Sarah Chieng
@MilksandMatcha • 32,461 subscribers
Head of DevX @Cerebras prev. @ExaAiLabs, @MIT wife to @tyler_fong_
Shorts
Videos
I create a lot of video content. Over the past few years, that work has helped me grow to 200K+ followers and 70M+ views across platforms. Lately, I’ve been experimenting with AI tools that make the process more efficient, without losing my voice, personality, or taste. From researching and writing scripts to editing videos and crafting captions, I’m sharing a few of my favorite workflows, including how I use tools like Hyperagent. I’d love to hear which tools or workflows have made the biggest difference in your own creative process. Try it out:
Sarah Chieng293,295 views • 3 months ago
The hard part of agent loops is not starting them! It’s knowing when to move up a layer, and when to come back down. swyx explains the operator skill behind useful loops: automate repeatable work, watch for failure, drop into the problem when reliability breaks, then climb back up once the system is sound. That flexibility (not token volume for its own sake) is the key to productive loops. Join us in the Token Billionaires Lounge, presented by Cerebras and AI Engineer
Sarah Chieng202,991 views • 2 months ago
so it turns out astra is AGI (this video is not sped up holy sh*t)
Sarah Chieng89,323 views • 1 month ago
I made Claude compete against itself. The smartest model does not automatically make the best agent. To prove it, I took the same Opus 4.6 model, initial prompt, and empty repo and but it inside two different coding harnesses: Claude Code vs. Factory Droid. The task: clone Excalidraw from scratch, inspect the original in a browser, implement its key interactions, and verify the result. Factory Droid: 8 minutes, 20 tool calls, $1.60 Claude Code: 19 minutes, 40 tool calls, $1.87 The only difference was the harness. Get Free Factory credits here:
Sarah Chieng106,993 views • 2 months ago
!["Technical writing completely changed my life." - Thariq In less than 2 years, Thariq (Anthropic) cracked the code on writing technical articles that consistently pass 1M+ views. In this 15-min workshop, he breaks down: → his exact writing workflow → tactics behind articles that go viral → how he leverages AI to write faster (without losing his voice) → why technical writing is the most underrated way to drive mindshare Technical writing is one of the most powerful (and completely free) ways to gain views, build authority, and teach the world what you know. This is the 4th [Technical] Write & Learn, a curated workshop series cohosted with swyx and Kernel Labs.](https://image.24vids.com/tw-2052812382137971115/amplify_video_thumb/2052796466771722240/img/Kc-2OHhcHKCDaRCu.jpg)
"Technical writing completely changed my life." - Thariq In less than 2 years, Thariq (Anthropic) cracked the code on writing technical articles that consistently pass 1M+ views. In this 15-min workshop, he breaks down: → his exact writing workflow → tactics behind articles that go viral → how he leverages AI to write faster (without losing his voice) → why technical writing is the most underrated way to drive mindshare Technical writing is one of the most powerful (and completely free) ways to gain views, build authority, and teach the world what you know. This is the 4th [Technical] Write & Learn, a curated workshop series cohosted with swyx and Kernel Labs.
Sarah Chieng269,503 views • 5 months ago
Cafe Compute has officially landed in NYC By popular demand, we're excited to expand! Some behind the scenes with Amanda Huang And a huge thank you to our partners Bain Capital Ventures, , Structify, Exa, , San Francisco Compute, Haize Labs Where should we go next?
Sarah Chieng477,042 views • 1 year ago
Build a real-time AI Voice Agent that can actually sell. In less than 30 minutes, you'll learn how to build a sophisticated real-time voice sales agent that can have natural conversations with potential customers. Includes a full code notebook, recorded tutorial, and docs The stack: ⚡ fast inference 🎙 LiveKit for real-time audio/video infrastructure 🗣 realistic speech synthesis (STT/TTS)
Sarah Chieng452,438 views • 1 year ago
What a fun little breakfast chat with swyx Windsurf just released Fast Context. Unlike traditional agentic search, Fast Context searches and retrieves relevant code from your codebase 20x faster. Game changing for developers who want to stay in flow. Watch it in action inside Andrej Karpathy’s nanochat repo. All over a bowl of Swyx's favorite childhood cereal, Raisin Bran. Powered by Cerebras.
Sarah Chieng397,034 views • 11 months ago
I host a ton of events. This video was so fun to make, capturing how my team and I leverage AI when curating an incredibly high volume of intimate, tasteful, and high-quality events using some of our favorite tools like OpenAI Developers Codex, Eve by Vercel and more. But we are also excited to learn. Let me know if you have any suggestions or favorite tools and workflows :) And if you're heading to ICML, definitely say hi to the Cerebras team.
Sarah Chieng136,558 views • 3 months ago
The underrated Codex pattern: stop asking one thread to hold the whole universe. OpenAI's jason talks about thread managers, threads that talk to other threads, Slack context, hourly loops, and feedback IDs. The win is not just parallelism. It is better-scoped context. Join us in the Token Billionaires Lounge, presented by Cerebras and AI Engineer
Sarah Chieng83,077 views • 3 months ago
If a prototype takes a day, waiting a week for user feedback is "really painful," said Andrew Ng. Well....now you can get user feedback in under 60 seconds :) Whether you're prototyping a feature or building a full fledged product, learn how to build an AI-powered user research system that automatically generates user personas, conduct interviews, and synthesize insights. All in <60 seconds. Includes a full code notebook, recorded tutorial, and docs. The stack 🤖 fast inference 🤖 's LangGraph for orchestrating multi-agent workflows 🤖 's LangSmith for tracing and evaluating
Sarah Chieng231,338 views • 1 year ago
A reminder that codex can unfollow all the fakes not following you back
Sarah Chieng61,101 views • 2 months ago
Sherif asked Codex to buy the parts for a new computer and send them to his house. it did. Then it noticed he accidentally ordered two motherboards, emailed the supplier, got him a refund, and found coupons. 0xSero didn’t ask it to do any of that. he also has Codex: > keep track of green card paperwork, taxes, and nonprofit filings > edit videos locally with FFmpeg > summarize his inbox > check for approvals and continue with the next step > turn repeated work into skills cheaper models can reuse > run experiments overnight while he sleeps In this episode of 'Independent Studies', Sherif walks through exactly how he setup his tiny staff of agents and the creative ways that he uses AI to make his life cheaper and more productive.
Sarah Chieng33,709 views • 1 month ago