[KongchangAI]
Expired90% confidenceFactExact time

AI模型越狱是指使用精心设计的提示或交互模式绕过模型内置的安全对齐机制,使其产生受限内容

7
Sources
90%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/45355
API
curl https://kongchang.com/api/v1/knowledge/claims/45355
MCP
get_claim(id=45355)