Topic
Test-time compute
2 stories on this topic, newest first.
ResearchExplainer
What "reasoning" models actually do differently
Reasoning models are trained to spend tokens thinking before they answer. Here is what that training involves, why it works on some problems and not others, and how to decide when to pay for it.
ResearchAnalysis
Test-time compute changed the scaling roadmap. Here is what it costs
For a decade, progress meant bigger training runs. Now labs can trade inference compute for capability instead. That shifts the economics from capex at the lab to opex at the user, and it changes what "a better model" means.
