Unverified50% confidenceFactExact time
Even in large models ranging from 70B to 72B, the penetration rate of safety instructions remains below 10%, and increased scale does not make safety prompts more effective.
1
Sources
50%
Confidence
Long-term
Relevance
10/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedEven when a model supports a context window of 128K or longer, its effective utilization rate is far below the theoretical upper limit.67% similarUnverified即使模型标称支持128K甚至1M token的上下文窗口，其有效利用能力往往远低于标称值，实际可靠工作范围可能只有标称值的几分之一65% similarUnverifiedFine-tuning GridSFM with just 10 scenarios can reduce cost error to below 2% and bring feasibility detection above 90%; using 1,000 scenarios can reach in-sample accuracy levels.65% similarUnverified混合架构中，仅当规则匹配失败或置信度低于阈值时才调用大模型兜底，通常可减少60%-80%的API调用量65% similarUnverified领域微调后的7B模型在任务准确率上往往超越未经微调的70B通用模型，同时推理成本降低一个数量级65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/964069API
curl https://kongchang.com/api/v1/knowledge/claims/964069MCP
get_claim(id=964069)