CONCEPT
Specification Error
A second new AI-era error category — the user's specification is incomplete in ways she did not know were possible, and the system produces a technically correct output that omits a requirement she never articulated because she did not know it needed articulating.
Where interpretation errors arise from ambiguity in what was said, specification errors arise from the absence of what was not said. The user asks for a sorting algorithm. The system provides one — correct, efficient, well-documented. But the user needed a stable sort (preserving the relative order of equal elements) and did not specify this requirement because she did not know it was relevant, did not think of it, or assumed the system would infer it. The system did exactly what was asked. The output is correct given the specification. The specification was incomplete. Chapter 4 of the Norman volume argues this represents a third error class that Norman's classical slip/mistake taxonomy cannot accommodate.
In The You On AI Field Guide
Specification errors are not the system's fault. Nor are they, in the traditional sense, the user's fault — she did not form an incorrect plan, only an incomplete one omitting