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

有赞技术团队
有赞技术团队
H
Hackread – Cybersecurity News, Data Breaches, AI and More
I
InfoQ
J
Java Code Geeks
Microsoft Security Blog
Microsoft Security Blog
G
Google Developers Blog
D
DataBreaches.Net
Recent Announcements
Recent Announcements
Microsoft Azure Blog
Microsoft Azure Blog
B
Blog RSS Feed
Y
Y Combinator Blog
博客园 - 【当耐特】
博客园 - 聂微东
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
大猫的无限游戏
大猫的无限游戏
P
Proofpoint News Feed
量子位
C
Check Point Blog
F
Fortinet All Blogs
罗磊的独立博客
Last Week in AI
Last Week in AI
GbyAI
GbyAI
L
LangChain Blog
博客园 - 司徒正美

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
DESIGN.md: The New Open Contract Between Designers and AI
kyanfeat · 2026-04-23 · via Hacker News - Newest: "AI"

The Brief:

  • The Problem. Solopreneurs waste hours fighting AI agents that generate generic UI

  • The Solution. Google open-sourced DESIGN.md. It blends machine-readable YAML with human-readable design rules.

  • The Impact. It shifts design from drawing to coding. Your brand rules sit in your root directory as the single source of truth.

  • The Result. AI agents build perfect, accessible interfaces on the first try.

Design used to be a bottleneck. You either paid consultants or suffered through endless CSS tweaking. DESIGN.md changed that. This format combines YAML tokens with Markdown philosophy. It has sparked an obsession: the awesome-design-md repository hit 35,000 stars in ten days.

Builders use these files to “prompt-inject” brand DNA into local AI agents. This “jailbreaks” tools like Cursor. It forces them to follow your style instead of generic defaults. The true hero is the Linter. It shifts the work from manual drawing to automated testing. The design-md-lint tool blocks any AI code that breaks your rules. If the AI misses a spacing scale or fails a contrast check, the build fails.

The hype focuses on speed. The reality is an opportunity to own your visual soul and protect your work.

Press enter or click to view image in full size

The Data: A Viral Standard

  • Viral Growth. Reached 62,600 stars and 7,800 forks by late April 2026.

  • Adherence. Projects report 85% fewer style errors.

  • Ecosystem. 69+ ready-to-use “Brand DNAs” available on getdesign.md.

  • Efficiency. Automated linting reduces design reviews from days to seconds.

  • Extract the DNA. Use design-md-gen to scrape your site’s CSS and map raw hex codes to roles.

  • Define the Why. Write for the AI.

  • Bad: “Primary color is Blue.”

  • Good: “Use our primary blue only for buttons. Keep the background neutral.”

  • Set the Guardrails. Install the CLI: npx @google/design-md lint. Add this to your local code checks. If the code breaks accessibility rules, the build stops. The linter blocks the error before it ever reaches your repository.

  • Deploy the Agent. Point your AI to the file. Your first prompt: “Read DESIGN.md. Make sure every UI component follows these rules.”

Google turned a “Vibe” into a “Variable.” Builders have already moved on. Design has reached a new level. It is no longer a static drawing meant for human eyes. It is an executable file that dictates system behavior. We are shifting from managing pixels to authoring logic.

Stop letting AI guess your brand. Use the public spec at getdesign.md or deploy the CMYK-Vault for absolute control.

I made this protocol to lock Cursor and Windsurf to your exact design DNA. No cloud. No style drift.

Get the CMYK-Vault

No posts