Caroline Vrauwdeunt ✌️☮️
1.7K posts
Caroline Vrauwdeunt ✌️☮️
@andrsnu
CEO @ANDRS_Projects | Leader in AI, Travel & Fin Tech | #Dare2Create Advocate
#AMS🌷+ #KWAwesome 🍁 + 🌍🚀🌕 Katılım Temmuz 2012
654 Takip Edilen346 Takipçiler
@elonmusk Where does it stop being human content and start being AI content? Seriously wondering about that.
English
Caroline Vrauwdeunt ✌️☮️ retweetledi
AI content will vastly exceed all human content
Brett Winton@wintonARK
We have been surpassed: AI written output exceeded human written output in 2025
English
@DataChaz Then my next question would be: what are you going to use it for that isn’t illegal? 🤔
English
Holy cow.
Someone literally built a Claude Code skill that clones any website in one prompt 🤯
Everyone tries to clone sites by grabbing screenshots and hoping for the best.
That barely gets you halfway there.
This new skill brings a MUCH smarter way!
It directs Claude Code's Chrome MCP straight to the source, pulling live assets and code directly.
→ No more guessing exact fonts.
→ No more eyeballing component sizes.
→ No more faking animations from screenshots.
Here is how the skill automates the magic behind the scenes:
#1 Opens Chrome MCP and navigates directly to the target website
#2 Extracts the visual foundation (fonts, colors, layout, patterns) while taking screenshots
#3 Builds the clone's core from that collected data
#4 Deploys parallel agents to clone separate sections simultaneously
#5 Reviews the agents' code, merges everything, and finalizes the clone
One prompt gets you a fully cloned website.
The best part?
It's 100% free and open-source.
Link to the repo in 🧵↓
English
Caroline Vrauwdeunt ✌️☮️ retweetledi
🚨Shocking: Microsoft just open sourced a Python tool that converts any file into Markdown for LLMs.
It's called MarkItDown. And it's not a document formatter.
It's a lightweight conversion utility built specifically for AI pipelines - takes any file you throw at it and outputs clean Markdown that LLMs can actually read and reason about.
Here's what it converts:
→ PDF - full text extraction with structure preserved
→ PowerPoint - slides, headings, bullet points
→ Word - full document with lists, tables, links
→ Excel - tabular data as Markdown tables
→ Images - EXIF metadata + OCR text extraction
→ Audio - EXIF metadata + speech transcription
→ YouTube URLs - fetches transcription automatically
→ HTML, CSV, JSON, XML, EPubs, ZIP files - all supported
Here's the wildest part:
LLMs natively speak Markdown. They've been trained on vast amounts of it.
When you convert your PDF or Excel file to Markdown before feeding it to an LLM, you get better extraction, better reasoning, and more token-efficient output than raw text or HTML.
One command:
`markitdown path-to-file.pdf > document.md`
Also ships as an MCP server for Claude Desktop integration.
87K GitHub stars. Used by 2,200+ projects. Built by the AutoGen team at Microsoft.
100% Open Source. MIT License.
(Link in the comments)
English
We also improved the MCP data logic, for all #Claude fans.
moneymagician.eu
#fintech #mcp #moneymagician #talktoyourfinances
English
Just added the ability to render mini charts in to Money Magician’s chat function “M”. Little horizontal bar charts or donut pie charts for situations where comparisons or breakdowns can clarify your money.
For visual beings, like me ;)
#freelancers #smallbusiness #creators
English
We continuously test our #MCP server across model versions, so the calculations you rely on stay accurate — the same way you'd expect from your CFO or a good accountant.
Use AI. Love AI. But know what it's actually doing with your numbers.
#fintech #mcp #talktoyourfinances #AI
English
Claude now comes equipped with financial management capabilities. Are you thinking to ending your accountant's contract, or cancelling your software subscription, and going all-in on #Claude?
Here's why that's a genuinely bad idea. 👇
#software #accounting #freelancers #smb
English
Caroline Vrauwdeunt ✌️☮️ retweetledi
English
Caroline Vrauwdeunt ✌️☮️ retweetledi
Every Pokémon Go player unknowingly trained future robots.
Over the years, players photographed 30 billion images from cities around the world.
And now that data is teaching delivery robots to navigate streets.
Niantic (company behind Pokémon Go), spun out an AI company called Niantic Spatial that's turning years of player data into a visual positioning system for machines.
When 500 million people installed the game and pointed their phones at buildings, landmarks, and street corners, they were also capturing detailed location data that normal GPS can't match:
> GPS signals bounce off skyscrapers and lose accuracy by up to 50 meters in dense cities.
> That's a dealbreaker for sidewalk delivery robots that need to stop at exactly the right point.
> Niantic Spatial trained a model on those 30 billion images to pinpoint a robot's exact location based on what its cameras see, not satellite signals.
> Delivery startup Coco Robotics is the first partner, using the system to guide thousands of robots across LA, Chicago, and Miami.
Don't think anyone thought they were training robots when they were chasing Pikachu during COVID.
English
I just installed Claude-Mem - persistent memory across files for Claude. Saving tokens and your sanity! claude-mem.ai #buildinpublic #claude #AI
English
