Follow AI Builder – Discover Real AI Creators & Projects

Follow AI Builders — Not Influencers

Discover real AI creators shaping the future. Track their latest blogs, X posts, YouTube videos, WeChat Official Account posts, and GitHub commits — all in one place.

Following Only

Simon Willison

𝕏x•15 minutes ago

Re Here's an example, recorded by "shot-scraper video" using a YAML storyboard constructed by Codex Desktop and GPT-5.5 xhigh

View on X

Simon Willison

𝕏x•17 minutes ago

I've added video support to my "shot-scraper" browser automation tool - you (or your coding agent) can now create a storyboard YAML file and use that to record a video demo of new web application features https://simonwillison.net/2026/Jun/30/shot-scraper-video/

View on X

Peter Steinberger

𝕏x•18 minutes ago

Retweeted from @alvin

RT alvin pane Day 2 at @aiDotEngineer World’s Fair. Great talk by @steipete on building loops.

View on X

Simon Willison

📝blog•19 minutes ago

Have your agent record video demos of its work with shot-scraper video

shot-scraper video is a new command introduced in today's shot-scraper 1.10 release which accepts a storyboard.yml file defining a routine to run against a web application and uses Playwright to record a video of that routine. I've written before about the importance of having coding agents produce demos of their work; this is my latest attempt at enabling them to do that. Here's an example video created using shot-scraper video, exercising a still in development feature adding the ability to create new tables in Datasette from pasted CSV, TSV or JSON data: That video was created by running this command: shot-scraper video datasette-bulk-insert-storyboard.yml \ --auth datasette-demo-auth.json --mp4 (That --auth JSON file contains a cookie, as described here in the documentation.) Here's the datasette-bulk-insert-storyboard.yml file: output: /tmp/datasette-bulk-insert-demo.webm server: - uv - --directory - /Users/simon/Dropbox/dev/dat...

3 min readSimon Willison

Read full article

Harrison Chase

𝕏x•20 minutes ago

Retweeted from @nikita

RT nikita Re @hwchase17 very spot-on! for our (http://qontext.ai) customers, the journey is usually: local .md files -> shared github repo (-> gbrain) before these approaches break down at a) multiplayer (incl access controls etc) and b) maintenance at high data volumes

View on X

Peter Steinberger

𝕏x•21 minutes ago

Retweeted from @Nick

RT Nick DeJesus 🛒🎉 - Former Unpaid CTO @BTPipeline I think the best thing about watching @steipete talk is that you can tell he LOVES what he does.

View on X

Boris Cherny

𝕏x•21 minutes ago

You asked, we listened. Claude Desktop on Linux is here! Download link: https://code.claude.com/docs/en/desktop-linux

@ClaudeDevs

Claude Desktop is now available on Linux (Ubuntu and Debian) in beta. Alongside the browser and terminal, you now get a first-class desktop experience with Claude Code, Claude Cowork, and chat on all paid plans.

View quoted post

View on X

Shawn Wang

▶youtube•30 minutes ago

Building Reliable Speech-to-Speech Voice Agents: Combining Gemini Live + LangChain Deep Agents

Watch on YouTube

Harrison Chase

𝕏x•30 minutes ago

good description of how someone has done wiki memory in the wild

@Miller

@hwchase17 @cognition @FactoryAI @karpathy We implemented wiki idea by hosting the "files" as doc db objects, added an API for db querying, and a CLI for agents to use. System prompt was updated to inform agents to store, update, and fetch things via the CLI. Interaction is great - just need to focus on information.

View quoted post

View on X

Shawn Wang

𝕏x•about 1 hour ago

Retweeted from @Matthias

RT Matthias 📍 @aiDotEngineer Mr @swyx kicking of @aiDotEngineer #aiengineer Slides at https://loopcraft.swyxio.workers.dev/

#aiengineer

View on X