[KongchangAI]
Verified90% confidenceFactTime unknown

A 2022 Stanford University study found that developers using AI coding assistants had a significantly higher probability of writing code containing security vulnerabilities compared to a control group that did not use AI.

26
Sources
90%
Confidence
Long-term
Relevance
6/1/2026
First Seen

Sources

Cursor安全审查功能深度解析：AI代码安全的新标准
twittercursor_ai

Related Entities

Stanford Universitycompany

Related Claims

VerifiedSome engineers have pointed out that AI-generated code has issues in security review and performance optimization.84% similarUnverifiedGitHub的研究发现AI辅助编写的代码中安全缺陷引入率与手写代码相近，但因开发者对AI产出存在自动化偏见，这些缺陷更难在审查阶段被发现84% similar

Cite This Claim

Stable URI
https://kongchang.com/claim/26961
API
curl https://kongchang.com/api/v1/knowledge/claims/26961
MCP
get_claim(id=26961)