Stefan Li
@autoconfig
Followers
219
Following
1K
Media
71
Statuses
998
Co-founder and CTO at https://t.co/cAEyxt2k1J (YC W23). Previously at Facebook, WalmartLabs, Sony. Thickening the wrapper. 🇸🇪 ðŸ‡ðŸ‡° 🇺🇸
NYC
Joined April 2010
I remember switching from android to an iPhone around 10 years ago and being very confused about the "buy" button not being available for kindle books in the Amazon app. It took a decade to get this, and it's not really a buy button, but I'll take it. Apple you greedy bastards.
1
0
1
Tried giving Claude Code runtime access by writing a simple Chrome DevTools Protocol MCP server (that's a mouthful). It worked shockingly well for the effort needed. Did a writeup here for anyone curious:
autoconfig.io
Give your coding agent direct access to Chrome DevTools Protocol through MCP, enabling it to inspect, interact with, and debug web applications at runtime.
2
1
7
The hundred billion dollar AI models have made Tailwind semi-usable.
0
0
4
RT @andrewchen: UPDATE:.big NYC tech week milestone -- we've hit **1000** events in a single week. Amazing. All the events are happening n….
tech-week.com
a16z presents Tech Week, bringing together the top funds, startups, and companies around the globe.
0
46
0
RT @livestoredev: Introducing LiveStore (beta). LiveStore is a next-generation state management framework based on reactive SQLite and buil….
0
111
0
Building a chat UI is the classic example of where getting to V1 takes like 2 minutes but then the long tail of micro UX wrecks you. Layout shifts. Virtualization. Growing input box that doesn't cause jump scrolls. Bottom align logic. etc etc. And yeah the AI won't get it right.
1
0
3
Something seems off with the Gemini 2.5 Pro integration in @cursor_ai. If being fed the right context explicitly, it often performs at or better level than Claude 3.7. But it consistently fails to do agentic lookup for the right context itself, leading to bad code.
0
0
1
Remember when Satya asked if google would come and dance? Well looks like they're dancing now. 😂.
0
0
1
Folks at google are really cooking with gemini 2.5! Was struggling with a bug somewhere in a 16K line file (not my code) and it found it in one shot. No other model would fit it into context. Cursor wouldn't allow me to pass the full file even with gemini selected so had to use.
0
1
10
RT @levie: We’re about to see AI Agents explode in SaaS. The entire architecture of most modern cloud services is to power multi-user, coll….
0
61
0
RT @GergelyOrosz: Fun fact: @craftdocsapp does not use AutoLayout. Every new joiner iOS engineer is horrified that this is the case. The f….
0
3
0
RT @SwedishPM: Sweden stands with Ukraine. You are not only fighting for your freedom but also for all of Europe’s. Slava Ukraini! 🇺🇦.
0
20K
0
This thing is amazing. Absolutely love the attention to detail.
We just launched Corca—a collaborative math editor. The main idea: there’s no 'text editor' for math. If you want to work on equations on a computer, there’s no app designed for that—so the only real option is paper. ↓
0
0
1
RT @stewfortier: New in @typedotai:. – File + url imports.- Table support 🎉.- Text extraction. No AGI. No agents (yet!). Just useful stuff….
0
2
0
RT @oznova_: My dad once told me the story of his CS department taking delivery of one of the first computers in his country (Turkey). Nob….
0
6
0
Sick. Can't wait for this (80% of which I don't understand) make it into the next game.
So what have I been up to this year? Hardware raytracing, Vulkan, deformable voxels, engine architecture, physics and lots of multithreading.
0
0
0
Insane.
USCIS just denied my US green card application. claiming my work lacks impact "beyond that of Apple, Inc." -- even though they acknowledge that I am the Apple CTO. WTF? I have NEVER worked at Apple!. I got my cs PhD, cofounded an AI startup, and raised $20M. Yet, after waiting
0
0
1
RT @mikeknoop: o3 is really special and everyone will need to update their intuition about what AI can/cannot do. while these are still ea….
0
402
0
Well this didn't age well. In the span of less than 4 months, OpenAI has gone from 4% (4o) to 76% (o3) on the ARC-AGI benchmark. The funniest part is that they said this while perhaps the largest step increase in capability was taking place since GPT-3.
Marc Andreessen and Ben Horowitz say that AI models are hitting a ceiling of capabilities: "we've really slowed down in terms of the amount of improvement. we're increasing GPUs, but we're not getting the intelligence improvements, at all"
1
0
1