A theoretical advantage that didn't survive contact with a real benchmark.
Can an Apartment Search Agent Call the Model Fewer Times and Still Find Good Matches?
Large Language ModelsI traced 2,500 listing checks with Weights & Biases Weave, removed avoidable model work one change at a time, and scored every version against the same answers.
Latest
The activation function was never a fixed biological commitment but a working hypothesis revised under empirical pressure.
The budget nobody saw coming
How the way we represent data can change what we think the data is saying
Coding agents give us more time for discovery and our review practices should follow the analysis
In DAX, we reuse existing measures all the time when writing new measures. What happens when we write a measure based on another measure and try to change a filter already set in the nested measure?
One run, and what it actually proves
I Compacted 1,000 Apache Iceberg Files Into 6. Here’s What Happened to Query Performance.
Data EngineeringBenchmarking the impact of fewer, larger files across three SQL workloads
The real shift is bigger than productivity: AI is reshaping ownership, judgment, and the career path of data scientists.
Not every decision needs a decoder, generation Is not always a decision
Editor's Picks
The activation function was never a fixed biological commitment but a working hypothesis revised under empirical pressure.
How the way we represent data can change what we think the data is saying
Coding agents give us more time for discovery and our review practices should follow the analysis
The real shift is bigger than productivity: AI is reshaping ownership, judgment, and the career path of data scientists.
Not every decision needs a decoder, generation Is not always a decision
Here’s how to solve it exactly.
The Variable Newsletter
Sorting through the good, bad, and ambiguous aspects of vibe coding
Don't miss our most-read and -shared stories of the past month
Deep Dives
How statistical moments connect the mean, the variance, and higher powers of a distribution
First in a series on probabilistic forecasting for physical signals. Next: what happens when you roll the forecast forward more than one step.
When Codex is the right shape for the problem, when Claude Code is, and how I split 5 specialist agents between them on dense AI capacity work.
Why the skill-inflation panic is aimed at the wrong thing, and what it costs to make agent knowledge a build artifact instead of a file.
A real Weave project that regression-tests three OpenAI models against the exact reply format your app depends on.
I built a system that automatically discovers, verifies, and applies relevant requirements from earlier interactions without asking the user where they came from.
