Unverified50% confidenceFactExact time
Kepler's core technical promise is that the model never writes numbers—numbers and facts are provided by external databases and deterministic tools.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
Unverified应将大模型输出视为外部输入，必须经过完整校验才能进入核心业务，而非当作可信数据53% similarUnverifiedThe zero synthetic data generation commitment means that user data is used only for the current inference, and will not be transformed, retained, or used for any form of model training53% similarUnverified任何将LLM与真实数据或工具链接的系统都必须在架构设计阶段将输入默认不可信作为基本假设52% similarUnverifiedThe aerospace software domain has long relied on formal verification and deterministic algorithms, because neural networks may exhibit unpredictable behavior on out-of-distribution inputs.51% similarUnverifiedThe user stated that the models require extremely detailed prompts, and even when a standardized prompt is provided, the output remains difficult to trust.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1011240API
curl https://kongchang.com/api/v1/knowledge/claims/1011240MCP
get_claim(id=1011240)