Shen Zhuoran @CMS_Flash

Coding agents/self-improvement @xai. Ex-@GoogleAI Resident/@augmentcode. Alum @HKUniversity. 💎 Terran @StarCraft II. Views are personal. cmsflash.github.io San Jose, CA, United States Joined February 2016

Tweets

1K
Followers

3K
Following

232
Likes

2K

Shen Zhuoran @CMS_Flash

3 days ago

In the internet age, people use apps for free in exchange of ads. In the AI age, people can use physical services for free in exchange of AI training LOL.

shift @joinshiftX

a week ago

Today, we're launching shift. We're starting by cleaning your apartment in New York City, for free. Here's how it works. Book a shift cleaning. A vetted shift operator comes to your home wearing one of our devices. They clean. They leave. You pay nothing. In exchange, we record

2K 359 6K 8.3M 4K

0 0 4 2K 2

View Details

Boyuan Zheng @boyuan__zheng

2 weeks ago

Excited to see people try Grok Build for web dev. Our team has put a lot of effort into improving its aesthetics, functionality, and more exciting features to be expected with recursive self-improvement loop. It’s still early beta, and feedback is very welcome. Please try it out and let us know where we can improve.

Kilo @kilocode

2 weeks ago

Grok Build 0.1 might be one of the most underestimated AI models right now. We tested it in Kilo Code by asking it to build 5 websites from scratch. Here are the results:

261 725 4K 23.2M 893

248 114 2K 31.9M 380

View Details

Shen Zhuoran @CMS_Flash

2 weeks ago

@boyuan__zheng @xai Finish our push for the best web dev model in the world 🔥🔥🔥!

0 0 0 77 0

View Details

Shen Zhuoran @CMS_Flash

3 weeks ago

I left @xai last week. It was quite a journey. I learned a lot technically and made some lifelong friends. I was fortunate to have spent almost all of my xAI tenure on a singular, long-term project on optimizing Grok's ability to one-shot complex, complete, and polished web apps. I am proud of this team. We contributed one of xAI's most successful alignment recipes, which has been replicated to other teams. We scaled another innovative recipe to incredible scales, for which Grok 4.3 gave a tip-of-an-iceberg preview. I am excited to see its full impact reveal on future releases. Looking forward, we are now at a critical point in the history of AI. Coding is on track to become a solved problem and AI is on the brink of its first total disruption of a major industry. Models show the first signs of substantial participation in their own development. The singularity might be on the horizon. Today might be analogous to the eves of AlexNet and GPT-3, or perhaps more profound. I am excited for what is to come.

32 12 392 24K 46

View Details

Shen Zhuoran @CMS_Flash

2 weeks ago

@JaySym_Ai How to get access to Cosmos?

0 0 0 195 0

View Details

Shen Zhuoran @CMS_Flash

3 weeks ago

@zhmeishi @xai It was a memorable journey pushing on web dev together with you!

0 0 1 102 0

View Details

Shen Zhuoran @CMS_Flash

3 weeks ago

@OpsoFacto @xai No.

1 0 1 63 0

View Details

Shen Zhuoran @CMS_Flash

3 weeks ago

@HoneybadgerFan4 @xai Sure, lemme know when you want to play!

0 0 1 64 1

View Details

Boyuan Zheng @boyuan__zheng

3 weeks ago

We put a lot of work into making it smarter and stronger at coding, especially for a small model. Excited for what's coming next with bigger models training at Colossus 2.

xAI @xai

3 weeks ago

An early beta of Grok Build, an agentic CLI for coding, building apps, and automating workflows is now available for SuperGrok Heavy subscribers. Through this early beta, we will improve the model and product based on your feedback. Try it at x.ai/cli

2K 1K 10K 56.6M 3K

8 6 138 7K 4

View Details

Shen Zhuoran @CMS_Flash

3 weeks ago

@ar0cket1 Why?

1 0 0 117 0

View Details

Shen Zhuoran @CMS_Flash

3 weeks ago

1. Residual connections 2. Attention mechanism 3. Linear attention

Core Automation @CoreAutoAI

3 weeks ago

What are deep learning architecture modifications you don’t consider hacks @_arohan_

5 2 82 27K 27

2 1 50 10K 12

View Details

Shen Zhuoran @CMS_Flash

4 weeks ago

End-to-end eval is the way to scale to the future. For general coding, it will be whole repo generation for production-scale libraries, tested by UTs. For app development, it will be one-shotting production-grade apps, like Amazon, X, or Workday, tested by agentic grading.

John Yang @jyangballin

a month ago

How much of SQLite, FFmpeg, PHP compiler can LMs code from scratch? Given just an executable and no starter code or internet access. Introducing ProgramBench: 200 rigorous, whole-repo generation tasks where models design, build, and ship a working program end to end. 🧵

103 246 2K 723K 658

1 1 10 3K 4

View Details

Shen Zhuoran @CMS_Flash

a month ago

@Designarena @XiaomiMiMo @Xiaomi No scores yet?

0 0 1 199 0

View Details

Shen Zhuoran @CMS_Flash

a month ago

Agents are pretty much just English compilers.

skcd @skcd42

a month ago

2018: waiting for my compiler to complete 2026: waiting for my agent to complete

3 2 69 6K 0

0 1 38 2K 3

View Details

Boyuan Zheng @boyuan__zheng

2 months ago

Incredible to see what we've been cooking this past month — and this is only the beginning. Stronger models and richer capabilities are on the way. What excites me most: what happens when the web dev model hits a singularity and unlocks Computer Use Agent self-play? Proud to be part of the team building this🚀

BijanBowen @Ominousind

2 months ago

Grok 4.3 Beta browser os test result, gta clone and voice control apps

152 604 2K 820K 244

40 9 181 16K 22

View Details

Beibin Li @beibin79

2 months ago

Good job team!~ @ahmnav @CMS_Flash @arnogau @boyuan__zheng @ebecker_xai @1kevin_h @michaelbzhu @zhmeishi

BijanBowen @Ominousind

2 months ago

Grok 4.3 Beta browser os test result, gta clone and voice control apps

152 604 2K 820K 244

4 4 148 8K 6

View Details

Shen Zhuoran @CMS_Flash

2 months ago

Cool work of the team is finally out in the world. This is a very early preview, and much more is to come around: - One-shotting complex web apps; - Pure vibe coding; - Self-improvement between browser use and web app development. The last point is critical and unique to web dev, because there is an intelligence gap between using a web app and building a web app that we can exploit, in theory leading to indefinite scaling of self-improvement.

BijanBowen @Ominousind

2 months ago

Grok 4.3 Beta browser os test result, gta clone and voice control apps

152 604 2K 820K 244

10 14 276 35K 27

View Details

Shen Zhuoran @CMS_Flash

2 months ago

Coming soon!

Elon Musk @elonmusk

2 months ago

@HighlyUnspoken @cb_doge @Similarweb @grok Beta release of Grok Build app & terminal next week

331 279 3K 596K 189

12 4 221 6K 4

View Details

Nat McAleese @nmca

2 months ago

A full-scale US Waymo rollout would cost ~700 full-time jobs in the funeral care industry (by saving around 35 thousand young American lives per year). Will no one think of (some of) the morticians!