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)
吾之观感于编程之AI
Paul J. Luca · 2026-05-24 · via DEV Community

引言

前帖余撰新器,论及用人工智能,书此。include-tidy(整洁)之用者Libclang(Libclang), 一庠序吾未尝涉猎者。

何助焉数也 正使人工智能(严言之,乃大语言模型),特指 Google 之 Gemini(盖因吾吝啬,不欲为 Claude 购费,尤非为吾所无营利之私业)。虽吾或撰续篇博文以述吾之经历,然简言之,人工智能使我免于读繁文牍,览教程,发问于邮列或 Stack Overflow,及候答(若其有之)。

此乃前所言之续作博文也。尔若久涉人工智能,则下文所述,恐不足为奇。未用人工智能于Tidy之前,吾仅以之应微末之务,或询偏僻之问。用之Tidy,实为吾首度“大用”人工智能之时。

若尔初遇吾之博客或吾,或疑“此何人耶?吾何故当重其言?”吾于机事,已涉四十年余,既为之好,亦为职业也。. 世有码匠,尤以老辈为甚,多疑于智械——常呼之为“强化的自动更正”。虽此言有几分技理之实,然犹为可惊。

提示之术

吾以为“提示工程”之名及其相称之“提示工程师”之衔,甚为虚浮(后者近乎“清洁工程师”),尔详尽明確——犹若尔若于Stack Overflow呈问也。

异于Stack Overflow,问旧题者不遭责,不阅FAQ者亦无罪;人亦不询尔何故欲为此;不闻轻慢之辞,亦无鄙薄之语;尔亦不不可。得解;不数秒,解自至。

虽此言甚美,然所答或谬。数度间,Gemini尝言当用无此API函数,后我指之,方自纠其误。

复次,汝所获之答,亦常仅基于尔确凿疑问。若思用人工智能,当如用猿猴之爪,恐汝得应答,名实相副,然有不期之果

举一例,吾初以示Gemini,欲成Tidy之命也。

撰一程式,以 clang 之 API,既得 C 或 C++ 之源文件,则列其上诸符(宏、常、函数、类型、变量等),并示其声于何文件、何行,或标“未知”若不可定之。

且显数屏之 C 代码,示 Libclang 之何文件所出。#include者,何功能以初始化及清理Libclang乎?又,如何解析源文件,遍历其抽象语法树乎?诚然,吾本可研读Libclang之教程,然Gemini之应,适吾所求。

固知其生成之程,远未周全。未措命令行之选,未理配置之文,未察谬误,未施色显,亦未遍析C、C++源码之偏微。此等事,当于来日数周内渐备。然吾已得善始矣.

寻常之事

用AI之便,尚有一善:可令其为吾辈行寻常之码,汝或可为之,然不欲为所扰,盖代码枯燥也。譬如,Tidy需预检命令行参数,察其前置者。-Xtidy欲分之为二数组:一为Tidy特有者,一为应原貌传于Libclang者。此乃吾所设之题也。

既予argcargvmainC程序中,选项有二:其一为(1)-Xtidy或可之选,此即或可之选也。-Xtidy前有之;二曰仅为一选项。"选项"者,短选项也,或长选项也。

吾欲操弄之argcargv如此则凡前置之选项皆-Xtidy分而别之tiny_argv数组与tiny_argc去矣argv剥尽其所有-Xtidy且次选之。

且之方才已正之数秒之内,皆无需我调试所难免之一位之误,若我自撰此码。

体悟

若为资深码匠,观其生成之码,可速辨其是否合宜。故于资深码匠而言,AI实为良助;若为初涉编程者(抑或非码匠也),则吾料汝必受猿爪之困.

寻觅谬误

复有一事可为之,既毕某项.c之后,.cpp之文件,乃上传之,而问曰:“汝能于此代码中察得谬误否?”且其能。然则汝岂能知其察得谬误否?故仍当为之立单元及其他之试。

其固能报虚警,如吾所遇者。c_chan 之项目也。以为吾用某互斥锁之术非是。诚然,此用互斥锁之法颇异,或亦能惑人。然亦确察数实谬,如结构成员未初值,并觉 tv_nsec 之属 timespec 结构之 宜在0至999999999之间,故需添码以验溢出。

人工智能未为之事

若夫众码之基,其大者非必直参乎码基之要旨。 tidy之例是也。

  • 唯十八分涉乎扫描之事#include指令与映射符号,以包含文件。
  • 26% 乃“器用”之码也(小函数,使余事易成)。
  • 25% 专为解析配置之文(句法析 TOML,义理解之,察谬误,示误文于行款)。
  • 15% 为泛型之数据结构(动数组,红黑树)。
  • 9% 为命令行解析。
  • 8% 为试验。

吾以人工智能之术助之与(非)书之) 以Libclang编代码,非为工具代码亦非配置文件,唯于命令行稍用(以分参数),非为测试。

启示

吾此博客之志,唯欲述吾于AI之于软件开发之印象尔。吾料众议必询吾于软件开发之全局所思,故今且明言。

虽AI之喧嚣必将继续,然如吾言,其助吾甚矣。数也 配 Tidy。此乃软件开发之变局。由经验程序员操之,则如加薪之助。吾今非复初学,故不能直论初学者用 AI 之状。此亦加薪之助,然初学者(或非)程序员见之,不能辨其谬误或缺安全之码。必多数据泄露与诉讼之事。

汝必闻之(或不幸亲历之),科技诸公司纷纷裁撤。吾尝言,然,裁撤者众,然吾以为,人工智能实为替罪羊,使CEO不显无能,使公司不显困顿。裁撤之由,与往昔无异:

  • 公司愚行,滥招之甚。
  • 新产或新务未成.
  • 公司财困.

此皆使CEO显无能。反若诿咎于AI,则CEO可显睿智,既采前沿科技,复节开支——此二者皆得华尔街之赏.

至于裁人,尚有由焉。无能之CEO:

  • 或竟信诸喧嚣,以为之以人工智能代开发者。

思此境焉。尔为科技之司首长,售旗舰软件,有众客户。司有百匠。月均增一新术,补十谬。尔欲增术补谬,然不能增匠。今智械至,有二途:

  1. 月增一新,修十弊,而减人减费。
  2. 每月增二乃至三新功能,且补三十之弊,而使开发者之数如一,以人工智能为助推。

何正常之CEO,择一而思曰:“吾等安于今之进退,客亦然”?择二则客愈悦,且或能更引新客。诚然,已有之研证此说。

故若君受裁撤之苦,或可稍得慰藉(schadenfreude)。 或许CEO无能之虞。

结论

人工智能之存,十有八九矣。实乃开发者之助。诚然,将有动荡、并购,兼数家破产,盖因至少于今,经营人工智能乃大出血。使人工智能获利事则异矣。如Google之辈,有他源之财(广告),可永续资AI;Anthropic则不然。方才始获微利初见如此。然其能否成事,未可知也。续之谋利之事。后数载可见分晓。