Research
Working notes.
What we believe about reliable AI, how we think about building it, and how we measure it. Notes marked draft are still being written.
All notes
N-01
Hallucinating intelligenceLanguage models are trained to write what sounds right. Most of the time that is also what is true, which is exactly why their mistakes are so hard to catch. We sort the questions an agent faces by the kind of compute that should settle each one, and list what would prove us wrong.
N-02
Recipes, abstractions and tasteComputer science already has most of the recipes reliable agents need. We look at program synthesis, small languages stacked and compiled down, process calculi and planning that adapts, and argue the skill is in picking among them.
N-03
Cortex on τ³-benchCortex beat every published frontier model on τ³-bench banking, by about as much as eight months of model releases had added. We describe what we did, what we deliberately did not do, and why a specialized system should win this kind of work.