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

人人都是产品经理
人人都是产品经理
Apple Machine Learning Research
Apple Machine Learning Research
云风的 BLOG
云风的 BLOG
罗磊的独立博客
博客园 - 三生石上(FineUI控件)
量子位
GbyAI
GbyAI
腾讯CDC
T
Tailwind CSS Blog
博客园 - Franky
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
D
Docker
G
Google Developers Blog
aimingoo的专栏
aimingoo的专栏
The GitHub Blog
The GitHub Blog
Microsoft Security Blog
Microsoft Security Blog
Stack Overflow Blog
Stack Overflow Blog
Hugging Face - Blog
Hugging Face - Blog
小众软件
小众软件
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
N
Netflix TechBlog - Medium
Jina AI
Jina AI
IT之家
IT之家
Y
Y Combinator Blog

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
AI-driven development - It's a spectrum
adrianthedev · 2026-05-19 · via Hacker News - Newest: "AI"

I want to share my experience regarding AI-driven development.
I know it's not a new and shiny thing, and it's been around for a while now, but some things should need some time to take it through its paces.

What I want to emphasize is this series is that AI-driven development it's a spectrum. It's not a single thing you should use, it's not one setup that's universal or one tool that's the best. Not one "influencer" person out there is the only one that's right or wrong.
You need to figure out your workflow by yourself or with your team.

That might not be what you want, but that's the truth.
Your setup is unique to you and your workflow.
It's the same as your editor setup.
You might remember in 2014-2018 that there were people out there who were selling editor courses, or themes, plugins or settings.
That's what the people "needed" (or we thought we needed).
That was a time when editors were becoming so advanced and there were folks who were extending them to beyond editing simple files.

So, there were developers who didn't know that editors were capable of such things and they loved the content.
They loved that you can supercharge them, that you can make them minimalistic, that you can match the theme to your OS or visual style, or that you can use advanced keyboard shortcuts or macros to lighten the development load.

I feel that we are in the same boat now with AI-driven development.
We have these LLMs at our disposal which can do so many things and it's tough to discover everything.
There are so many tools which empower LLMs to do things, so many skills you can use that it may seem overwhelming.
In the beginning I used to install every MCP someone was recommending.
Then it was skills, so uninstall the MCPs and install every skill.
Then there were sets of skills (Impecable design, Compound Engineering).
Then, there are workflow differences. "You should start in your editor", "No, you should start in your terminal", "You should use Cursor", "Claude Code is the only thing you need", "Do all of your designs in X or Y"... It's truly, truly overwhelming and it feels like you're wasting much time on setting up the "perfect" environment and not get too much done.

I'm working on a series of posts to share how I got started and how I stay sane through all of this.
I'm not testing all the tools, but I'm not not testing anything.
It's a lot of threading the water and keeping my eyes open.