creaτepjf ⚡️ 🟦

@JoySong_J lol, 我也收到了

🚨🚨IMPORTANT! my tg was hacked!!! please ignore anything coming from it!!! Best way to reach me for now is here on X. Also setting up a new tg account: @lucalovescake

@ziyuccccc 用ide

同样是用claude code vibe coding，别人做出来的版本看起来比我的靠谱多了是为啥？？？紧急装了个本地claude code，真的赶不上AI进步的步伐🤣

@0xLaughing 太对了，亲测苹果系统通常用的都是whisper和自带的体验最好，自己搭一个prompt 清洗工程。

用一小时在本地从0复现了一个Typeless 个别的单词有识别不准确的情况，长文本分段需要自己个性化调优，其他的几乎和原版98%一致 现在看，Typeless 底层大概率并不是什么神秘牛逼的模型，更像是高性价比语音转写模型 + 一整套工程化后处理 真正拉开体验差距的，不一定是ASR本身，还可能是：分段、断句、术语词典、上下文 prompt、口语清洗、改口修正、LLM 重写等等 也就是说，复现Typeless的关键不是找个更强的模型，而是把 ASR + context + rewrite 这条链路打磨到位

thx for saving my life

🎥 LIVE NOW: Nuts and bolts of AI agents—how to build your first one Presented by FLock's founder and CEO, @0x7SUN, joined by colleagues from @UNDP and @UNDP_AltFinLab. x.com/i/broadcasts/1…

What does sovereign AI look like in practice? FLock worked with the Sarawak AI Centre (SAIC) to show how federated learning can power AI in the public sector while keeping data and computing power under regional control.

转转、得物都有机会。预测 Anything，就上转转！

@0xLaughing 共享经济是吧，何尝不是一种缘分

用廉价 Claude Code API 中转站，输出了共享账户池里别人的对话历史，有一种放屁带出黄的美感

最近又重新拿起书，放慢点，以史为鉴找解法。起初是想做一个 Agent DAO，链上代理治理，后来再借助 OpenClaw 架构做了 Cleo(Agent Teams), 遇到一堆问题。是想从通信和社交方向解决，于是翻了翻大学时候传播学的东西，发现这些问题人类社会早就经历过了，而且有人研究了几十年。就顺着这个思路写了篇长的，通过传播，网络学科理论梳理，算是给自己理清楚了～ 这是第一篇，后面会再探索复杂网络。

Our Head of DevRel, @YifanX, just took the stage at UK AI Agent Hack with the keynote: "AI Agents for Good." While everyone's debating whether AI will end the world, we're here building AI that can improve lives. Our work with @UNDP on public healthcare in Mauritius, climate insurance for LATAM farmers, GenAI for Moroccan artisans, and more shows this isn’t hypothetical, it’s practical and happening now. But we can't do it alone. That's why we’re teaming up with @ChainforGood to launch the OpenClaw for Good track. Join us to build responsible AI: 🎯 Build AI Agents to solve UN Sustainable Development Goals 🔓 Use @openclaw and open-source models from FLock API Platform 💰 $5,000+ in prizes Submissions close on March 7th.

arrived ...... 33.33% of CLEO multi-agent system with #erc8004 enabled, and hit @claudeai Code's rate limit again haha Next milestone: on-chain Marketplace & DAO Governance

@TheChainLytic @flock_io @openclaw could you share a screenshot of the error? seems working fine on my side

@flock_io @openclaw Plugin cannot be installed. It's good to support it directly like vvv in openclaw.

Plug FLock API into @openclaw and you instantly get multi-model routing through a single OpenAI-compatible API. No refactors, just faster iteration, better pricing, and more choices at the model layer. Detailed guide below 👇

beyond models, agent skills and memory should also be treated as monetizable assets

cooking 🥘

@bugerpepper let flock have a try～

这篇写得太真实了，让人一边点头一边觉得苦涩。开源确实解决了“分发”，但“价值回流”几乎是空白——用的人越多生态越繁荣，真正做最重工作的训练方却几乎拿不到钱，这种结构长期来看一定不可持续。 Tailwind 的例子像一个警报：LLM 把知识直接“端到端”交付给用户，文档→付费组件这种传统转化路径被绕开了；而在开源模型这里，收入更直接地流向“谁在托管/谁在提供推理服务”，而不是“谁训练了模型”。 我不觉得 crypto 是万能解，但把“使用量 → 现金流 → 自动回流给贡献者”的机制做进系统里，至少是在对准问题本身。归根结底关键不是技术，而是激励设计；如果创作者长期只能白干，最后不是回到围墙花园，就是社区被消耗到 burnout。有人愿意去试这些机制，本身就很重要。

@cosmeticfish 冲

@createpjf 彭导要做头部researcher了！

推和B站的信息流已经被各种教程、如何实现xxx，xxx又发布了xxx 这样的内容填充了。 不得不感慨我作为人类的学习能力已经无法匹及 agent 和 model 的迭代速度。为脑子不够用感到焦虑😐 还是offline，打开上个时代的媒介，比如说看看春晚，回归生活，享受生活…