Unverified50% confidenceOpinionExact time
作者强调大部分时间花在与AI的沟通上，真正的编码时间反而很短
1
Sources
50%
Confidence
Long-term
Relevance
7/24/2026
First Seen
Sources
Related Claims
VerifiedIn AI-assisted programming, the time developers spend on communication and correction often exceeds the actual coding time.81% similarUnverified借助Cursor的AI编程能力，原本可能需要数小时的编码工作被大幅压缩76% similarUnverifiedAccording to the presenter's observations, programmers at large tech companies may spend 70%–80% of their AI usage time writing Skills, with relatively little time spent directly writing code.74% similarUnverifiedAI programming scenarios involve large amounts of context input and lengthy code output, consuming tokens far faster than ordinary conversations, making them particularly prone to triggering Claude's usage limits.74% similarUnverifiedAI tools currently can significantly accelerate mainly the coding portion (approximately 15%–20%), while support for implicit work such as architectural design and requirements communication remains very limited.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/604472API
curl https://kongchang.com/api/v1/knowledge/claims/604472MCP
get_claim(id=604472)