跨国深谈

提示词 (prompt)

Properties1
aliasesprompt, prompts

18分钟阅读

跨国深谈← 返回←提示词 (prompt)
提示

提示词 (prompt)

概念 · 又名 prompt / prompts
本站收录 13 集 · 19 条金句 · 关联 10 个

集里怎么说它

① 提到它的金句

19 条

我认为如果你真的不清楚成功是什么样子的，提示词，你可能无法获得最棒的工作。我认为这对管理团队来说是真实的，对管理 AI 来说也非常真实。
I think if you’re really unclear about what success looks like, the prompt, you’re probably not going to get the most amazing work. I think that’s true for managing teams and it’s very much true for managing AIs.
—— Julie Zhuo · [13:50]

指向原始笔记的链接

如果目标是更多的代码行，我可以提示某物写出有史以来最长的代码并添加大量的注释。
If the goal is more lines of code, I can prompt something to write the longest piece of code ever and add tons of comments.
—— Nicole Forsgren · [12:56]

指向原始笔记的链接

我们只是把 Agentforce 用在这些人身上，并且用非常相似的提示词训练了它。它有 70% 的回复率。
We just took Agentforce just on those and we trained it on very similar prompt. It had 70% response rate.
—— Jason Lemkin · [38:41]

指向原始笔记的链接

所以当 Claude 未能做某事，或者我看到这个非常糟糕的错误，表明 Claude 真的没有理解某些东西时，我会问它，“是什么在你的系统提示或工具中导致你犯了这种错误？”
So when Claude will fail to do something or I’ll see this really bad bug that shows that Claude really didn’t understand something, I’ll ask it, “What in your system prompt or tooling made you make this mistake?”
—— Zevi Arnovitz · [46:31]

指向原始笔记的链接

这种有人写了一个提示词并且他们刚得到了一个前沿模型就要扼杀一切的想法被极度夸大了，而投资者们只是我这辈子遇到过的最愚蠢、最不理性的人，我无法相信他们掌握了所有的资本。
This kind of idea that someone wrote a prompt and they’ve just got a frontier model that’s going to kill everything is wildly overblown and investors are just the silliest, most irrational people I’ve ever met in my life, and I can’t believe they have all the capital.
—— Barney Hussey-Yeo · [38:10]

指向原始笔记的链接

每一个这些产品都有远超 10000 个提示词，所以不要在第一个提示词后就放弃
each of these products have way over 10 000 prompts each so do not give up on the first prompt
—— Meng To · [73:17]

指向原始笔记的链接

但对于我们担心的主要风险类别,比如提示词注入、数据窃取,风险远低于人类审核员的平均水平。
But for the main categories of risks that we’re concerned about, like prompt injection, data exfiltration, the risks are far lower than the average human reviewer.
—— Cat Wu · [32:33]

指向原始笔记的链接

有一个很好的问自己的提示是：什么样的东西会让你最兴奋地发消息给别人说，嘿，我做了这个，对吧？
Like, one thing that I think is a good prompt to yourself is like, what would you be the most excited to text someone like, hey, I made this, right?
—— 嘉宾 · [38:46]

指向原始笔记的链接

所有这一切意味着核心模型任务是什么,不再是从用户那里获取一个提示词并返回一个答案,但实际上是从用户那里获取一个需要许多、许多步骤的任务。
All this means is what the core model task is, is no longer to get a prompt from a user and come back with an answer, But it is actually to get a task from a user that requires many, many steps.
—— Daniel McKinnon · [13:20]

指向原始笔记的链接

字面意义上，就是在提示词注入发生时，观察模型大脑中亮起的神经元。
where it’s literally, we’re looking at neurons in the model’s brain that light up when prompt injection happens.
—— Boris Cherny · [03:00]

指向原始笔记的链接

因为架构这些庞大的系统很有趣，但一个月后它就只是一个提示词了。
Because it’s fun to architect these huge systems, but in a month it’s just a prompt.
—— Wes Bos · [09:52]

指向原始笔记的链接

我们库里有超过 1.65 亿个模板、图片和图形素材,而我们真的不认为提示词框是创建视觉内容的正确向量。
We’ve got over 165 million templates, images, and graphic assets on the library, and we really don’t think the prompt box is the right vector for creating visual content.
—— Cliff Obrecht · [10:22]

指向原始笔记的链接

如果你有一套好的评估套件，你可以让 Claude、Codex 之类的进去替你修改提示词，而你确信你不会发布任何会毁掉生产环境的东西。
If you have a good eval suite, you can let Claude or Codex or Devon kind of go in, make prompt changes for you, let BlinkchainEngine make prompt changes for you, and you know that you’re not shipping anything that is going to ruin production.
—— Vishu · [02:26]

指向原始笔记的链接

同理，如果你只用一个很小的 eval 集去爬山，你的 prompt 很可能开始只是镜像那些 eval 示例。
Same if you’re only hill climbing with like a small eval set, your prompt is probably going to start to mirror just those eval examples.
—— Vishu · [07:41]

指向原始笔记的链接

你比只是写个提示词时更多地把自己从循环中抽离出来。这样你才能真正把自己扩展放大。
So you’re taking yourself out of the loop more than you are with just like a prompt. That way you can actually scale yourself.
—— Tyler Folkman · [05:26]

指向原始笔记的链接

要么我们在学习系统提示词，要么我们在学习 harness 本身——这非常迷幻。
Either we’re learning the system prompt or we’re learning the harness itself, which is very trippy.
—— 嘉宾 · [14:18]

指向原始笔记的链接

所以工程师们不得不手动给这些智能体写提示词，让它们做正确的事，而这往往比手动编码本身还要花时间。
So the engineers had to prompt these agents Manually, to do the right thing, which used to take more time than the manual coding itself.
—— Ajay Prakash · [04:37]

指向原始笔记的链接

一个形容词后面不带任何东西,只是一个更好的提示词。
An adjective with nothing behind is just a nicer prompt.
—— Paul Bakaus · [13:52]

指向原始笔记的链接

从那以后,那套东西几乎全被扔出了窗外,现在流行的是提示词工程、上下文工程、循环工程。
Almost all of that has gone out the window since prompt engineering and context engineering, loop engineering.
—— Robert Lucero · [25:19]

指向原始笔记的链接

② 出现在这些集

13 集

③ 关联

点进去有真内容 —— 本页主要出口

智能体 · ChatGPT · Anthropic · Figma · Codex · 评估 · GitHub · Lenny · Ankur Goyal · LLM

反向链接