Amelia Wattenberger 🪷

@Wattenberger • 34,990 subscribers

design, AI, web dev, data viz, tools for thought ✨ @shv, Intent lead @Augmentcode, previously R&D @GitHubNext, design @AdeptAILabs

Shorts

160,201 views

38,842 views

Videos

sweetdream.ai

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Private Show

Join now for exclusive access

Free preview available • Premium content

199,253 views • 3 months ago

38,196 views • 1 month ago

88,993 views • 4 months ago

50,269 views • 3 months ago

259,379 views • 3 years ago

140,155 views • 1 year ago

31,648 views • 3 months ago

19,565 views • 2 months ago

178,492 views • 3 years ago

10,489 views • 1 month ago

82,754 views • 1 year ago

80,607 views • 1 year ago

15,196 views • 2 months ago

60,657 views • 1 year ago

93,692 views • 2 years ago

43,934 views • 1 year ago

16,277 views • 4 months ago

16,528 views • 4 months ago

16,254 views • 4 months ago

69,085 views • 2 years ago

Live Cam

Amelia Wattenberger 🪷

Shorts

I left prototype land to help implement this ✨ adorable ✨ SVG animation to celebrate 100M developers using GitHub 😍 check it out on your profile page!

starting something I've been wanting to do for a loong time.. email the way I want email to work! to come: I have lots of ideas for using LLMs that aren't just write-email-for-me

Videos

Watch Anya Live

What comes after the IDE? This is our take.

I make a custom sandbox 100% of the time I build anything now this has been the biggest change in how I work, almost as impactful as having agents write code for me. Bespoke editors too cheap to meter, making the craft and polish step way more enjoyable

Orchestrating many agents can feel transparent, with the right ui

omg Figma 😍

😅 is anyone else getting sick of chatbots? I wrote down a few thoughts on why chatbots are not the future of interfaces and how we can be more thoughtful:

soo the Perplexity API is good and cheap?!

pssst gpt5.4 is free to use in Intent right now

･ ｡ ☆∴｡ * ･ﾟ*｡★･ ･ *ﾟ｡ * ･ ﾟ*｡･ﾟ★｡ ☆ﾟ･｡°*. ﾟ * ﾟ｡·*･｡ ﾟ* ﾟ *.｡☆｡★ ･ * ☆ ｡･ﾟ*.｡ * ★ ﾟ･｡ * ｡ ･ ﾟ☆ ｡ ﾟ * into the rabbit hole

wrap it up, folks! I just proved that hot dogs are, unequivocally, sandwiches 🌭 embeddings for different foods from the OpenAI API, reduced dimensionality with UMAP, plotted here colored by "category". Hot dogs are solidly in the sandwich cluster, along with tacos and burritos

we need ways to stay oriented and understand - what's in a codebase - what are my agents working on - what are they looking at - what they've changed &amp;c something in between "read a summary in chat" and "read every line of code"

Getting all of my thoughts down and organized is always the hardest part when writing something. At least for me. I'm playing with an interface that you can speak to. It will jot down index cards as you're rambling and organize them into main topics.

😱 I just realized I never shared the svg tool I spent so much time on! I wanted to create a playground to help learn and discover how to write SVG code, which can be so funky! Remember when we learned physics in the sandbox? Yeah, like that.

this is wild turns out the best part of Figma MCP is that the agents are really good at FigJam now when I plan work with the agents, I get ✨ collaborative ✨ diagrams that are easy to read, easy to share, and easy to edit

🐟 some musings on how we might use LLMs 🐠 to interact with text at multiple levels of abstraction 🐡 inspired by the fish-eye lens

here's a quick write-up of a way I'm using OpenAI's embeddings that I haven't seen before. For my writing app, I want to highlight each sentence on any scale: ✨ happy — sad ✨ concrete — abstract ✨ + anything! but had to get creative to do this cheaply, quickly, &amp; robustly

wrote up some thoughts on how our interfaces are getting flatter, and how we might design with 💃 our bodies 🤸 in mind

Working with agents is a collaboration problem. Our tools didn’t even really support working together *before* agents. What happens when we reinvent then around collaboration? If we get the primitives right, we can build workflows that match exactly how we want to work

If you bundle together the changes, agents, and context for each task, you get: - parallel workstreams - instant task switching - more informed agents - saner workflows - painless handoff - perpetual context (why did we do X) ...

what if... agents writing code, but it's always easy to see - what changes were made, - who made them, - a digest of why, and - their detailed thinking

Infinite canvases! we love them! 🤩 but can we make them even better? Here's a little exploration of how we might make them easier to use by 🍃 adding physical forces, or 🌱 exporting the data into other formats.

･｡ ☆∴｡ * ･ﾟ｡★･･ﾟ｡ * ･ﾟ｡･ﾟ★｡ ☆ﾟ･｡°. ﾟ * ﾟ｡·･｡ﾟﾟ .｡☆｡★ ･ ☆ ｡･ﾟ.｡ ★ ﾟ･｡ * ｡･ﾟ☆ ｡ﾟ * into the rabbit hole

we need ways to stay oriented and understand - what's in a codebase - what are my agents working on - what are they looking at - what they've changed &c something in between "read a summary in chat" and "read every line of code"

here's a quick write-up of a way I'm using OpenAI's embeddings that I haven't seen before. For my writing app, I want to highlight each sentence on any scale: ✨ happy — sad ✨ concrete — abstract ✨ + anything! but had to get creative to do this cheaply, quickly, & robustly

Working with agents is a collaboration problem. Our tools didn’t even really support working together before agents. What happens when we reinvent then around collaboration? If we get the primitives right, we can build workflows that match exactly how we want to work