Unverified50% confidenceOpinionExact time
Dan Klein argues that a system with about 80% or 90% accuracy is still unreleasable if one in ten customers is told a flight is booked when it is not; a system that is correct every time in 70% of scenarios is more valuable.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDan Klein argues that layering a second model on top of a system to check the first is a weak fix, because both can err and often fail on the same hard cases; he estimates that 80% checking 80% ends up at about 82%.65% similarUnverifiedGetting a system to work 90% of the time requires relatively limited effort, whereas making it reliably work 99.9% of the time may require dozens of times more investment.62% similarUnverifiedWhen techniques are explicitly specified, 93% of model proposals avoid clichés, but when only moments are given, that proportion drops to 75%–82%, indicating that models revert to the most formulaic approaches when left to their own devices.60% similarUnverified一个 90% 成功、10% 出错的工具调用系统几乎无法投入实际使用，因为单次错误会污染后续上下文造成级联失败59% similarVerifiedCalibrated confidence means that when the system gives a score of 0.9, the probability of being correct should be close to 90%.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1062300API
curl https://kongchang.com/api/v1/knowledge/claims/1062300MCP
get_claim(id=1062300)