Unverified50% confidenceOpinionExact time
Letting a model see the outputs of other models is essentially injecting additional information into the input, which is a different matter from whether models can develop emergent capabilities through interaction.
1
Sources
50%
Confidence
Long-term
Relevance
9/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedEach time a token is generated via a forward pass, the model must go through a complete multi-head attention computation and feed-forward network layers, with the amount of computation determined by the model's parameter scale77% similarVerifiedExcellent prompt engineering can improve the output quality of the same model several-fold, and in certain tasks can make small models match the performance of large models.76% similarUnverified提示词工程本质上是利用模型已有能力提供更多相关信息，并未扩展模型的能力边界75% similarUnverifiedThere is a positive correlation between a model's calibration capability and model scale; larger models can more finely distinguish between states of knowledge.74% similarUnverifiedThe knowledge of large models is implicitly encoded in parameters; once a model provides API services externally, its capabilities are at risk of being reverse-distilled.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/931939API
curl https://kongchang.com/api/v1/knowledge/claims/931939MCP
get_claim(id=931939)