信息流 (feed)
集里怎么说它
- 《Meta 的 Muse 亲测：我玩过设计最好的个人智能体》(07:22起):Muse 的独特原语：一句提示词（「做一个关于我兴趣的信息流，语气清晰直接、可快速浏览、避免标题党」）就能生成每天推送的个性化新闻，比她的 Facebook 信息流健康得多。
① 提到它的金句
10 条
你绝不会看到 Facebook 把他们信息流的控制权交给 Amazon。
指向原始笔记的链接
You would have never seen Facebook giving control of their feed to Amazon.
—— Rishabh Jain · [07:24]
我不会粉饰太平。设置起来很麻烦。你得喂养并维护你的 Claws。它并不是全自动的,但价值太大了,我愿意忍受这种痛苦。
指向原始笔记的链接
I won’t sugarcoat it. It’s a pain to set up. You got to feed and maintain your Claws. It is not hands-off, but the value is so high, I am willing to go through the pain.
—— Claire Vo · [62:59]
如果你做一个纯按时间顺序的信息流,每个人的激励就是尽可能多地发布,因为只要你一发,它就会始终位于每个关注你的人的信息流顶部。
指向原始笔记的链接
if you do a pure chronological feed the incentive for everybody is to just post as much as possible because it will always be at the top of everyone who follows you’s feed as soon as you post
—— Adam Mosseri · [38:56]
我们发现,随着模型演变得更有能力,如果你将逐字稿和记忆状态作为一个周期性批处理过程,并使用我们所谓的做梦,它允许我们提取新的洞察和新的组织结构,这基本上会反馈并编辑记忆,从而让第二天的智能体会话自动地变得更加智能。
指向原始笔记的链接
What we found is that as models have evolved and become more capable, if you feed the transcripts and the memory state as a periodic batch process with what we call dreaming, it allows us to extract new insights and new organized structures that essentially feedback and edit the memory as needed to make the next day’s agent sessions automatically much more intelligent.
—— Gagan Bhat · [27:45]
当我们尝试打开 10 个网站，只有 3 个返回有效内容，却把全部 10 个都喂给模型时，这就是个问题。
指向原始笔记的链接
And when we attempt to open 10 websites, but only three return valid content, but feed all of the 10 to the model, it is a problem.
—— Giedrius Šteimantas · [09:30]
所以是的，Transformer 在你喂给它整个互联网时很强大，但我们知道存在一个更优秀的算法，它能从小得多的数据中学习，并在所学的东西上表现得令人惊叹。
指向原始笔记的链接
So yes, transformers are great when you feed them all of the internet, but we know there is an algorithm that’s even better and it can learn from much smaller data and be amazing at the things it’s learning.
—— Lucas Kaiser · [05:03]
你要么领先一年，要么落后一年，仅仅取决于你的信息流。
指向原始笔记的链接
You’re either a year ahead or a year behind simply based on your feed.
—— Aaron Levie · [56:19]
所以如果我们把这个推向极端，那就是：为什么不把每一种数据——编程、计算机使用、自我中心视角——都喂给同一个模型？我认为这就是我们如何得到最强机器人使用智能体的路径。
指向原始笔记的链接
So if we take this to the extreme, it’s like, why not feed every kind of data, coding, computer use, egocentric, into the same model? I think that’s how we get to the most capable robot use agent.
—— Ham · [25:00]
我常说的一句话是，如果你在分类广告和报纸的时代试图向人们描述信息流这种形态，那根本讲不通。
指向原始笔记的链接
The thing I always say is if you try to describe the form factor of the feed to people during classifieds and newspapers, it would make no sense.
—— David George · [23:12]
你的 LLM 的表现取决于你喂给它们的上下文的好坏。
指向原始笔记的链接
Your LLM are as good as the context that you feed them with.
—— Eli Cohen · [14:56]
② 出现在这些集
1 集
③ 关联
点进去有真内容 —— 本页主要出口
Claire · Muse · Meta · 智能体 · OpenClaw · 浏览器使用 · 权限授予 · 活动流 · 目标 · 资料库