跨国深谈

上下文窗口 (context window)

20分钟阅读

跨国深谈← 返回←上下文窗口 (context window)
上下

上下文窗口 (context window)

概念
本站收录 18 集 · 6 条金句 · 关联 10 个

集里怎么说它

① 提到它的金句

6 条

那种上下文无法进入人脑，但它可以进入 AI 的上下文窗口。
That context can’t go into a human brain, but it can go into the AI context window.
—— Evan Reiser · [08:04]

指向原始笔记的链接

我们最初的尝试是把 Base64 数据直接传进代码，那是个非常糟糕的主意。它直接把上下文窗口撑爆了，方方面面都很糟。别那么做。
Our first attempt was just passing Base64 data into the code, and that was just a terrible idea. It just blew up the context window and was bad all around. Don’t do that.
—— Jesse Lumarie · [05:16]

指向原始笔记的链接

如果你能影响或在那些 token 里留下印记，那价值比出现在单个上下文窗口里高出数量级。
if you can get influence or imprint in those tokens, it’s worth, like, orders of magnitude more than being in a in a in single context window.
—— Ben Moore · [52:00]

指向原始笔记的链接

模型是 CPU,上下文窗口是内存(RAM),而记忆是磁盘。
The model is the CPU, the context window is the RAM, and the memory is the disk.
—— Dylan Couzon · [06:46]

指向原始笔记的链接

在智能体之间共享上下文窗口，就像是给其他智能体添加垃圾，因为并不是所有智能体都需要彼此之间的信息。
You share the context window between agents is like add garbage to the other agents because no all the agents need the information between them.
—— Elizabeth Fuentes Leone · [09:59]

指向原始笔记的链接

当每个人都想要个人智能体，或者每个企业都想要自己的、全天候 24-7 持续在线并运行大量自动化的个人智能体时，上下文窗口比内存中的模型权重更重要。
When everybody wants personal agents or every business wants its own personal agents that’s always on and working 24-7 and running a lot of automations, the context window matters even more than the model weights in the memory.
—— Arvind Srinivas · [30:26]

指向原始笔记的链接

② 出现在这些集

18 集

③ 关联

点进去有真内容 —— 本页主要出口

智能体 · MCP · harness · Anthropic · Claude · Claude Code · Cursor · Codex · 沙箱 · RAG

反向链接