开启时会模糊预览图，关闭后正常显示
这个视频充分解释了Agent在实际生产场景中的综合运用 - Agent是多Single组成的Multi智能组织 - Agent既存在Agentic的，也需要Workflow的，往往在一个任务中这两类同时存在 - 对于stateless 和stateful也应该有不一样的处理机制，这取决于不同的场景 - Agent本身也是一种外部工具，就像我们称一些人为“工具人”一样 所以大家与其讨论agentic和workflow，不如多聊聊什么场景适合agentic，什么场景适用workflow 共存而非独立，这个事情恐怕直到现在还没能达成一个共识 https://t.co/juOCY1sU0x
Believing is seeing
他妈的，Open AI 真鸡贼，真有你的 Sam 通过积分制变相缩减免费和付费用户生成 Sora 视频的配额 他这里说的 100 条指的是最基础的模型 10 秒长度的视频 一旦变成 Pro high 模型 15 秒时长，即使是 Pro 用户也只能一天生成 5 条！ 那我 200 美元掏哪里了，服了
关注人工智能、LLM 、 AI 图像视频和设计（Interested in AI, LLM, Stable Diffusion, and design） AIGC 周刊主理人｜公众号：歸藏的AI工具箱
RT @DanielleFong: completing minecraft??
FOLLOWS YOU. Artificial Intelligence, Cognitive Architectures, Computation. The goal is integrity, not conformity. https://t.co/rFUNzdYXuK
学习了。
Growth Coach｜Helping creators build their personal brand on X 增长教练｜帮助创作者在X上打造个人品牌 公众号：PandaTalk8 X 增长群群主
RT @arvidkahl: Now THIS is bootstrapper thinking :D
Building https://t.co/od97B0HVrk and https://t.co/666FnyVVE0 in Public. Raising all the boats with kindness. 🎙️ https://t.co/6w69DZmi8H · ✍️ https://t.co/lpnor5rsTW
Father always talked bitterly about the failure to do proper static tests. N-1 had four full-scale flight attempts and all four failed. If Elon was doing that nonsense with Starship, he'd have had 20 failures in a row. also about Glushko
We're in a race. It's not USA vs China but humans and AGIs vs ape power centralization. @deepseek_ai stan #1, 2023–Deep Time «C’est la guerre.» ®1
