Aug. 9, 2023, 4:46 p.m. | MLOps.community

MLOps.community www.youtube.com

// Abstract
This talk describes how we think about collecting RLHF data at Surge. We highlight the risks of collecting low-quality data for RLHF and describe some of the practical strategies we use in our full-stack RLHF data collection product.

// Bio
Andrew has a background in ML engineering and previously worked on bringing ML to the finance industry at Kensho and safeguarding elections at Twitter. He was the first engineering hire at Surge AI and has spent the last …

abstract andrew bio collection conference data data collection full-stack highlight llms low part practical practice prod product quality quality data risks rlhf stack strategies talk think

More from www.youtube.com / MLOps.community

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne