Beau HU

The agent experiments I’m running right now don’t need a database at all—just a shared file pool for team collaboration. Databases don’t scale imagination. They constrain it.

I just launched /office-hours skill with gstack. Working on a new idea? GStack will help you think about it the way we do at YC. (It's only a 10% strength version of what a real YC partner can do for you, but I assure you that is quite powerful as it is.)

@traderphos Honestly, in some ways, Scott matters more to me than GitHub.

China will always amaze us 🔥 🔥 🔥 🔥 🔥 🔥

This is what it looks like when the UI stops being the product. LaunchDarkly is going AI-native. Feels like the right direction.

@MuwaffaqBadawi I use a lot of CSX and AOT these days to build Bash CLIs — .NET is all you need.

.NET and C# are my taste

It's actually the opposite 😂

My version of a cyberpunk future — still a rough build, where high tech meets a sunlit utopia powered by natural energy.

People spend more time reviewing AI-generated code—understanding it, shaping it, making small, deliberate edits—not just for correctness, but to teach the system. The better the AI understands your codebase, the better it compounds.

🙉

@chenbimo 我是这两种人. 关键项目代码必看，简单业务类工具一行不看.

用AI的程序员有两种人，一种是完全不看AI写的代码，一种是AI写的代码非看不可。

When the AI is not generating human‑made programming languages.

Yes

Searched “FeatBit” on Google. First result: LaunchDarkly ad. I’ll take that as validation 😄

Thanks Bro.

Sam Altman: "I bet there is another new architecture to find" Sam Altman believes we are on the verge of discovering a new underlying architecture that will be as big of a leap forward as Transformers were over LSTMs. He noted that we finally have AI models that are smart enough to help conduct this level of research (GPT 5.4 and above 👀) His direct advice to builders looking for the next major leap is to look for a "mega breakthrough" and use current models to help them find it.

@dodyg @aspiredotdev Thanks @dodyg But I don’t think this is what I need. I’m looking for an Aspire-native skill that supports Python and TypeScript project integration, deployment workflows, coding tasks, etc. Ideally something that includes the full Aspire documentation.

@RealFeatBit @aspiredotdev github.com/novotnyllc/dot…

@aspiredotdev Is there any agent skill or MCP (maybe Microsoft Docs / Learn?) that I can use with Copilot to automatically introduce Aspire into my existing projects?

@pankajsameold @rohanpaul_ai Reality: China is embracing advanced tech and connecting with the world to build a better life. Being “more advanced” isn’t what matters — being happier than before is. So: things work better when they’re done with love.

@rohanpaul_ai I feel like China was as good as U.S. in robots. Or May be ahead, at least at scale. Now with AI, they have a very good chance of leaping ahead of U.S. if American politicians & public do not get going fast enough

New research from Tsinghua, Peking University and other top labs taught a humanoid robot to play tennis using scattered human movement clips instead of perfect match data. The big deal here is how the team solved the data problem for physical robots. Usually, teaching a robot to do something highly athletic like playing tennis requires perfect, continuous tracking data of professional human players. Getting that kind of flawless 3D physical data during a high-speed match is extremely difficult and expensive. This paper bypasses that massive hurdle entirely. Instead of needing perfect full-match data, the researchers just used short, disconnected, and imperfect clips of basic human swings. The AI system uses these rough clips as a basic hint for how a swing should look, and then a physics simulator corrects the physical errors so the robot does not fall over while swinging to hit the ball. Because they proved they can take messy, fragmented human data and turn it into a smooth, highly dynamic robot athlete, this means we can start teaching robots all sorts of complex physical tasks without needing to record perfect human demonstrations first. It severely lowers the barrier to making robots useful in fast, unpredictable physical environments. The robot successfully tracked fast incoming balls and consistently hit them back to specific target zones while looking surprisingly natural.