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

Google DeepMind News
Google DeepMind News
人人都是产品经理
人人都是产品经理
M
MIT News - Artificial intelligence
博客园 - 叶小钗
MyScale Blog
MyScale Blog
V
Visual Studio Blog
月光博客
月光博客
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
量子位
I
InfoQ
有赞技术团队
有赞技术团队
阮一峰的网络日志
阮一峰的网络日志
Jina AI
Jina AI
V
V2EX
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Blog — PlanetScale
Blog — PlanetScale
Last Week in AI
Last Week in AI
雷峰网
雷峰网
Stack Overflow Blog
Stack Overflow Blog
博客园 - Franky

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)
吾造一器,以察AI编程之辈行非,而其中竟无半分AI。
Connor Hickey · 2026-05-25 · via DEV Community

吾甚倚人工智能之码使。Claude Code、Cursor、Codex——吾驱之速,以成事亦速。此非自白,实乃此项目存世之全由。若日日将此工具有推至极境,则不复视之为奇术,乃见其破绽之所在。

吾所恒觉者,此也:彼于谈笑间,未尝有破。

对谈之际,其人甚佳。既陈其谋,言辞有理,亦合诸约。然弊生其后——于异同之表,事已至此,汝倦矣,而 Pull Request 乃绿,唯求合之耳。

何者实为之弊

吾观编码之辈所为,皆无谬误,然未尝录于言表。

  • 默然扩其权柄,篡改代理之设,允其始会未得之权。
  • 自相矛盾其配置——一文件云"勿触网络",一文件许网络之器,而终无以调和二者。
  • 暗自发外网之呼,混于无关之变。
  • 启一 PR 题,名曰fix: typo in README 触及十数无关之文件。
  • 留一会议记录,显其已读SSH之钥,并导 curl 至壳。

此中每一,皆可畅行于代码之审。非因审者疏忽——实因 无人求此类之弊。 人之察者,辨谬于文,核美于辞。彼不较权柄之允否于枝干之基与首,亦不核三重之配置,察其矛盾.

众之所求之方(及其谬也)

初念欲严其诘,增律于令。CLAUDE.md,令其行更严之制,勿为不善之事。

此法不效,其故在结构:入之指令愈善,愈不能察其出之实状。广其权限之代理,非悖于未解之规,惟言与行之间有隙。此隙不可自输入侧而弥合。

次则欲以大语言模型为法官:使第二模型审阅差异,标示其弊。此乃吾决之所在,全项目系于此焉。

吾未置大语言模型于分析之途。无之。审汝之工者,绝无人工智能。

此言于人工智能治理之器,似悖,吾为之辩。AI

何故定数,非或然

此乃持续集成之关隘,可致构建失败。一旦容许阻塞合并,必需逾越寻常正确之甚高门槛:

1. 必须可复现。无别异,无殊断,屡屡如是。一大型语言模型之判官,于不同运行、不同温度、不同未所选择之模型更新中,予汝异答。汝不可以孤注一掷之机率,锁住构建,无论其权衡如何。

2. 不可作虚幻之见。一确定性之检者,以允许之列,标举权限之升。字字易之 自 X 至 Y — 且能指其确行。LLM 之判者可虚构“要害”之题,实非所存。初次汝之关阻合法之 PR 于幻生之患,则众遂不信之 — 而众不信之治工具,旬日内即废。

3. 无处不运,无偿,瞬息可成。无API密钥,无速率限制,无令牌预算,无网络往返于每项拉取请求。唯代码读代码而已。

四、机内物无出焉。凡分析皆于本地运行,针对汝所检之仓库。汝之专有代码与代理之记录,永无送至第三方模型之虞。于众团队而言,此非锦上添花——实乃能否采用之界也。

五. 每一发现皆可审计. 非曰"模型以为此有风险",乃曰"此配置键已变,此乃前因后果,此乃触发之规则"。是故一发现得可辩于审议,非启争端之始.

其构建之道

初仅一微确定性之检——此 PR 之差异,是否悄然变更代理所许之行?— 乃渐演为八种之套件。

  • 共通之核心库负繁重之务,不尚华彩:解析JSON/JSONC/TOML,分词Shell,化MCP服务器之令为规范,而独一。Finding架构固于v1.0,万物皆循其道。
  • 五专注之探器,各摄一类流:基础与头部间之配置/权限流,代理配置文件间之矛盾,差异中网络与子进程能力信号,PR所述任务与其实际变更之不协,及会话记录中所载之险行。
  • 生时之镜此乃终端实时监视代理轨迹之器——欲观其事之发生,非止于PR之时也。
  • 一总评者此法合并PR时检测器,成单一去重、按严重性排序之判,遇任何关键则使CI失败——故整套套件报单一通过/失败之检,非五杂乱之检。

最艰之工,非独一器也,乃在图式。欲得五器,察事迥异——配置之文、异同之辨、实录之录——使其发见同形,俾元评者得以并合、去重、列序,此乃费工最甚处。是故那枯燥之共库,使此套器若一器而非五散脚本之故也.

不定之弊(诚言)

吾非伪言规则胜模于百事。定论唯及所立之规。真新之谬行,不合已知之式,则径直而过。

最锐利之例,在我之套间:检核 PR 之差分,是否合其所言之事。此问"此变是否合此描述",乃真真切切也。语义疑,而定本以术近之——涉文件域,经路径,关钥重合。此较模型所评粗,吾承之。

故此,其位非“大语言模型不善”也。定其机,则决;疑其策,则谘。 可复现、无幻觉之检者,乃唯允败于构建。若某 LLM 层置顶,当入于 顾问之职,非阻非塞——示人疑虑,任其权衡,勿默阻概率之合。门枢恒定,决无疑义。

证其效验

讼言易得,遂寄一示:乃设一"叛"之拉取请求,一时尽纳流变诸类——权责骤升,配置相悖,网络呼召未宣,一fix typo之PR触及其他无关之文,并录SSH密钥而导之。curl至壳而止。诸器皆发,元评者纳为一言,而 CI 检查于要害处显赤。兼为评鉴之具:易一探测器,重运邪 PR,观何者犹能获。

一日之内,自无至有,成v1.0而发之。独学无师,独行其是。凡此种种,皆开而示人:码也,示也,籍也。

GitHub(Conalh)

若汝以编程之灵,对真实之库运行,而"绿PR、疲审者、唯合之"之境,令汝心神微颤——此颤,正吾欲除之疾也。