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)
若汝之投资组合验证者竟能窥见汝之界面耶?
Soham · 2026-05-24 · via DEV Community

此乃投献于Gemma四挑战:以Gemma四构建之


凯恩——将"我想成为一名人工智能工程师"转化为认证作品集


吾所建也

岁岁年年,兆民键击若此吾欲为人工智能工程师 搜索 Google,继而两星期沉浸于标签之海。路线图不知起于何处。YouTube 播放列表无结构。免费课程完成率仅十三。ChatGPT 路线图一闭标签即消。

吾建 Cairn ,盖其隙实存,百倍廉之替代编程训练营者,诚未现也。

凯恩乃个性化之智能学艺与生涯驱动器。尔以平实之英语告之志向——"欲六月内得人工智能工程之职,知Python之基,已建一Flask之应用" — 乃为君筑十二周之程:分阶段,设周次之里程碑,具实效之成果,选辑免费资源,以真实学成之效为评,并设项目以成之。非固定之文。乃活系统,随君之行而适。

然吾最性行者,乃君成事之时。

君以 GitHub 之库呈之。Cairn 引代码,试之而验。三阶评审流程 — 结构检验,由大语言模型驱动的代码审查,及多模态视觉审查,其中Gemma 4 12B实观审视运行应用之截图 — 若通过,则签发密码学认证凭证,置于cairn.dev/u/your-handle之公开作品集。此乃简历所载之URL。非“完成课程X”之虚言。实绩验证。

凡习得之器,有三失焉:

难题 如何凯恩应对之
路径之困 — "吾竟学何物耶?" 量身定制十二周之途,源于尔实际之始,非泛模板所成
无责无咎,自遗其志。 日日微醒,连日之迹,遇生事则自适重策。
无工作量证明——教程克隆者不得面试 多阶段项目验证,以HMAC签名凭据于公共作品集

此产品初为印度工程学子与转行者设——此乃一市集,有十兆以上活跃学子,其价高,不能入训练营(逾三十万卢比),然得免费资源,却无结构之助。然此问题亦存于全球,其架构亦映此。


演示

🎬 五分钟导览

🌐 实时应用 (https://cairnapp.netlify.app/)

👤 示例公开作品集 — 无需注册 https://cairnapp.netlify.app/example

例作集者,验实凯恩之表观最速之途也——乃用户十二周后置于履历之物也。


码文

链接GitHub仓库 (https://github.com/Soham-0047/cairn

此代码库乃全栈TypeScript单体代码库也:

frontend/    → Next.js 15 (App Router, SSR, Tailwind)
backend/     → Express + TypeScript + MongoDB + Mongoose
              └── llm/   → provider-agnostic router with fallback chains

入全景模式 退出全屏模式

凡可见之品牌——名、徽记、色、题句、号召之文、大语言模型之链——皆可于运行时编辑,不触代码。此非偶然;此乃使代码库可于下次极客马拉松无需重写而复用之由也/admin


如何使用Gemma 4

此乃吾欲详言之者,盖吾以为,趣旨所在非Gemma 4之模也,乃何故择三异者以应三事.

"径用最大之模"之弊

生成路径需载入五十余精选资源,如往昔学成者所成路径,及用户全貌之资料于一提示——继而推演周全,以成十二周之规划。此需巨模,具长境之窗。

自文本框中解析目标陈述——提取结构化字段如current_skillstarget_roletimeline_weeks — 乃微而时滞所系之萃取事也。以三百一十亿参数之模,为之则费工而迟滞矣。

觀他人運行應用之螢幕,察其用意是否合乎碼之稱述?此非文辭之問題也。

職事有三形,模型亦有三異。


模型一 — Gemma 4 4B:登陸時之目標解析也。

人键其志于平英,是文即至Gemma 4 4B,以取其序。

何故择4B?于Google AI Studio之免费层级,其运行约600毫秒。此调用每于用户导入之际,随其输入之精炼,屡次发生。此27B之模型,于此将感迟滞,未待用户启程,已耗尽速率限制。此任务有界:自短段中提取数字段。4B处理之,洁净、迅捷、且无偿。

// backend/src/llm/router.ts
{
  task: "parse_goal",
  primary: "gemma-4-4b",  // fast + cheap; perfect for extraction
  fallback: ["gemini-flash"]
}

入全屏模式 出全屏模式


模二—杰玛四二七B:路径生成与代码审查

重负在焉Gemma四二七亿经Google AI Studio与OpenRouter之免费Gemma 4端点。

生成路径,载用户之结构化画像,乃精选资源库之缩影(约五十项契合用户目标角色),并汇过往相似学习者之成果要旨——悉纳于一提示之内,而适于128K之语境窗。此模型须明辨诸题之相系,实然周时之数,及何种项目实能彰显目标角色所需之技艺。此非小模型所能任之任也。

同此模态,亦司代码评审于项目评估之第二阶:览多文件之仓库快照,而辨其码实应 README 所言,抑或显其技乃用户所习,及其阙失所在。多文件代码之推究,涉境深远,此 27B 之价值所在也。

SYSTEM: You are an expert career coach generating a personalized learning path.
You have access to {N} similar-profile learners' actual completed paths and outcomes.
Prefer concrete projects over passive content...

[resource corpus subset]
[similar past learner paths with outcomes]
[user's profile + target role + weekly hours]

OUTPUT: JSON path schema only, no preamble.

入全景模式 退出全屏模式


型号3 — Gemma 4 12B Vision: 侠之大者

此乃吾最心悦者.

用户提交其项目时,可上传其运行应用之四张屏幕截图,并附GitHub网址.Gemma 4 12B—具视能之变式—察实UI,以与代码及README所载相参验。

此可捕二失态,纯代码检视所遗也。

  • "观之精工,然码则草率"— 美观之模板,裹他人之理也
  • "代码尚可,然界面仅作敷衍之用" — README称应用可用;截屏示404错误。

余所知,无他评法如此。非仅"测试是否通过"。乃"示我以实装"。

// eval.service.ts — Stage 3
const visualReview = await llmRouter.call({
  task: "visual_eval",
  model: "gemma-4-12b-vision",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: visualEvalPrompt(repo, readme) },
        ...screenshots.map(s => ({ type: "image_url", image_url: s }))
      ]
    }
  ]
});

全屏模式 退出全屏模式

评鉴之页,示人以明,何供者何模,司何段也。此透明之设,意深焉——凡投项目者,皆得见模型之择,非徒藏于文牍耳。


通管全段

User submits GitHub repo + screenshots
         │
         ▼
Stage 1: Structural (deterministic)
  • README present?
  • Commit count + history
  • Tests exist?
  • File tree size reasonable?
         │
         ▼
Stage 2: Code review  →  Gemma 4 27B
  • Does code match README claims?
  • Originality vs known tutorial repos
  • Domain-specific checks (ML training loops? Backend auth?)
         │
         ▼
Stage 3: Visual review  →  Gemma 4 12B (vision)
  • Does the UI match what the code claims?
  • Polish level: shipped / demo / prototype?
  • Per-screenshot findings
         │
         ▼
Stage 4: Synthesis
  • Weighted score (pass threshold: ≥0.65 + originality ≥0.55)
  • If passing: HMAC-signed credential → public portfolio
  • If failing: specific, actionable feedback

入全景模式 出全屏模式


供者路由兼备退回

此LLM路由器乃三百余行之模组,于Redis中追踪各供者速率限制之剩余额度,俟免费层级用尽则自动切换。

Google AI Studio  →  OpenRouter (Gemma 4 free)  →  Gemini 2.5 Pro  →  DeepSeek V3

Enter fullscreen mode Exit fullscreen mode

无用户可见之失。不致意外之账——每路有月费之限;若免费之级尽,则路由拒呼,示优雅之降级语,而非失控击付付费之端。

全表路由,可于运行时由/admin/providers编辑。易Gemma 4为其他型号,乃UI之变,非码之变。吾故为之。


何以此乃Gemma 4之提交,而非"具Gemma标识之Gemini提交"

三款Gemma变体皆以Google AI Studio之免费层级为首要供给。27B任务之备选乃OpenRouter之免费google/gemma-4-27b之端点非Gemini也。视之评无非Gemma之备;若Gemma 4 12B不可得,则第三阶段遂废,其评标为"独评代码"。多模态之故事惟与Gemma 4相合。


技术之堆

  • 前端: Next.js 15(应用路由,服务器端渲染),React 18,TypeScript,Tailwind CSS,NextAuth
  • 后端: 节点二十,Express,TypeScript,Mongoose,MongoDB Atlas
  • LLM 路由: 自定义提供者无关路由 — Google AI Studio,OpenRouter,Groq,Cerebras,Together AI
  • 存储: MongoDB Atlas (路径/进度),Cloudflare R2 (屏幕截图)
  • 认证: GitHub OAuth 通过 NextAuth
  • 支付: Razorpay (印度UPI及卡支付), Stripe (全球)

独力而建,公之于众,为欲求首任AI工程之职,而无力耗资三十万卢比于训练营者。若尔属此——或尔知有合此描述者——Cairn即为此而设。