Unverified50% confidenceOpinionExact time
The core principle of dsh-superagent is to occupy as little human attention as possible: it acts only when requested or permitted by rules, asks only one specific question at a time, and decides whether to stop based on the scope of impact rather than the amount of work.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
DeepSeek's Open-Source Agent Teardown: 11,700 Stars but Only One Commit
bilibili翻车老头11/3/2026
Related Entities
Related Claims
UnverifiedThe first design principle of Super Agent is "exchange the least human attention for the greatest value".67% similarUnverifiedHuman-in-the-Loop does not require human confirmation at every step, but rather concentrates limited attention on irreversible, highly destructive nodes.60% similarUnverifiedThe truly deadly combination is not 'too many permissions', but 'too many permissions + never expiring + no monitoring'; the principle of least privilege only solves the static problem of 'what can be done'.60% similarUnverifiedClarifying follow-up questions are considered the most direct strategy for handling intent uncertainty, meaning the model proactively asks for clarification when its confidence falls below a threshold rather than rashly calling a tool.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1133479API
curl https://kongchang.com/api/v1/knowledge/claims/1133479MCP
get_claim(id=1133479)