I asked Claude Code to use tldraw to make a shared canvas so I can work with it with a shared canvas.
and it offered different approaches with pros and cons and suggested the best approach, and it's going to make it happen.
If you like this, read some linked essays here: https://t.co/lVLZUauDrd
Also, @buckhouse has an incredible article with real examples https://t.co/wU1h9DK2Nq
it's time to style the moss industry 🪴🍄
more exploration of interactive (conceptual) elements for web design with ThreeJS
it works via geonodes and is based on basic math and proximity functions, I think I'm going to keep making concepts like that
This is wild.
China's Manus AI just dropped and it will completely change the AI agent game.
10 wild examples.
1. Create Interactive Website based on Data Insights
the thing is called MeshPad and even lets users easily add or delete mesh parts through simple sketch changes
amazing times ahead 🙌
https://t.co/MKHaGuipiN
this. is. wild.🤯
I sketched up a quick app to find where to go on a honeymoon, and it pretty much just… works
this feels like a peak into the future, where people can spin up their own custom apps on the fly as they need them without writing a line of code…
Played with some ideas for a new https://t.co/A75JoyWeHW landing page last night.
If you break the connection between these two nodes on the landing page, it would switch the page into dark mode - how about that? 🤓
Today 6 years ago, "Attention is All You Need" went on Arxiv! Happy birthday Transformer! 🎂
Fun facts:
- Transformer did not invent attention, but pushed it to the extreme. The first attention paper was published 3 years prior (2014) and had an unassuming title: "Neural Machine Translation by Jointly Learning to Align and Translate", from Yoshua Bengio's lab.
It is a combination of RNN + "context vectors" (i.e. attention). Many of you likely haven't heard about this paper, but it's one of the greatest milestones in NLP and has been cited 29K times (compared to Transformer's 77K).
- Neither Transformer nor the original attention paper talked about the general-purpose sequence computer. Instead, both were conceived as solutions to one narrow & specific problem: machine translation. It's remarkable that AGI (some day soon) can trace its origin to the humble Google Translate. 😅
- Transformer was published at NeurIPS 2017, one of the top AI conferences worldwide. Yet it didn't even get an Oral presentation, let alone awards. There were 3 best papers at NeurIPS that year. Combined, they have 529 citations as of today.
Mind2Web: A Benchmark for Language Grounding to Automate Tasks on the Web
- Presents the first dataset for developing and evaluating generalist agents for the web
- Over 2,000 tasks collected from 137 websites
proj: https://t.co/DfGg526gCR
abs: https://t.co/TXPqQao3pn