Expired30% confidenceFactTime unknown
Anthropic decided to seal the Mythos model for safety reasons, as its capabilities in certain dimensions exceed the coverage of the current safety evaluation framework.
1
Sources
30%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedAnthropic在其Claude的设计文档中将可纠正性机制称为'corrigibility'，视为安全AI系统的核心属性之一72% similarUnverifiedAnthropic提出「宪法AI」、OpenAI提出「模型规格」等对齐技术，主要面向价值观对齐，在限制模型执行异常指令方面提供一定安全加固但不应作为主要防御手段72% similarUnverifiedAnthropic officially explained the relevant mechanism as a measure to prevent order fraud and model distillation theft.71% similarUnverifiedAnthropic长期强调前沿模型可能带来的滥用风险，主张对模型权重的公开发布保持审慎甚至限制态度71% similarUnverifiedAnthropic以「宪法AI」安全训练方法著称66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/13842API
curl https://kongchang.com/api/v1/knowledge/claims/13842MCP
get_claim(id=13842)