跨国深谈← 返回←Sandhya Subramani

① 他说过的话

5 条

让我写一个工具来数你想要的字符数，因为它显然知道自己没有这个能力。
Let me write a tool to count the number of characters you want, because clearly it knows that it does not have the capability to do it.
—— Sandhya Subramani · [04:00]

指向原始笔记的链接

现在你的重点不仅仅是构建一个能完成工作的好的智能体系统，你可能还想开始考虑编写自愈代码，考虑创建一个能审视自身、查看有哪些 bug 并自我修复的智能体。
So now your focus is not just building a good agentic system that can get the job done, you would also maybe want to start thinking about healing, writing self-healing code, about creating an agent that can sort of go over itself, look at what bugs are there and fix itself.
—— Sandhya Subramani · [14:20]

指向原始笔记的链接

如果这个元工具或元智能体能派生出工具和智能体，它也能修改和删除。
If this meta tooling or this meta agent can spin off tools and agents, it can also modify and delete.
—— Sandhya Subramani · [17:11]

指向原始笔记的链接

而且它能解决比最初被教会的更多的能力。这是自我改进智能体和自我进化智能体的开端。
And it can solve more capabilities than it has been initially taught to. This is the starting of self-improving agents and the self-evolving agents.
—— Sandhya Subramani · [18:53]

指向原始笔记的链接

我们写了 Strands 的 Python 版本。然后 Strands 的 Python 版本自己写出了 Strands 的 TypeScript 版本。
And we wrote the Python version of strands. And the Python version of strands wrote by itself the TypeScript version of strands.
—— Sandhya Subramani · [19:45]

指向原始笔记的链接

② 出现在这些集

1 集

• 《智能体自己造工具、自己修 Bug:AWS 工程师现场演示》 — 作为嘉宾

③ 他谈到的

点进去有真内容 —— 本页主要出口

智能体 · StrandsAgents · AWS · 元工具化 · 系统提示词 · 运行时 · 沙箱 · 护栏 · 评估 · 多智能体系统

④ 也在聊「智能体」的人