Unverified50% confidenceDecision RuleExact time
A rule was set in the experiment: any judgment with a confidence level below 60% would be directly handed over to human processing.
1
Sources
50%
Confidence
Long-term
Relevance
10/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn 10%–25% of cases, reasoning about the hypothetical grader pulled the agent's work away from the user's original specification.71% similarUnverifiedResearch shows that in certain tasks, simply changing '请判断' to '请分析' in a prompt can cause accuracy fluctuations of 5–10 percentage points.71% similarUnverified斯坦福大学人机交互研究组实验显示，即便自动化系统建议明显错误，参与者采纳错误建议的概率仍高达60%以上70% similarUnverifiedThe 80% rule means that when an AI's confidence in a judgment reaches or exceeds 80%, the system directly executes the result (writing it back to the data); when it falls below this threshold, the case is handed over for human review.69% similarUnverifiedThe author recommends designing the Agent's confidence threshold as follows: execute autonomously above 90%, present an intermediate state for user confirmation between 60% and 90%, and below 60% forcibly acknowledge uncertainty without guessing.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/993713API
curl https://kongchang.com/api/v1/knowledge/claims/993713MCP
get_claim(id=993713)