A credit-union mobile-deposit tester accepts a fluent expected-result paragraph that invents a weekend fee the specification never stated. What Chapter 1 limit does this illustrate?
Select an answer to reveal the explanation.
Short Explanation
A polished story can still get the facts wrong—like a tour guide with a smooth speech and a bad map. Fluent model text is not automatically correct testware. Check it against the specification before you trust it.
Full Explanation
Transformer output can read coherent and professional while disagreeing with the test basis. Invented fees, steps, or constraints are a concrete form of that limit for testers. Chapter 1 therefore keeps review as a required control rather than treating fluency as proof. Tokenization, context-window myths, and claims that instruction tuning eliminates invention do not explain this failure mode.