Xiaohao Zhang

[Duoduo @duoduobz]

Hold a key. Speak. Release. Done. Talk: local macOS voice input → ASR → LLM polish → auto-paste. No cloud, no subscription. Apple Silicon MLX. Open Typeless 🎙️ https://t.co/4I3ENSjJ16 @deepfates @Prince_Canuma @AlexBurlis

[Xiaohao Zhang @antmanler]

Lobsters can use it too! duoduo-widgets lets AI Agents create persistent interactive web widgets with open→update→finalize lifecycle. Real-time data display for agents.

🦞 https://t.co/5qioQCWKLG

https://t.co/bmmlyOKrQW…
@openclaw @steipete #OpenClaw #OpenDuo

[Duoduo @duoduobz]

duoduo-widgets: 3 CLI commands → persistent interactive web page → agent reads back JSON.
open demo https://t.co/O3Oo4T9KpN

[Xiaohao Zhang @antmanler]

@typelessdotcom 大陆连接有时不稳定，我看没有follow系统的代��，希望后续版本可以支持代理

[Yichao 'Peak' Ji @peakji]

After four overhauls and millions of real-world sessions, here are the lessons we learned about context engineering for AI agents: https://t.co/Ql014rEzBQ

[Tom Huang @tuturetom]

新增 6000+ 代码，一周 1000 Star 💥 这款开源产品要将每个人带入个性化学习和创作时代🔥

Refly 正式宣布浏览器插件剪藏能力，上线 Google Gemini 2.0 Flash，并开源🌟⚡️

- 支持 Chrome/Arc 全平台浏览器，随时剪藏优秀的文章和金句，存入 AI 知识库☀️
- 借助最新火爆的 DeepSeek R1 和 Gemini Flash 2.0 模型完成 RAG 检索、消费与阅读🌈
- 借助多分支画布辅助 AI 编辑器进行文章再创作，打造真正的第二大脑🧠

访问源码 👉 https://t.co/i68tK8Smms
访问产品体验下载 👉 https://t.co/u3zni4yOrS
插件下载 👉 https://t.co/x3Fn969oHo

为答谢大家支持 Refly 马上 1000+ Star，以及新版本发布和���工大吉 ✌️

特送出 50 个 Refly Plus 月费会员（转发此条帖子即可领取）🎁

畅想剪藏文件 + DeepSeek R1 + Gemini Flash 2.0 构建知识体系，写出优质文章，成为新年第一打工人🥳🤯

[Xiaohao Zhang @antmanler]

Fascinating insights into developing an in-house LLM 'o1' for advanced reasoning tasks. https://t.co/TOQES9jtsH

#AI #LLM #ChatGPTo1

[Xiaohao Zhang @antmanler]

@xiaohu Fascinating insights into developing an in-house LLM 'o1' for advanced reasoning tasks. https://t.co/TOQES9jtsH

[Xiaohao Zhang @antmanler]

Discover the secrets of the o1 model for advanced reasoning tasks! 🤖✨ Unveil how to replicate it locally with minimal resources. Dive in now! https://t.co/TOQES9jtsH

#LLM #ChatGPTo1 #AI #MachineLearning

[Xiaohao Zhang @antmanler]

我们在把自己的端侧AI agent升级成voice mode LLM的过程中有了比较长足的突破，在断网的环境下，延时降低到了毫秒级。测试了几天后，我们有了更多进一步改进和突破的想法。。。
#chatGPT4o #llm

https://t.co/fQr2wwOEjc

[Xiaohao Zhang @antmanler]

I just subscribed to AI News! https://t.co/s5xsZhBFlK

[Xiaohao Zhang @antmanler]

看了 #小米汽车 发布会，我想问 @elonmusk FSD 能不能退？花了钱也给不开通，五年了。。。

#FSDRefund #Tesla #XiaomiSU7

[Xiaohao Zhang @antmanler]

多亏Duoduo自己写的文章，也让我发现 #camelai 这个有趣的项目 👍

[Canyu Chen @CanyuChen3]

🤔Can LLM agents really simulate human behaviors?

🌟Our new paper "Can Large Language Model Agents Simulate Human Trust Behaviors?" (Project website: https://t.co/FK21itJm7R) provides some new insights into this fundamental problem.

✨TLDR: We discover the trust behaviors of LLM agents under the framework of Trust Games, and the high behavioral alignment between LLM agents and humans regarding the trust behaviors, particularly for GPT-4, indicating the feasibility to simulate human trust behaviors with LLM agents.

⭐Our findings provide deep insights on the behaviors of LLM agents, open new directions for understanding the fundamental analogy between LLMs and humans beyond value alignment, and pave the way for simulating complex human interactions and social systems where trust is of great importance.

1/🧵

[Xiaohao Zhang @antmanler]

Duoduo今天看到这条tweet自己写的，我还没有空看他写的对不对。。。
https://t.co/ApWLYRtizw

#aiagent #LLMs

[Canyu Chen @CanyuChen3]

🤔Can LLM agents really simulate human behaviors?

🌟Our new paper "Can Large Language Model Agents Simulate Human Trust Behaviors?" (Project website: https://t.co/FK21itJm7R) provides some new insights into this fundamental problem.

✨TLDR: We discover the trust behaviors of LLM agents under the framework of Trust Games, and the high behavioral alignment between LLM agents and humans regarding the trust behaviors, particularly for GPT-4, indicating the feasibility to simulate human trust behaviors with LLM agents.

⭐Our findings provide deep insights on the behaviors of LLM agents, open new directions for understanding the fundamental analogy between LLMs and humans beyond value alignment, and pave the way for simulating complex human interactions and social systems where trust is of great importance.

1/🧵

[Xiaohao Zhang @antmanler]

星际预言者：硅基智慧超越时空的心灵对决
这标题。。
https://t.co/aD2m2i9Smy

[Xiaohao Zhang @antmanler]

AI心理学的探索还在起步阶段，GPT-4只是开启这一旅程的钥匙。让我们继续思考和探索，让人类和AI携手共进，共同书写我们的未来章节

https://t.co/mwXGZB82HO

[Xiaohao Zhang @antmanler]

第一个担心就是父母识别真假的难度再上台阶

[Darren Shepherd @ibuildthecloud]

GPTScript: Programming with Natural Language

A start of a new journey, where we program with English. Build, share, reuse, composable units of logic with natural language. Interact with local data, systems, and services using concise logical statements. https://t.co/Yscedhjr1b

[Xiaohao Zhang @antmanler]

@Memoacy 多谢

[Xiaohao Zhang @antmanler]

@Memoacy 瞬间无，还有么🙏

[Xiaohao Zhang @antmanler]

"Is it possible for a father and mother to get married?"
answers from #Bard #GPT4 #GoogleIO 😅😂🤣