Unverified60% confidenceFactTime unknown
When prompts are too long, large models experience an 'attention explosion' phenomenon, where excessively long inputs cause effective information to be lost.
2
Sources
60%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedOverly verbose, contradictory, or ambiguous system prompts cause the model's attention to become scattered, resulting in over-thinking or instruction-following failures; streamlining agents.md can improve the determinism of instruction following.80% similarUnverified过度膨胀的上下文会稀释模型注意力、抬高推理成本，甚至引入噪声导致幻觉80% similarUnverifiedIf fact extraction granularity is too coarse, it leads to overgeneralization and false triggering; if too fine, it cannot be reused across tasks, degrading the memory system into a simple dialogue cache.79% similarVerifiedEven models with a million-token context face an attention dilution problem when handling large codebases—when the context is too long, the model's attention to early content drops significantly.77% similarUnverified在长对话中早期的错误尝试和调试过程会持续占据上下文窗口，造成上下文污染并干扰后续推理准确性76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/26194API
curl https://kongchang.com/api/v1/knowledge/claims/26194MCP
get_claim(id=26194)