Folyd (@_hisriver) 's Twitter Profile
Folyd

@_hisriver

Opinions Are My Own. Creator of query.rs, 2d2d.io, huhu.io, anyshortcut.com, and paybase.cn

ID: 761559886312321025

linkhttps://folyd.com calendar_today05-08-2016 13:50:01

1,1K Tweet

7,7K Followers

803 Following

Folyd (@_hisriver) 's Twitter Profile Photo

感觉生命演化和互联网产品演化有点类似,只要有资源的地方就一定会存在某种生命形态,同样只要有需求的地方就一定会出现某种形态的产品,各种生命五花八门各显其招来活下去,互联网产品也类似

感觉生命演化和互联网产品演化有点类似,只要有资源的地方就一定会存在某种生命形态,同样只要有需求的地方就一定会出现某种形态的产品,各种生命五花八门各显其招来活下去,互联网产品也类似
Folyd (@_hisriver) 's Twitter Profile Photo

Do you want to vibe coding a programming language? 欢迎 27 号来现场听我的分享,我这里有 5 张免费的赠票(含午餐),需要的可以联系我

Do you want to vibe coding a programming language? 欢迎 27 号来现场听我的分享,我这里有 5 张免费的赠票(含午餐),需要的可以联系我
Folyd (@_hisriver) 's Twitter Profile Photo

Look at the Airtable agent field in action! One prompt → automatic analysis of the entire column. Batch operations have never been this simple! Amazing, this is insane! 🚀

Folyd (@_hisriver) 's Twitter Profile Photo

Been working on something cool for the #buildinpublic community 👀 Built an ARR leaderboard tracking real founder revenue data: 785 founders 1,212 products You might already be on it → arrfounder.com Help me hit 1K founders? 🎯 #startups #indiehackers

Been working on something cool for the #buildinpublic community 👀
Built an ARR leaderboard tracking real founder revenue data:

785 founders
1,212 products

You might already be on it → arrfounder.com
Help me hit 1K founders? 🎯
#startups #indiehackers
Michael Qizhe Shieh (@mpulsewidth) 's Twitter Profile Photo

Introducing MCPMark, a collaboration with Eval Sys and LobeHub! We created a challenging benchmark to stress-test MCP use in comprehensive contexts. - 127 high-quality data samples created by experts. - GPT-5 takes the current lead and achieves a Pass@1 of 46.96% while the

Introducing MCPMark, a collaboration with <a href="/EvalSysOrg/">Eval Sys</a> and <a href="/lobehub/">LobeHub</a>! 

We created a challenging benchmark to stress-test MCP use in comprehensive contexts.
- 127 high-quality data samples created by experts.
- GPT-5 takes the current lead and achieves a Pass@1 of 46.96% while the