Unverified50% confidenceFactExact time
In 2016, Amodei et al. published the paper "Concrete Problems in AI Safety," systematically summarizing five core challenges including reward hacking, negative side effects, and scalable oversight.
1
Sources
50%
Confidence
Long-term
Relevance
9/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe phenomenon of reward hacking has been repeatedly observed in AI safety research practice.72% similarUnverified2024年已有多份威胁情报报告记录了攻击者利用AI辅助编写钓鱼邮件、生成恶意代码变体和自动化侦察流程的案例71% similarUnverifiedObfuscated Reward Hacking was prominently discussed by OpenAI in its 2024 safety evaluation report on the o1 model.71% similarUnverifiedFollowing the AI's zero findings, manual review discovered 6 CVE-level security issues in the curl project.70% similarUnverifiedThe Ministry of Industry and Information Technology issued a security warning regarding a type of AI Agent tool, listing multiple vulnerabilities.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/862865API
curl https://kongchang.com/api/v1/knowledge/claims/862865MCP
get_claim(id=862865)