
Data Angels
286 posts

Data Angels
@data_angels
A Slack community connecting over 2000 women interested in data to resources for support, education, and opportunity | Created by @jessica_cherny









LLMs have made exciting progress on hard tasks! But they still struggle to analyze complex, unstructured documents (including today's Gemini 1.5 Pro 002). We (UC Berkeley) built 📜DocETL, an open-source, low-code system for LLM-powered data processing: data-people-group.github.io/blogs/2024/09/…

Even without the AI explosion, the operating environment of the data professional has been a constantly evolving space. We dug into that from a lot of directions on our latest episode with @imightbemary. analyticshour.io/2024/08/20/252…





Today we’re shipping some updates to our Magic AI assistant that make it more powerful, intuitive, and faster. We built these AI tools to help humans do their data work— writing queries, futzing with Python code, digging up answers— faster and with more confidence. Our goal is to augment, not replace, human insight. That means Magic isn't an "AI data analyst", because honestly, we don’t really think that should be a thing. Today's updates let you: * Generate multiple cells in your notebook with AI, chaining together SQL, Python, and Charts. * "@ mention" warehouse tables and dataframes to point Magic at specific resources. * Quickly switch between editing, fixing, and generating new cells with keyboard shortcuts * Work faster and more confidently with overall improvements to generation speed and accuracy. Check out some unedited examples of Magic being helpful in the thread below, and let us know what you think of these new features!







Update: won 2nd place! My partner Mattie (who I met in the elevator that morning) and I built an app that was inspired by a movie I'd watched the night before: "La La Land" The app combined sf film location data + bus route data to show you:







