Unverified50% confidenceFactExact time
When Claude encounters ambiguities during a task, it proactively asks questions, with the final decision remaining in the user's hands.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/16/2026
First Seen
Valid until: 12/15/2026
Sources
Related Entities
Related Claims
UnverifiedAnthropic has designed a mechanism whereby Claude can ignore instructions in claude.md if their content is not highly relevant to the current task.68% similarUnverifiedAnthropic found that forcing Claude to strictly follow all claude.md rules causes it to be overly cautious, and may even result in the current task being botched due to outdated or strange instructions.65% similarUnverifiedUnlike Claude.md, which is loaded with every conversation, Skills are loaded on demand and only activated when a matching relevant request is detected.65% similarUnverified该项目引入主动消歧机制：当不确定性超过阈值时智能体不直接输出，而是主动向用户提出澄清问题65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/927432API
curl https://kongchang.com/api/v1/knowledge/claims/927432MCP
get_claim(id=927432)