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)
谷歌抗重力2.0:集成开发环境已死,长存智能代理之乐章
Mohammed Aya · 2026-05-24 · via DEV Community

此乃投于Google I/O写作之挑战

吾悟吾之IDE已成博物馆之陈设也

吾业编程八载。吾之开发之境,神圣也——精调之Neovim键位,不可或缺之VS Code插件十数,及经月完善之终端配置。故当Google于I/O 2026年宣Antigravity 2.0,称其为"以代理为先之开发平台"时,吾初念欲斥之为一如AI编程助手上演之 autocomplete 之戏,欲使吾之生涯尽付其 autocomplete 之手。

继而观其演示。软件工程总监Varun Mohan立于台上,指挥群AI之使,自无始之境,构筑一可用之OS核。非儿戏之例,非"hello world"之衍。乃真之操作系统,具内存管理、进程调度、文件系统之能。奇者何?复于斯新成之OS上,运行一实时光Doom之克隆。成本之计:不逾千美元。时之迁:十二分钟耳。

是时也,吾悟矣:Google非欲智吾IDE也,欲使其废也。

Antigravity 2.0之实(及其所系)

且破浮华。Antigravity 2.0者,Google应软件开发之根本变也:工作之单元非复文件,乃至代码库,乃任务矣。

此平台分五面相接而运。

  1. 桌面应用独立应用(非VS Code分支),全然围绕多智能体编排构建
  2. 命令行界面 (Command Line Interface)agy)以终端为先之作业流程,同此代理之具,以Go书之,为速
  3. 软件开发工具包(SDK): 自建定制代理,整合自用工具
  4. 管理代理接口:持久化之服务器端Linux沙盒,运行诸代理
  5. 企业平台:含治理、会话记忆与合规控制之Gemini企业代理平台

此异于GitHub Copilot、Cursor或他人工智能编程之器者何?反重力视代理为上宾,非助人者也。

并行执行之变局者

I/O大会上宣布之最被低估之功能乎? 多智能体并行编排

旧式开发之中,纵有AI之助,犹根本次第。汝书一函数,AI进善言,汝纳或拒,复次一函数。循环往复。较纯手工编程为速,然犹一事一时耳。

反重力2.0则颠覆此模式。予之高层任务,如“将此巨石重构为微服务”,则生众专司之使,并行其事:

  • 使A析依存,定服务之界
  • 使B立API之约于各服务
  • 使C造Terraform之配置于基设
  • 使D撰迁移之章
  • 智能体E生成周全之试

皆并行之。皆隔离于Linux沙盒。皆共协于共享之境.

吾试此于五万行之旧式Node.js应用,吾欲重构之已二年。此等工程,既启之,深叹而复闭之。吾以CLI授Antigravity 2.0之任:

agy task create "Break this monolith into domain-driven microservices. Maintain API compatibility. Generate deployment configs and migration plan."

入全景模式 退出全屏模式

既而二十三辰,吾得:

  • 七微服务,界域清朗
  • 每务有OpenAPI之规
  • Docker Compose与Kubernetes之制
  • 迁更之策,兼有回滚之序
  • 八百四十七单元之试

其善乎?非也。认证之务须重整,数据库迁移之脚本有隐微之竞态。然予得七成之先发于所惧之业。尤要者,得正其架构之择 — 择之需日研日谋者。

命令行器实通文脉

吾欲论agy,新之抗重 CLI 也,盖此乃 Google 勇下注之处也。

大抵 AI 编码之器,皆附于既有之流程。与吾之 IDE 相合,居吾之终端,然其本質乃應對者也。吾促之,彼應之。其心象也,曰「助人」。

agy则异于常者。乃以Go自筑,非徒裹API而已,且持恒久之境于尔之开物之际

此乃余所验之实务:

# Morning: Start a new feature
agy task create "Add rate limiting to all API endpoints"

# Agents generate middleware, tests, config schema
# I review, make some changes

# Afternoon: Something breaks in CI
agy diagnose "why is the rate limiting test failing in CI?"

# Without me providing any context, agy:
# - Pulls the CI logs
# - Identifies the test is failing because of timezone assumptions
# - Suggests a fix
# - Auto-commits with a proper commit message

# Later: Product asks for a change
agy modify "make rate limiting configurable per endpoint, not global"

# Agents refactor the middleware, update tests, regenerate docs

入全景式视界 出全景式视界。

察其未行之事:吾未复制粘贴错误日志。未释"速率限制"所指。未指明更改何文件。命令行界面已通晓之。任之境也晨间所得之见,持守一整天。

此即"agent-first"之真意:此代理非汝所唤之器,乃共事之侣,持守工作之忆也。

经纬之理,实属荒诞

且论屋中大象:价码是也

反重力2.0增“AI超能”月费百金。此价不菲。举隅为证:

  • GitHub Copilot:月费十金
  • Cursor:月费二十金
  • Supermaven:月费十金

然此中数理,颇有趣味。彼操作系统内核之演示乎?十一时辰,不足千元之代币。吾等姑且保守,言需资深开发者(时值百五十元)两星期(八十时辰)方得手作。此乃万二千元之劳力之费。

而此智能代理,未及午餐之资,已为之事。

吾非谓代理人将取代开发者(此言非虚——代码须人审,架构之决需明断,而边界之例待巧思)。然其根本改易某些工作之经济:

  • 重构旧时代码之基
  • 撰作周全之测试套
  • 迁移框架或语言
  • 构建新务之骨架
  • 著述之业

此皆繁难而寡巧之事,巧者所恶,然不可阙也。此乃诸工之长处所存也

谷歌之失(且其事甚要)

反重力2.0之技,可称奇观,然未臻至善。有三事令吾忧:

1. 锁定之患,实有之

凡运行皆依 Gemini 3.5 Flash 之制。此平台与 Google 之模组栈密合无间。若于 Antigravity 构建繁复之众智工,即系于 Google 之基设、价码与模组之途。

较之Cursor,此可于Claude、GPT-4及本地模型间切换。抑或LangChain,此乃设计上即模型无差别。Google之围墙花园策略,或可使其优化更优,然则减损开发者之灵活性。

2. 企业之功能,隐于付费之墙

会话记忆,集中治理,合规控制——此非企业采用之可欲,乃其必需。之需,皆囿于 Gemini Enterprise Agent Platform 之层级

。此乃怪状,独开发者得试其桌面之用,而其司业欲采之,必经重大契约之商榷。似见 Google 欲兼得两端:以开发者之宣导致病毒式之采纳,以许可之收入谋企业之利。

三. "玄妙"之题

智者用之,则玄妙莫测;智者废之,则幽微难明。

吾问抗重2.0以优化数据库之询,其改写询式,更新索引,易缓存之策。效能增四成。善哉!然 其故何哉?何事致此?若吾须于子夜三时,于生产环境调试此,能否洞悉代理所为?

谷歌需更优之可解释性工具。非惟“此乃所变”之异同,更须“此乃吾择之由”之推演日志。何故吾作此选?

宏图远志:此间所向何方

抗重力2.0非惟速编之术,实乃软件开发之先声也。

吾五年之期:

  • 初学者将统御灵使,而非撰拟陈文
  • 高阶者将专精构架与奇境之辨
  • "灵使之策"将成为核心技艺,犹Git之今时
  • 瓶颈非在码之撰述,而在需求之体认与权衡之抉择

此变局已肇端。如 Devin、Claude Code 及今之 Antigravity 2.0 等器,正使众知代理可统御全般流程,非惟能补续行末之词。

盛者非速于码,乃达于思也。思达者,能析系统之理,剖问题为能行之务,察机生之码,持严正之鉴。

试一周,吾诚荐之:

若欲用Antigravity 2.0,则:

  • 汝主事于Google之生态(Firebase,Android,Google Cloud)
  • 汝有重大重构或迁移之项目
  • 汝于审阅生成之码,调试之务,甚为安适
  • 汝重并行代理之调度,轻模型之变通

若欲越抗重力2.0,则

  • 汝需無模型工具之器
  • 尔公司需自建之解
  • 尔方初涉AI编程之器(可始以Copilot或Cursor)
  • 尔所业语言/框架,训数据寡而有限

于我而言,《抗重2.0》已得永驻吾之工具箱,然未尽替旧物。吾犹用《NeoVim》以速修。犹用《Claude》以释繁码。然吾若欲攻吾所延之业——此等需持恒之力、协众文之务——吾必先取agy

《I/O 2026》之真得

谷歌之意昭然若揭:开发之未来在于自主。非AI之助,非AI之强。自主。 盖因自主者,独立之行者,有能也,非待命之器也。

抗重力2.0之为标准抑或仅成谷歌荒冢之实验,犹未可知。然其所引之念——多智能体协理,任务层级抽象,持久沙盒——此皆永驻矣。

吾人所知之IDE乎?今已成博物之器矣。


尝试抗重力2.0乎?尔之体验何如?留一言以闻——吾欲知吾之体验与众人同否,抑或独饮Kool-Aid耳。