惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

V
Visual Studio Blog
博客园 - 司徒正美
Hugging Face - Blog
Hugging Face - Blog
博客园 - 叶小钗
The Cloudflare Blog
D
DataBreaches.Net
J
Java Code Geeks
G
Google Developers Blog
L
LangChain Blog
N
Netflix TechBlog - Medium
Stack Overflow Blog
Stack Overflow Blog
月光博客
月光博客
酷 壳 – CoolShell
酷 壳 – CoolShell
WordPress大学
WordPress大学
小众软件
小众软件
量子位
Apple Machine Learning Research
Apple Machine Learning Research
P
Proofpoint News Feed
博客园_首页
罗磊的独立博客
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
B
Blog
腾讯CDC

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
Forced to code without AI yesterday
Yousra S · 2026-05-03 · via DEV Community

Yousra S

Yesterday, I hit the rate limits on all my AI subscriptions.
Kimi K2. Claude Pro. Copilot.

I was blocked. For two hours.

I was just sitting there, staring at the message in Copilot CLI… wondering what to do next.

Do I:

  • Buy extra credits? Upgrade my plans to some “pro max” tier
  • Or just code by myself like I used to?

First option = more money. And honestly, I wasn’t ready to invest more.

Second option = free, but let’s be real… slower. More friction. All the “boring” parts: syntax, class declarations, wiring things together.

Still, I chose to code on my own.
And weirdly… I was excited.

I hadn’t done that in weeks. It felt like a long time.

But wow — I didn’t expect it to be that challenging.

I was working on a small feature: refactoring a top bar and customizing a greeting based on time (Good morning / Good evening, etc.).

Simple, right?
Yet Kotlin syntax didn’t come instantly. I had to pause on basic things — const, class declarations… stuff that used to be automatic.

That was the first wall.

Then came the second one: thinking in terms of logic.
I got so used to AI proposing the logic and me just reviewing it… that building it myself didn’t click right away.

I had to slow down. Think step by step. Rebuild that flow.

And that’s when something interesting happened.

I started enjoying it. A lot.

It took me back to the good old days, when I would build features end-to-end on my own.

There’s a different kind of satisfaction when you build something yourself vs delegating it to AI.

When I use AI, usually:
→ I ask for a plan based on brainstorming
→ I validate it
→ It implements

When I code myself:
→ I am the plan
→ I structure the thinking
→ I solve the problems in real time

It’s slower, yes. But it’s deeper.

You feel the decisions. You understand deeply the “why” not just the “what”.

Reviewing AI-generated code is not the same as writing it.
When you write it, the learning sticks differently.

Small takeaway from this experience: I’m going to keep at least 1 hour per week where I turn off AI completely and just code.

Not because AI is bad. It’s incredibly powerful and life changing.
But because I don’t want to lose that muscle. Also, I miss that sense of full ownership.

Curious — has anyone else felt this?
Who’s in? Anyone want to join me on this challenge?