Unverified50% confidenceTradeoffExact time
Recursive training makes extensive use of task completion rates and code execution results as reward signals, lacking explicit supervision for narrative consistency, which may lead to catastrophic forgetting of general language modeling capabilities, and this is more pronounced in models with small parameter counts.
1
Sources
50%
Confidence
Long-term
Relevance
9/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSimply stacking parameters without sufficient training data results in a model that is large but not capable; a leap in parameters must be accompanied by a proportionally expanded training corpus and computing power to realize capability gains.79% similarUnverifiedFor domains where code errors are extremely costly and high-quality training data is scarce, purpose-trained small-to-medium models may be more cost-effective and reliable than calling the most powerful general-purpose models.78% similarUnverifiedLarge language models possess Emergent Abilities, whereby after the model parameter scale and training data volume reach a certain threshold, capabilities not explicitly required by the training objective suddenly appear, such as a sense of humor, use of metaphor, and situational empathy77% similarUnverifiedAs the scale of pretrained models increases, many previously effective explicit knowledge injection techniques have gradually become ineffective or even produced negative effects.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/924346API
curl https://kongchang.com/api/v1/knowledge/claims/924346MCP
get_claim(id=924346)