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)
认知之隘:重思人工智能辅助发展之速
Lawrence Coo · 2026-05-24 · via DEV Community

自传统编程迁至能动编程,需有大智识之迁变。

为开发者者,其职迁为总持与稽核之任。汝设券,委诸如Claude Code之能动者以施行,稽其所为,请更易之。

此迁变之大弊,乃传统敏捷速率之估,不复如曩昔可算。

古之估费,多重人匠成码之时日。今以能动之码,撰述之暇几可不计;纵大项之务,亦不过半时辰至一时辰可成,非若昔日数日之久。然此非谓于此时窗内即可推出可制之软。

首者,开发者须与代理共谋其事。次者,乃最费时力者:代码复审。审人工智能所撰,以保其合乎架构之标准,且严遂其业务之志,此需全然不同之精力。

瓶颈非在开发者能速写代码,而在其心智之能详审之。

有谚语甚彰于软件开发,言此至当(常谓之Parkinson's Law of Triviality,或Bikeshshedding):五行之变,于PR中细察之;万行之更,则略不经思而了之。此盖源于大段代码审阅之巨劳于心神也。

以能动之码,此心智之疲当于程中早生;非积于开发之末,乃贯于其时也。

勿以实施之时计速,当以心智之繁为镜观之。

心智之繁何以算之?

深思此事后,吾以为复杂之事当分为五类,每类之中,又可评其低、中、高。

  • 筹谋之繁复
  • 评表面积
  • 心智之重
  • 测其繁复
  • 含糊不明

1. 策划之繁复

筹谋之会,其难几何?AI启程之前,设计之决断需固若何?

简易之CRUD端点,路径昭然可循者,也。触及三层架构,需新创抽象,或涉数据迁徙之功能,也。筹谋之繁简,定其时日之长短。/plan会晤之过,若失其宜,改之者几何?

二、审表面积

一评者需阅几卷?几行代码?

此可量也。五檔案二百行以下者,; 一念之变,评者可持之。逾十文或五百行以上者,则; 及是时,汝乃令评者持全系统之貌,虽非所设计,而求察微AI之失。

三. 认知负荷

观表面积者,乃阅时之困;认知负荷者,乃解意之难。二者殊途。

三文件之变,触及其认证与权限之制,较之十五文件之变,增一资源而具增删改查之能,其审之或难。认知之负,度审者须同时持系统之识,以察AI最易致误之失。

孤立自足之变,卑之。. 须通晓状态机、权限规则及异步协调模式者,方为盖风险非在单件之难,而在一误于众件相协之理,遂致谬误而诸试皆通。

四、测试之复杂

AI亦能撰试,然犹需有人设试之境,验仿作实映系统之行,并证偏例尽覆。境愈繁,外务桩愈众,合度之求愈增,皆增人力之费。

5. 疑义

此异于他者。人之为工,遇歧义之务于中程,则决断或诘问。若智械逢歧义之务,则自信而臆断;臆断之常近理,故人于检阅时多不觉察。

一票之歧义,非徒增固定之费,实倍诸般之耗。盖因票义不明,易致成果需重修;而重修则须再历全盘之计议、复审、质验之程。

化分数为数

量度形制,虽有益,然规划之板需数字。此乃有效之公式。

就规划、评审面、认知负荷、测试复杂度诸维度,以非线性尺度量之。低=一,中=三,高=六; 并之,此汝之本分自四至二十四不等。

此非线性乃有意为之。复杂之性非等比增减:持一繁复心智模型之审者,较之无持者,非止税负增半,实增三至四倍,盖无容错之余地。高值六者,映此不均之耗。二高相合,耗复叠加:审者须于一过中同时持二难模型,此较之分别持之,质上更艰。

则施之含糊之倍增器

  • 低歧义:×1.0(无调整;票证定义明晰)
  • 中庸之歧义:×1.25(有缺漏;预期将有所修正)
  • 高歧义:×1.5(需重修;AI或失其意)

四舍五入其数,乃映诸速率之点。

校准锚点在此处要紧:此等点表示人耗时非实施之时,乃常规之用。一點等於四時疾驰之速,其映射若此:

权衡之分数 速度之点 人之上
四至九 一磅 四时辰;专注计划速览
十至十四 二分 八时辰;终日人力专注
十五至十九 三分 十二时辰;计策检视质询历一日半
二十至廿三 五分 二十时辰;繁复计策重负检视
二十四至廿八 八分 三十二时辰;近一人周之工
二十九加 十三点 史诗;取货前须分拆

若汝队所用锚点异(每点二时辰,每点八时辰),则界域范围相应滑动;公式不变,唯查表移位

此非实施时辰。乃人力冗余时辰也凡真人所费于谋、察、核者,皆在AI所造之工也。

按票计之

此算非易,使开发者算之,需时日与经验,待其熟稔于工作之习、于机关之码,则自能了然于心。

及是时未至,产品经理与开发经理犹欲知其票速之可能,然以所需编码之量计之,非得正解(或得之而缘非其理)也。

是故吾为Claude Code制小技,取PM所建之票,详察其要,兼考代码之境,预谋其事,量其轻重。此技可由Dev Manager、Principal developer或team lead于票入 backlog meeting之前施之。或可显须改之事于呈票于众之前,若票之复杂,则可竖剖之;若票之简,则可并他票于一。

估者所生之策,非为定策,此当委诸开发者,由其研办而呈之。开发者自有建树之制,纵有智械相助亦然。然初策可予产品经理所需之讯,俾其创速程,于自主之域以达其功。

解除阻塞

匠者可助心智之劳,于开物成务之际,设制程式。其要,众可创机巧之察,较所生之码于 claude.md 之规、构架之则、初票之谋,俟人目未睹而先验之。

如是,则AI之代理可自省其码,于开发者察之先,已能察其隙。具初探AI之能,可除显弊,使开发者惟需察深微,不复需兼察二者。

有益之视器

吾为汝提供一助益之估量器,俾汝见诸般组合于全速之变。冀观其效,可助汝明其理!

https://lawrence72.github.io/claude-tools/calculator/