Back at it again! PyData Boston + Cursor hackathon

Double feature by @fayshaw.bsky.social !

Popping in to Boston Python meetup for @fayshaw.bsky.social's talk on LASER for learning analysis github.com/laser-instit...

#odsc @allendowney.bsky.social difference in life expectancy over time between men and women

#odsc Pydata frequent flyer and great dude @allendowney.bsky.social doing his Bayesian best at ODSC

Using LLMs to better "model" how a piece of software works based on tests and contextual information #odsc

Analysis bottleneck - coding tools mean more code to review, and there's only so many reviewers #odsc

Briefly stopping by #ODSC - liked this statement that AGI isn't necessary for societal improvements

Open source foundation model for time series - MOMENT github.com/moment-times...

Just what is time series classification?

#pydata our next speakers Abhishek Murthy and Evans Addo about time series analysis

#pydatabos setting up an experiment to see how LLMs treat speaker transitions

#pydatabos interesting diagram for explaining transformers poloclub.github.io/transformer-...

#pydatabos LLMs vs humans as participants in studies

#pydatabos first up is Julia Mertens on LLMs hallucinating speaker transitions

#pydatabos back at it for April!

#pydatabos different flavors of graphs

#pydatabos our second speaker on sparql-tool how to have your agent use knowledge graphs

#pydatabos interesting use of color to draw attention to specific parts of the visual

#pydatabos two different ways to use the gofish syntax

#pydatabos Grouping principles behind the gofish visualization library

#pydatabos visualization of this "shrinking" trend is easy to miss depending on the choice of visual

#pydatabos welcome back! Pydata Boston March meetup (madness)!

#pydatabos recommended approach to building with AI agents

#pydatabos Part 2 of our cursor tutorial with Sebastian!

#pydatabos our February event! Focused on an introduction to building with Cursor

#pydatabos architecture of the Informed Consent Form workflow at Vertex

#pydatabos the Vertex journey for incorporating data science into clinical trial operations

#pydatabos our second speaker Lily Xu on a combined traditional + Gen AI use case

#pydatabos new RAG approaches focus more on knowledge graphs vs embeddings

#pydatabos expecting your user to frame the question correctly is ambitious - embeddings just take the query at its word

#pydatabos - I like this terminology - indexing vs query phase it's more specific for capturing this

#pydatabos Context rot - more irrelevant context worse quality

#pydatabos Back in action for 2026 - starting with Griffin Bishop on embeddings for RAG

#pydatabos Jupyter extension popularity per category

#pydatabos closing us out! Talking about the Jupyter extension ecosystem

#pydatabos example open and performant "small" LLM - xLM model

#pydatabos better usage of small language models for complex "autonomous" tasks

#pydatabos a practical talk on how to process large files

#pydatabos how to involve domain experts in LLM pipelines

#pydatabos discussing inherent biases in data fueling ML

#pydatabos the famed Eric Ma on how to code with agents

#pydatabos use of anomaly detection in predictive maintenance

#pydatabos day 3! Foundational models for times series anomaly detection!

#pydatabos the boring loop underlying agentic AI

#pydata last talk of the day! Sebastian Walkotter on Gen AI apps

#pydatabos the inimitable @allendowney.bsky.social presenting a Bayesian mystery

#pydatabos more on developing metrics for data products

#pydatabos Our second keynote Lisa Amini talking about what's next in AI

#pydatabos boundary failure in LLMs - asking a car dealership chatbot to solve complex mathematics