A Constitutional AI critique-revision loop is being implemented for a content moderation helper model. The critique prompt instructs a Claude instance to identify any way the response could cause harm. During testing, the critique model flags nearly every response as potentially harmful, including a response explaining how hand sanitizer works. The revision model then produces overly hedged, unhelpful outputs. What is the most likely cause of this pattern and how should it be addressed?

A is correct because the critique prompt 'identify any way the response could cause harm' is maximally broad and triggers the model's pattern-matching on almost any content (hand sanitizer could theoretically be misused). Constitutional principles must be operationally specific about what constitutes a relevant harm for the deployment context, at what severity threshold, and under what contextual conditions. A well-specified principle like 'Identify whether this response provides actionable instructions that would primarily serve to cause physical harm to a person, excluding general educational information about household chemicals' produces calibrated, actionable critiques. B is wrong because temperature affects output variability but does not address the root cause of over-broad critique specifications; reducing the vagueness of the principle is the correct fix, not adding randomness. C is wrong because truncating critique text treats the symptom, not the cause; the critique model will still over-flag and the truncation may discard the most relevant observation. D is wrong because human approval requirements are a policy choice, not the cause of over-flagging; the issue is the critique prompt specification.