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)
吾尝遍试Google I/O 2026开发者之具,汝勿须劳神——此间实情,何者可用,何者不可,今悉陈之。
Mamoor Ahmad · 2026-05-24 · via DEV Community

此乃投于Google I/O写作之赛

Google I/O 2026 Banner

🎬其境

Google I/O 2026于两时之内布公告之墙

🔥 Gemini 3.5之速
🤖 Antigravity 2.0
🛡️ Firebase AI之智
🌐 WebMCP
🎨 Stitch
智灵·儒尔斯
目之智,万象皆通。

主旨之糖分激增也.

Mind Blown GIF

吾所阅之回顾,皆选公告并解释之。此有益。然未答吾于直播既毕时所问之实。

🤔 吾今日用之,于实事,而无败亡之患者,何物也?

吾乃度此四十八时辰,以筑之。I/O 2026 之新器也。非演示之项目,非“你好世界”。真欲融入实际之流程。

此乃所发生之事。


吾所试之四器

吾择工具有涉乎栈之异部:

# 工具 其效何为
1️⃣ Antigravity CLI 1.0.2 继Gemini CLI之后——代理之调遣
2️⃣ Gemini 3.5 Flash 新之默认模型由AI Studio API所定
3️⃣ Firebase AI 逻辑 客户端 AI 推理之安全
WebMCP 使网页应用可被智能体解读之协议

吾尝各试其于特定之务非为教程。乃吾实欲发行之实事。🚀


1️⃣ 抗重力 CLI:未有人言之一百二十九技

Antigravity CLI Screenshot

众皆言Antigravity之多元路由(Gemini+Claude+GPT-OSS于一CLI中),诚为奇事。🆒

然实令吾工作之变者,/skills.

Antigravity自带129内置技能。非仅补全规则,实乃智能代理之行为。如:

  • 🔍agency-code-reviewer — 审核变更为提交前之更动
  • 🤖 agency-agentic-search-optimizer — 检核智能代理能否于尔之站成事
  • 📖 agency-codebase-onboarding-engineer — 助新者明不习之库藏

🧪 试验

吾试于实React/TypeScript之项目,一令:

"Create a skill that enforces TypeScript strict mode violations before any PR merge"

全屏模式 退出全屏模式

⚡ 重力反作用力之实

Step 1: Read tsconfig.json and package.json → understood the stack ✅
Step 2: Scanned src/ for existing type patterns ✅
Step 3: Ran git status → understood current state ✅
Step 4: Proposed SKILL.md + checker script + pre-commit hook ✅
Step 5: Asked for approval, then built all three ✅
Step 6: Created mock violations, ran hook against itself, verified ✅

进入全屏模式 退出全屏模式

Chef's Kiss GIF

✅ 佳处

一令。无手书之配置文件。预提交钩子方在用,将阻次 TypeScript 违犯.

⚠️ 恶处

此技存于寰宇之中~/.gemini/config/skills/非在项目之目录。是故,其可用及于四方。悉矣此机之上诸事。方便,然六十技艺相悖,殊为烦忧。😬

❌ 丑陋者

双子座命令行界面(开源,逾万贡献者)将停用六月十八日反重力者,密源,谷歌移开发者之器于其利器之堆。

此权衡,当察之。🫠

🏆 判词

技之系,诚有力。密源之迁,诚可忧。二事皆然。

⭐⭐⭐⭐ (4/5)


2️⃣ Gemini 3.5 速闪:速、廉,失一事

Gemini 3.5 Flash Speed Test

余以 AI Studio 激 Gemini API,以成内容概要之能。事简明:纳三千言之文,得结构化之要。

⚡ 速

多数输入,亚秒应之。较之 Gemini 1.5 Pro,等事而速显

Gemini 1.5 Pro:   ~2.3s average
Gemini 3.5 Flash: ~0.8s average  ← 3x faster 🚀

入全屏模式 出全屏模式

🎯 品质

长于萃取与撮要。稍欠精微 — 言及求其"争议之见"于论说之文,辄取显赫之论,而非激越之辩。

💰 费用

此中颇多玄机。Gemini 3.5 Flash 定价甚厉 适于高量使用。若汝建一器,日处数千文书,其利弊实存。📈

🚨 众人未言之事

上下文之态。 至128K字元,其理可应长输入。然吾察得 质量渐降,逾60K字元后尤甚。 — 模式渐失长篇之中隐匿之细。

Surprised Pikachu

此与诸开发者所报相符,然鲜有论及.

🏆 判词

于高量、结构化提取之务,甚优。无检索层,勿信其于长篇之细析。

⭐⭐⭐⭐ (4/5)


三、Firebase之智术:安危之理,即其事也

Firebase AI Logic Architecture

Firebase之智术,使君得以直运Gemini之推演,自客端发之——君之网应用或移应用,直与Google之API语,无需后端之介).

I/O之要旨,使此若显玄奇。🪄

然其实,犹有微言。

何谓真新:四层安全模型

┌─────────────────────────────────┐
│  Layer 1: App Check             │  ← Verifies requests from YOUR app
├─────────────────────────────────┤
│  Layer 2: Firestore Rules       │  ← Controls who can call the model
├─────────────────────────────────┤
│  Layer 3: Rate Limiting         │  ← Per-user throttling
├─────────────────────────────────┤
│  Layer 4: Output Filtering      │  ← Content safety on responses
└─────────────────────────────────┘

入全景模式 出全屏模式

此事为要,盖因客户端之智,素来有信义之患若 API 密钥存于浏览器,则人人可滥之。Firebase 之策,非能绝此患,然增其阻,使偶发之弊不至轻易。🔒

旧者何哉

推论之事。尔已能以AI Studio API自前端呼Gemini。Firebase AI Logic乃以Firebase之认证与安全生态裹此。

若尔已在Firebase → 无碍之合 ✅
若尔未在Firebase → 迁移之费实存 ❌

🕵️ 难处何在

客户端推理,谓汝提示结构见于浏览器网络标签凡应用之需,工程之巧为竞胜之要者,犹需后端之代理也。

🏆 裁决

善用于 Firebase 本地应用,需 AI 之能而无后端之繁。非安全攸关之应用中服务器端推论之替代品也。

⭐⭐⭐ (3/5)


4️⃣ WebMCP:最关紧要之宣告(然尚未成事)

WebMCP Protocol Diagram

WebMCP 乃一协议,使 Web 应用可显结构之信息于 AI 之代理。思之若 robots.txt 然。智能体交互 — 此以示AI爬虫,汝之应用能,非惟其页也.

🤔 此事之要

凡智能体之栈(如Gemini智能体、Antigravity、Jules等),必通网络应用,乃能与之相交互。WebMCP乃Google欲为此标准化之尝试也。

为何吾心未动

吾尝试于小应用中施以WebMCP,得见:

  • 📚 文牍匮乏——I/O会话仅述其要于四分钟之顷
  • 🔧 工具简陋——无CLI之模版,无验证之器,无测试之制
  • 📉 从者无己——今尚无巨构之框架用之
  • ❓此乃谷歌之议,非标准也——W3C/IETF之参与,未定

Waiting GIF

🏆 判词

候此间消息。勿急于建之

⭐⭐ (2/5)


📊 终局之记分牌

若欲用之则 若欲弃之则
🤖 反重力CLI ⭐⭐⭐⭐ 汝欲代理之开发流程 汝需开源之工具
Gemini 3.5 之速闪 ⭐⭐⭐⭐ 汝建高量之AI功能 汝需精微之长文解析
🛡️ Firebase AI之逻辑 ⭐⭐⭐ 尔已至 Firebase 尔需服务器端提示之防护
🌐 WebMCP ⭐⭐ 尔可从容试验 尔需今日即见效之物

💡 变我思虑之唯一事

Lightbulb GIF

技能之簿。毋庸置疑. 🏆

未至 I/O 2026 之期,吾之 AI 作业流程若此:

Open chat → Paste context → Get answer → Copy result
Open chat → Paste context → Get answer → Copy result
Open chat → Paste context → Get answer → Copy result
...forever 😩

入全屏模式 出全屏模式

其技能文件 乃逆转之操作:

Define behavior once (SKILL.md) → Agent executes autonomously → Forever ♾️

入全屏模式 出全屏模式

此非功能之增,实乃编程模型之异也。

吾所建之无障碍审查者,今已技艺娴熟第壹佰叁拾于吾机。其居在:

~/.gemini/config/skills/soilsense-accessibility-reviewer/SKILL.md

入全景模式 出全屏模式

凡未来之反重力之会,皆可召之。一提示所成,无编排之码。

💬 贰仟壹佰伍拾叁年叁月叁拾伍日之後,双子座叁点伍之閃電測試將成為過眼雲煙。一技能之檔案,能強制吾輩之標準於每項提交——此之謂累積。


🎯 君將何建?

吾甚好奇他人所見。君試此諸器於實項乎?何者有效?何者崩潰? 🤔

尤為所重者:

  • 🐧 诸于 Linux 之上行 Antigravity CLI(吾试之于 Windows)
  • 🔥 Firebase AI 之智用于实境(非徒示于众)
  • 🌐 WebMCP 之实见于天下

尔等之经验,请投于此下! 👇

至善之 I/O 覆盖,出自于实筑诸事之人,非徒观演者之流。 📺➡️🔨


善哉阅之!若此助尔择I/O之器,幸心印于下,并述己验于注。

Thanks GIF