慣性聚合 高效追讀感興趣之博客、新聞、科技資訊
閱原文 以慣性聚合開啟

推薦訂閱源

博客园 - 司徒正美
V
V2EX
T
Tailwind CSS Blog
有赞技术团队
有赞技术团队
aimingoo的专栏
aimingoo的专栏
Apple Machine Learning Research
Apple Machine Learning Research
IT之家
IT之家
Blog — PlanetScale
Blog — PlanetScale
A
About on SuperTechFans
月光博客
月光博客
T
The Blog of Author Tim Ferriss
宝玉的分享
宝玉的分享
Martin Fowler
Martin Fowler
博客园 - 聂微东
The GitHub Blog
The GitHub Blog
V
Visual Studio Blog
WordPress大学
WordPress大学
酷 壳 – CoolShell
酷 壳 – CoolShell
Engineering at Meta
Engineering at Meta
GbyAI
GbyAI

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant Common SOC 2 Failures (Real World) Stop Vibe-Checking Your AI App: A Practical Guide to Evals How to Use SonarQube and SonarScanner Locally to Level Up Your Code Quality Your Next To-Do App Is Dead — I Replaced Mine with an OpenClaw AI Sign a Nostr event in 60 lines of Python using coincurve — no nostr-sdk, no nbxplorer, no rust toolchain ITGC Audit Explained Like You’re in Big 4 Patch Tuesday abril 2026: Microsoft parcha 163 vulnerabilidades y un zero-day en SharePoint Stop scraping everything: a better way to track competitor price changes Listing on MCPize + the Official MCP Registry while routing payments OUTSIDE the marketplace — how I kept 100% of my x402 revenue Building an AI-Powered Risk Intelligence System Using Serverless Architecture Why We Ripped Function Overloading Out of Our AI Toolchain Testing AI-Generated Code: How to Actually Know If It Works SaaS Churn Is Killing Your Business. Here Is What to Do About It (Without a Support Team) The Speed of AI Is No Longer Linear - And Self-Improving Models Are Why How to Implement RBAC for MCP Tools: A Practical Guide for Engineering Teams From Standard Quote to Persuasive Proposal: AI Automation for Arborists I built a CLI that scaffolds complete multi-tenant SaaS apps Axios CVE-2025–62718: The Silent SSRF Bug That Could Be Hiding in Your Node.js App Right Now The dashboard that ended our friendship Data Pipelines Explained Simply (and How to Build Them with Python)
人工智能之效率增益,确有其事,然于生产之中,增益之效稍逊。
Paulo Victor · 2026-05-24 · via DEV Community

今月有新文论于GenAI编程助手上载于arXiv,吾以为此乃双方论辩之清凉浴也。

是文遍览二十三篇研究,得见GenAI之助于编程,实有统计显著之效率增益。非幻术,非虚妄,乃真效也。

然其效不显,甚依乎境,于开源及企业之设,逊于控试。亦未睹统计有显著之学益。

此一言尽AI编程之辩:工具有助,然演示非实作也。

诚然,此感甚当。

吾用人工智能编程之器。其甚有裨益。能省 boilerplate、测试、重构、库之粘合、CLI 之标志,及彼烦扰之"吾知所欲,然不欲键之"之刻。

然若久处真实之系统,亦知大效生产之许诺为何若滑。生产编程非徒生代码而已,乃解怪异之制约,易旧系统而不坏之,议所有权,读日志,应浮移之测试,候评审,理发布,而忽觉简易之变触及2019年税则。

僕役可助其事之半。

非尽废之。

reality check

实验室非仓库也

制御之实验,以其能绝异所测之物也。予一队以人工智能之僕,予另一队无僕,较其成事之时或其出。此可告吾以某事。

然非尽告吾以万事。

凡工程之事,多非所居之阻。其务之述不备,其试之套迟缓,其构有旧史。高鉴者忆迁之役几破账目。显之庠因许可而禁。

AI之器,当问题明晰,反馈速捷时,其用为至。曰:"为之解析。"曰:"为之制验。"曰:"易此物形。"曰:"释此误。"曰:"草此庸常初稿。"

然其力稍弱,非在指键之勤,而在决断之难。

此别有深意,盖因多生产力之论,暗自游移于二境之间。工具有时于限域编程甚为可观,然于成熟公司代码库中,其增益仍显微薄。

非工具之过也。

由是瓶颈移矣。

生產力非一數也

人言"人工智能使开发者速",吾常欲问:速于何事?

速于成代码行乎?或然。

速于成小制乎?常然。

速于更易危要之系,其要不明,旧测存,跨队相倚,产险在焉?或然,或否。视乎其时。

是厌厌之答,实诚之答也.

软件之效能,乃诸般活动之集合:察真问题,谋变革,撰代码,试之,评之,布之,察之,负其果.

若团队唯计产出,则将高估其得。代码增矣,PR启矣,票移矣,人人皆觉碌碌,极今世之形。

然若评审之序渐增,事端愈难明释,而工师耗时更多以验所生之业,其净得实小于仪表所示.

所不适者,二者可同时为真。独任之师或感速,而众人之制未增若此.

企业之税,实也

开源与企业之境,其效显微,吾不怪也。

企业之软,有重负焉。其或繁于章制,然多实为复杂之缚。

尔有领域之则,合规之律,安卫之策,可察之准,发布之期,内库之藏,私钥之接,旧制之限,及客用之能,非今人所为。

凡编程之助,不自发知当处之实理。

其可推知于库,若导之以文,则读其籍;循其式,则随其常;命其器,则因其安。然未尝入乎众之制器之忆也。

是故吾常以境为基。得AI编程之利者,非惟购其华器,乃能显其地实:良测、良文、良册、良API、良例、良制、良评之俗耳。

AI非去工之熟,乃倍其功也。

若汝之码库条理分明,则助手有所效法;若汝之平台有金光大道,则可循之;若汝之测试蕴含真实行迹,则得有益之反馈;若汝之架构乃民间传说与 Slack 古物考古之术,则可自信自动化此混沌。

学之成效,当令后生忧心。

此文亦未发现对学习成果有统计学上显著之效。

此段当加意焉。

编程助手可助人成事,然非助人精进其能。教程、复制粘贴之答、框架之奇术,其形亘古如斯。人工智能惟使此径更畅耳。

未解其题,已得可行之码。可求明解,以为续进之资。可发其修,未具明理之模,以待来月之察。

于老成之工,此亦无妨。彼心已具结构,足以辨其效。助者,乃其用也。

少年者,其险异矣。若器示解于未尝苦思以成趣之前,则可缓学之痛而必需:自砺调试之性。

此非谓后辈当避人工智能之器。此乃愚举。今此等器已成职事之常。然善用之,乃需技艺。其旨非在"得解",而在"明此解之所以然,察其或谬之处,思继当查之事。"

业途之患,非在人工智能使学无由成,而在其使浅尝辄止似学。

此乃不同之物也。

何谓工程领袖当度者?

若吾领众,必不欲以虚气解AI之效。

吾欲度纤毫之诚。

寻常之事自始至合,其速几何?审阅之期,短耶长耶?所生之试,究捉真谬抑或徒饰异同?经智助之变,纠谬之事易耶难耶?初涉之工,其独立日进乎?

吾亦欲分事类。

若使人工智能治繁冗之工,可增其效三成;于模棱之构,几无增益;若团队懈怠,于机要之变,反损其利。

一数蔽之,则众妙隐矣。

智之策者,当绘其器之所长,其所平,其所需之制也。

实用之姿

吾今之姿,简矣:用人工智能以加速,然勿外委其权属。

使其草拟,使其解说,使其搜罗,使其撰冗杂之测试,使其勾勒变通之途,使其觅汝遗忘之API,使其为迁移脚本初度修订。

然后使人力之众,主其终成之形。

是故,评者犹需明变,测试犹需达意,架构之决犹需其理,生产之系犹需可察。必有人知此码之所以如是而非彼也.

此元析之用,在于不与两派易标语.

所谓"AI无用之虚"者谬矣,此中实有生产品之效。

所谓"人工智能使人人十倍"之论,亦谬,至少大而不周。世间软件之事,情理交错,协契繁复,非编程之助可化凡工为炫技之影.

事之实,不炫而实用:人工智能编程之助,实为杠杆,惟周遭工程之系能纳之.

此末句,乃职之所系也。

境愈明,则试愈精,习愈善,台愈优,度愈准,断愈明.

器可速成良工之制.

亦能致乱政于速乱.

故曰,用之可也.

然勿以速书为速工.

引据