[KongchangAI]
Verified65% confidenceFactExact time

开源模型权重一旦公开,攻击者可以通过微调(fine-tuning)移除模型的安全限制

3
Sources
65%
Confidence
Long-term
Relevance
8/7/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/702565
API
curl https://kongchang.com/api/v1/knowledge/claims/702565
MCP
get_claim(id=702565)