Grounded execution · September 2026
Programming with Classifiers
The worked example, Lecter, retrieves exact source evidence. It is a small, inspectable operation with a replayable companion, not evidence of a general reasoning system.
Two studies of how models make decisions and what the evidence supports, each with its methods, retained evidence and limits.
Grounded execution · September 2026
The worked example, Lecter, retrieves exact source evidence. It is a small, inspectable operation with a replayable companion, not evidence of a general reasoning system.
Representation robustness · September 2026
How much should a decision change when the facts stay the same but their representation changes? This investigation examines representation robustness in Jev.
The first conversation is about your work: one representative workflow, what a useful result would be, and whether a paid pilot is worth doing.