Scoring Models and Prompts: Optimizing GenAI Decision Making | AWS Events

It seems like there is a new LLM released every day, and each seems to have a vastly different price, so how do you choose the right model for your use case? Is one prompt better than another? This session delves into Trellix research into the performance and efficacy of various AI models for cybersecurity and how our framework for continuous model scoring allows us to use different combinations of models for efficiency by defining model strengths and limits. We’ll walk through our journey of real-world examples in which we use AI to make critical decisions to show the keys for developing your own long-term model and prompt management strategy.

Speakers:
Martin Holste, CTO Cloud and GenAI , Trellix

Learn more about AWS events: https://go.aws/events

Subscribe:
More AWS videos: http://bit.ly/2O3zS75
More AWS events videos: http://bit.ly/316g9t4

ABOUT AWS
Amazon Web Services (AWS) hosts events, both online and in-person, bringing the cloud computing community together to connect, collaborate, and learn from AWS experts. AWS is the world’s most comprehensive and broadly adopted cloud platform, offering over 200 fully featured services from data centers globally. Millions of customers—including the fastest-growing startups, largest enterprises, and leading government agencies—are using AWS to lower costs, become more agile, and innovate faster.

#AWSEvents