code red
Speaker

Will Hang

Member of Technical Staff @OpenAI, Former Founder, Previously @DeepMind, @Google Brain, @Snorkel AI

Will is a Member of Technical Staff at OpenAI and tech lead on efforts such as Agent Reinforcement Fine Tuning and Vision Fine Tuning. Prior to OpenAI, Will led interactive ML infrastructure at Snorkel AI, speaking at venues like the Ray Summit, and was a cofounder of include.ai, a Sequoia-backed company. Previously, Will spent time at DeepMind and Google Brain, where he was a coauthor on AlphaChip, with work appearing in venues like Nature and NeurIPS. Will studied computer science at Stanford.

Find Will Hang at:

Session

Fine Tuning the Enterprise: Reinforcement Learning in Practice

In this talk, we’ll discuss the Reinforcement Fine Tuning (RFT) platform, allowing you to train OpenAI models to reason better on your specific tasks to arrive at better answers.

Read more

Date

Tuesday Dec 16 / 11:30AM EST ( 50 minutes )

Location

Library Reading Room

Share