technology Review’s 35 Under 35 list.