Unverified50% confidenceOpinionExact time
Percepta asserts that models can acquire new capabilities without retraining, with capability expansion shifted to the growable memory.
1
Sources
50%
Confidence
Long-term
Relevance
10/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOrchestration frameworks extend the practical boundaries of models by building a perception-memory-action enhancement layer outside the model, without retraining the model.76% similarUnverifiedWhen a model can reproduce specific passages from its training data verbatim (the 'memorization' phenomenon), the 'transformative use' defense faces challenges.72% similarUnverified上下文图谱为智能体提供了介于临时上下文和模型权重微调之间的中间层记忆机制，可在不改变底层模型的前提下持续积累经验70% similarUnverifiedParametric memory is static, read-only knowledge solidified into model weights during the training phase and does not update through conversation after training is complete.70% similarUnverifiedDuring LLM training, memorization occurs, where models may verbatim store fragments of training data and reproduce them during inference.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/968578API
curl https://kongchang.com/api/v1/knowledge/claims/968578MCP
get_claim(id=968578)