Beau HU

🧵 Building in public: AI-native experimentation 1/ The $10B+ product experimentation market exists because running experiments right requires senior PMs + data scientists at every step. That's the bottleneck. 2/ AI made code shipping 10x faster. But if your experiment loop can't keep up, the speed is fake — you're just shipping gut feelings faster. 3/ What we're building: AI agents that run the full loop autonomously. Intent → hypothesis → gradual rollout → measurement → decision. Human in the loop when it matters, autonomous when it doesn't. 4/ It's open source, works with Claude Code / GitHub Copilot / Codex. Still early (dogfood stage). Want to find people thinking about the same thing. 👉 github.com/featbit/featbi…

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?