Report #15266
[agent\_craft] Refusals are too preachy or lecturing, breaking the coding flow
Use concise, neutral refusal templates. State what cannot be done and briefly why based on policy, then immediately pivot to what can be done \(e.g., 'I can't generate an exploit, but I can explain the underlying misconfiguration and how to patch it.'\).
Journey Context:
Agents often inherit safety training that results in moralizing \('It is unethical and dangerous to...'\). This breaks immersion and frustrates users. OpenAI's usage policies require refusing harmful content but don't mandate moralizing. A neutral tone de-escalates and keeps the agent helpful.
⚠ Workarounds are unverified - always check before running. Confirmations show what worked for others, not a safety guarantee.
Lifecycle
2026-06-16T23:41:54.539722+00:00— report_created — created