In today's excellent episode, renowned technical author Antje Barth reveals how Amazon's prestigious "AGI Labs" are using Reinforcement Learning to make A.I. agents vastly more reliable.
In case you don't already know brilliant Antje:
Member of Technical Staff at Amazon AGI Labs, where she is responsible for bridging cutting-edge AI research with the global developer community.
Over 400,000 students have taken her "Generative A.I. with LLMs" course via DeepLearning.AI.
Multi-time bestselling author of O'Reilly books ("Generative A.I. on AWS" and "Data Science on AWS").
Holds a Diploma (equivalent to an undergraduate degree) in Computer Science from the University of Tübingen in Germany.
In this episode, which will be particularly appealing to hands-on practitioners but can be enjoyed by any interested listener, Antje covers:
"Nova Act", Amazon's new service for building reliable A.I. agents (available free to prototype with now).
How Nova Act achieves over 90% reliability by training on reinforcement learning "web gyms".
The future of agents, including multi-agent collaboration with humans.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.