Using 600,546 digitized newspaper pages to measure how suffrage coverage changed from 1890 to 1920
Sometimes we need to calculate results based on contradictory filters. Without any action, these filters will lead to an empty result. Let's see how we can improve the data model to make it work.
Latest Articles
GPT-Live does the talking. A decision model tracks what’s confirmed and picks what to ask next.
Introducing CoQS-LSTM, a Coherent Quantum Long Short-Term Memory Architecture
The case for paying people to play when machines do the work
In basketball, field-goal percentage tells us how often a player makes a shot. But what about the shots’ difficulty? Let's use Python and machine learning to separate shot selection from shot making.
The demo is the easy part
Learn how to use Claude Code to write feature memos, review pull requests, and build visual HTML explainers, so you understand what your agents ship
Let’s start with a loan and work out what PD, LGD, and EAD tell us about losses and bank capital.
A 501B model that only activates 23B parameters per token sounds like a bargain, until you look at what it takes to host.
The hardest part is no longer getting the numbers. It's deciding what to do with them.
Latest Videos
Editor's Picks
Introducing CoQS-LSTM, a Coherent Quantum Long Short-Term Memory Architecture
The case for paying people to play when machines do the work
In basketball, field-goal percentage tells us how often a player makes a shot. But what about the shots’ difficulty? Let's use Python and machine learning to separate shot selection from shot making.
Learn how to use Claude Code to write feature memos, review pull requests, and build visual HTML explainers, so you understand what your agents ship
Let’s start with a loan and work out what PD, LGD, and EAD tell us about losses and bank capital.
The hardest part is no longer getting the numbers. It's deciding what to do with them.
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
Beyond basic ReAct loops: six production-oriented architectures for building autonomous, reliable, and scalable LLM agents.
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.