✳flâneur — a map of the web's best reading

Tips and Code for Empirical Research Workflows — LessWrong

lesswrong.com · 6,836 words · saved by 1 readers

Our research is centered on empirical research with LLMs. If you are conducting similar research, these tips and tools may help streamline your workflow and increase experiment velocity. We are also releasing two repositories to promote sharing more tooling within the AI safety community. John Hughes is an independent alignment researcher working with Ethan Perez and was a MATS mentee in the Summer of 2023. In Ethan's previous writeup on research tips, he explains the criteria that strong collaborators often have, and he puts 70% weight on "getting ideas to work quickly." Part of being able to do this is knowing what tools there are at your disposal. This post, written primarily by John, shares the tools and principles we both use to increase our experimental velocity. Many readers will already know much of this, but we wanted to be comprehensive, so it is a good resource for new researchers (e.g., those starting MATS). If you are a well-versed experimentalist, we recommend checking ou

x Tips and Code for Empirical Research Workflows — LessWrong AI Practical Frontpage 2025 Top Fifty: 13 % 110 Tips and Code for Empirical Research Workflows by John Hughes , Ethan Perez 20th Jan 2025 AI Alignment Forum 23 min read 17 110 Ω 43 Our research is centered on empirical research with LLMs. If you are conducting similar research, these tips and tools may help streamline your workflow and increase experiment velocity. We are also releasing two repositories to promote sharing more tooling within the AI safety community. John Hughes is an independent alignment researcher working with Etha

Explore this link on the map →

related reading