正在加载视频...

视频加载失败

Someone figured out why every AI-coded site looks the same, and shipped the fix. Most common attributes of an AI generated website: - Purple gradient at the top - Rounded cards - Frosted glass look - Inter font - Emoji as icons And a prompt: "Transform your workflow" to...

107,153 次观看 • 17 天前 •via X (Twitter)

40 条评论

Lohit sai 的头像
Lohit sai17 天前

creator of vibecurb here, glad the constraint rules are helping! working on a few enhancements this week 🙌

Ryo 的头像
Ryo17 天前

thanks brooo

Veee 的头像
Veee16 天前

Anytime

BAsh 的头像
BAsh17 天前

this is actually a good tool

KAGAWA 的头像
KAGAWA17 天前

Plug ins What a tek

Veee 的头像
Veee17 天前

Plugins is everything

Apollon Foivos Bakis 的头像
Apollon Foivos Bakis16 天前

Strong design constraints make agents more creative.

Pukerainbow 🤮🌈 的头像
Pukerainbow 🤮🌈17 天前

this is the fix AI coding needed, better constraints give models taste instead of letting them average every website they’ve seen

𝗧𝗼𝗯𝗶 的头像
𝗧𝗼𝗯𝗶17 天前

I knew it was gonna get fixed sooner or later.

Veee 的头像
Veee17 天前

when create your own portfolio though?

𝗧𝗼𝗯𝗶 的头像
𝗧𝗼𝗯𝗶17 天前

soon 😅

Big Gids👨‍🍳 的头像
Big Gids👨‍🍳17 天前

thanks brother

Veee 的头像
Veee16 天前

Anytime G

Kairo (⌁) 的头像
Kairo (⌁)17 天前

you can tell an AI made website before you even scroll sometimes

Captain web. 的头像
Captain web.17 天前

You are a great observant....

J A Z I I 的头像
J A Z I I17 天前

bro this looks so flipping cool

Veee 的头像
Veee16 天前

h3ll yeah man!

Ghost 的头像
Ghost17 天前

let me clone his ass

Zephyr ✪ 的头像
Zephyr ✪17 天前

already got something similar will add this

JDollar☂️ 的头像
JDollar☂️17 天前

thanks for sharing as always vee will check em out

Knowix 的头像
Knowix17 天前

this is so smart, I’m tired of seeing the same interface on every site

Josh 的头像
Josh17 天前

That’s quite an observation I literally think that’s the patter you need to follow creating to website or just a mere coincidence

dBoom 的头像
dBoom17 天前

This is a good example of why “better prompting” eventually turns into system design. The hard part is encoding what it should not default to. Constraints, rules, and reusable skills are becoming part of the product architecture.

DylanUX 的头像
DylanUX17 天前

Inter font and the purple gradient are basically a tell at this point, I can spot an AI-coded landing page in about two seconds now.

Zoha 的头像
Zoha16 天前

Wait bro, I really like inter font 😭 that's the font that I can trust will go with almost anything and looks good too.

Salman • Dusken.io 的头像
Salman • Dusken.io16 天前

so the fix is essentially forcing the AI to have an opinion on design

Brjan | AI Builder 的头像
Brjan | AI Builder16 天前

I get why those attributes are common, but I'm more curious about how they approached the fix to make sites feel unique again

Leo🦁 的头像
Leo🦁17 天前

Check out @mypipdev bro

Nuvora 的头像
Nuvora17 天前

Swapping Inter out is the fastest tell to kill — pin one specific typeface in the SKILL.md and half the sameness goes away before you touch the gradients.

Kaysta 的头像
Kaysta17 天前

thanks vee

Ryan Keary 的头像
Ryan Keary17 天前

i can spot them in about a second. same font, same purple, same hero layout

Kiro 的头像
Kiro16 天前

yeah cause the fix is just another prompt. the real issue is nobody's asking the site to solve a problem. it's all vibes over conversions. here's a tip: force your AI to design for a 3-second hook and a single CTA above the fold. purple gradient won't save your AOV.

Xman 的头像
Xman16 天前

This is why project rules matter more than endlessly tweaking prompts

griffin fuzzystripes 的头像
griffin fuzzystripes16 天前

They didn't copy. Twenty-seven machines, one 147-word brief, separate sandboxes — same room. Six independently named a fictional company Meridian. Floor plans can be physics. An arbitrary name is inheritance. #AI #LLM

Solution 的头像
Solution17 天前

Thanks for this vee

Max Bevza 的头像
Max Bevza17 天前

now websites will be more unique, lovely

Gabri Torres 的头像
Gabri Torres16 天前

Inter. That’s the giveaway.

Tucker King 的头像
Tucker King17 天前

I just opened this. I would have reused Inter and the purple wash and called it done.

Mahadev 的头像
Mahadev16 天前

Yep gonna use this one

Prompt Kracka 的头像
Prompt Kracka16 天前

"no strong opinions" is the whole bug. before you prompt, paste in two real references and name what you're stealing from each — the model can't average its way out of specific constraints.

相关视频

how to use Google's NEW open source Design.md + AI Skills to make your startup look like a $100 million company in 1 hour: 1. Design.md is an open source file from Google that captures the soul of a design. Typography, colors, spacing, all in one markdown file. You attach it to your prompt and your agent builds beautiful things every time. 2. Think of it this way. The HTML is the finished dish. The design.md is the recipe. The skills are the ingredients. Put them together and everything you build looks consistent and professional. 3. Don't create a design system from scratch. Find a brand you love. Linear, Stripe, Vercel, whatever resonates. Study it. Use ChatGPT or Claude to help you extract the design language into your own design.md file. 4. Build skills on top of your design.md. A landing page skill. A mobile app skill. A motion design skill. A slide deck skill. Each one references the same design.md so everything looks like it came from the same designer. 5. The biggest mistake people make: they nail one screen and then everything else looks generic. Design.md solves this. One file keeps every page, every format, every medium consistent. 6. Use it across everything. Your landing page. Your app. Your pitch deck. Your promo videos. Same DNA. Same taste. Same system. That's what separates a startup that looks real from one that looks vibe-coded. 7. Build a second brain for design inspiration. When you see something beautiful in the real world or online, capture it. Save it. When you're building something new, reference it. Taste is developed, not downloaded. 8. It's obvious but the difference between a product people trust and a product people bounce from is how it looks and feels. Design.md gives you that edge. you can watch below shoutout to Meng To for coming on The Startup Ideas Podcast (SIP) 🧃 and walking through his full workflow. if you want to use AI to actually build gorgeous designs, you'll want to use see this. watch

GREG ISENBERG

511,448 次观看 • 4 个月前

A DEVELOPER CONNECTED CLAUDE CODE TO OBSIDIAN SO HIS AI AGENT WOULD STOP FORGETTING THE PROJECT EVERY MORNING. Every coding session used to start the same way. Claude would understand the repo, fix the bug, explain the architecture, and then the moment the session ended, all of that context disappeared. Same codebase. Same decisions. Same architecture. Same mistakes repeated again. So he added a memory layer. Instead of treating Claude Code like a smart terminal, he connected it to a local Obsidian vault through MCP. Now Claude can read the repo, open the vault, create notes, link concepts, and write important decisions back into the system. When it studies the codebase, it does not just answer once and forget. It creates notes for the major services, maps how the architecture works, links auth to the database, connects APIs to storage, and records why certain migrations or design choices exist. Obsidian becomes the project graph. Now when he asks why something was built a certain way, Claude does not guess from the current prompt. It reads the decision notes. When he starts a new branch, Claude checks the active context file. When the work is done, it updates what changed, what is blocked, and what the next agent needs to know before touching the repo. That is the real loop: read context, write code, capture decisions, update memory. Most people are still using AI coding tools like disposable chat windows. Ask, patch, close, forget. This setup turns Claude Code into infrastructure. The repo gets a memory layer that survives every session, and multiple AI agents can work from the same project map without stepping on each other. The unlock is not better prompting. The unlock is giving the agent somewhere to remember what it already learned.

DegenCalls

20,124 次观看 • 2 个月前

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,177 次观看 • 3 个月前