Unverified50% confidenceFactExact time
OpenAI公开发布了Model Spec（模型规格文档），规定模型不应模拟浪漫情感、不应假装拥有主观体验、在用户表达离开意图时应尊重其自主权
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/26/2026
First Seen
Valid until: 11/24/2026
Sources
Related Entities
Related Claims
UnverifiedBoth OpenAI and Anthropic have explicitly stated that the only reliable way to determine a model's true identity is through the model identifier (model ID) returned by the official API, not through the model's self-description in conversation.70% similarUnverifiedOpenAI模型规范中存在明确的信任层级：OpenAI训练时植入的价值观 > Developer Message > User Message68% similarUnverifiedOpenAI provides the strict:true and response_format:json_schema parameters, which can mathematically guarantee that the model does not output intent results outside the enumerated values.65% similarUnverifiedOnce Anthropic releases a new model, OpenAI typically follows shortly after with a competing product.64% similarUnverifiedFor domestic model providers not directly supported by LangChain, model_provider can be set to openai to invoke them via OpenAI-compatible mode.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/802203API
curl https://kongchang.com/api/v1/knowledge/claims/802203MCP
get_claim(id=802203)