Measuring

a decade working in analytics, I firmly imagine that observability and evaluation are essential for any LLM application running in production. Monitoring and metrics aren’t just nice-to-haves. They ensure your product is functioning...

I used to be working on a script the opposite day, and it was driving me nuts. It worked, sure, however it was just… slow. Really slow. I had that feeling that this...

Enhancing cross-product insights inside dbt workflowsFor multi-product corporations, one critical metric is commonly what known as “cross-product adoption”. (i.e. understanding how users engage with multiple offerings in a given product portfolio)One measure suggested to...

Deprioritizing quality sacrifices each software stability and velocity, resulting in costly issues. Investing in quality boosts speed and outcomes.Continuing our example, our hypothetical organization would find that the actual impact of their improvements is...

Though the brand new PyArrow backend for Pandas is bringing exciting features, it still looks disappointing when it comes to speed.Things are changingFor years now, Pandas have stood on the shoulders of NumPy because...

Though the brand new PyArrow backend for Pandas is bringing exciting features, it still looks disappointing when it comes to speed.Things are changingFor years now, Pandas have stood on the shoulders of NumPy because...

Goodhart’s law famously says: “When a measure becomes a goal, it ceases to be a great measure.” Although originally from economics, it’s something we've got to grapple with at OpenAI when determining the right way...