沙箱

沙箱 (sandbox)

概念 · 又名 sandbox / sandboxes
本站收录 99 集 · 10 条金句 · 关联 10 个

集里怎么说它

① 提到它的金句

10 条

很难让我们的沙箱发生 OOM 或内存溢出。因为我们可以动态地实时调整大小,这在几乎任何其他东西上都是不可能的。
it’s very hard to OOM or out of memory our sandboxes. because we can dynamically on the fly resize, which is like impossible on almost any other thing.
—— Ivan Burazin · [28:56]

指向原始笔记的链接

我们在 2023 年 5 月构建了沙箱,在任何人甚至知道这将成为一件事之前。
we built sandboxes in May of 2023 before anyone was even knew this was going to be a thing.
—— Akshat Bubna · [09:19]

指向原始笔记的链接

所以这不是说我们不能对齐这些系统,而是一个巨大的控制内部监控失败,其中沙箱是不够的。
So it’s not that we can’t align these systems, but it is a massive control internal monitoring failure where the sandbox was insufficient.
—— Adam Gleave · [80:47]

指向原始笔记的链接

因为如果你没把沙箱做对,那其他的一切都免谈。
Because if you don’t get the sandbox right, forget everything else.
—— Jerry Murdock · [25:19]

指向原始笔记的链接

大多数做沙箱的人都在计算上赚钱。坦白说,在我看来这是个愚蠢的主意。
most sandbox people make money on compute. Frankly, that’s a dumb idea in my opinion.
—— Jerry Murdock · [27:19]

指向原始笔记的链接

给它们一个不会被杀掉的沙箱,在那里它们可以探索你的代码库,可以处理非常困难的任务,并且知道当你合上笔记本盖子时它们不会被关掉。
Give them a sandbox that won’t get killed, where they can explore your code base, where they can work on really hard tasks, where they know that they’re not going to get shut down when you close your laptop lid.
—— Charlie Holtz · [08:50]

指向原始笔记的链接

如果我们把越来越多的开发生命周期迁移到沙箱里,我们就可以根除供应链攻击。
We could eradicate supply chain attacks if we move more and more of this development lifecycle to sandboxes.
—— 嘉宾 · [00:25]

指向原始笔记的链接

所以如果你在使用 Claude,你就是在向 Anthropic 发送大量你的数据,除非你在使用沙箱,那样你就会被巧妙地拦截掉。
So if you’re using Claude, you are sending Anthropic a lot of your data, unless you’re using sandboxes, in which case you’re cleverly being blocked by that.
—— Rowan Christmas · [06:35]

指向原始笔记的链接

给你的智能体解决问题的空间,但让单个沙箱表达任务的意图。
Give your agents room to solve problems, but let individual sandboxes represent the intent of the task.
—— Jim Clark · [14:56]

指向原始笔记的链接

我们习惯于考虑建模能力、为任务构建合适的沙箱、把任务放进去,而现在我们开始看到,这个个体循环更安全,因为它拥有的访问权限比整个工作流实际拥有的要少。
We get used to thinking about modeling capabilities, building the right sandbox for the task, putting the task in, and now we’re starting to see that this individual loop is safer because it has less access than the entire workflow effectively has.
—— Jim Clark · [15:54]

指向原始笔记的链接

② 出现在这些集

99 集

③ 关联

点进去有真内容 —— 本页主要出口

智能体 · Anthropic · OpenAI · Claude Code · 护栏 · harness · Codex · MCP · 评估 · 推理