护栏

护栏 (guardrails)

概念 · 又名 guardrails / safeguards
本站收录 46 集 · 9 条金句 · 关联 10

集里怎么说它

① 提到它的金句

9 条

实际上我认为人们会在国防行业感到惊讶,我们的行业周围可能比大多数商业行业有更多的护栏和负责任的 AI 努力。在美国这里有联邦法规禁止某些事情,而在商业领域人们为了安全问题可能只是激增并去做。
I actually think people would be surprised in the defense industry that there is probably more guardrails and responsible AI efforts around our industry than most commercial industries. There are federal regulations here in The US that prohibit certain things that in the commercial space people might just surge and go do in terms of safety issues.
—— Chris Benson · [22:38]

指向原始笔记的链接

这个问题在于前沿模型在自动化红队测试方面极其糟糕,因为它们内置了大量的保障措施。
the issue with this is that frontier models are extremely bad at automated red teaming because they have a lot of safeguards built into them.
—— Zico Kolter · [09:59]

指向原始笔记的链接

而现在我们实际上发现,我们设下的所有那些护栏,正在拖累这些聪明得多的 AI。
Now what we’re finding actually is that all those guardrails we put in place are holding these much more intelligent AIs back.
—— Jon Noronha · [15:46]

指向原始笔记的链接

归根结底,所有的闭源专有模型 API,它们的护栏有点武断,但也很难强制执行。
In the end, it’s about all the closed proprietary model APIs, their guardrails are a little bit arbitrary, but also very difficult to enforce.
—— Simon Mo · [32:24]

指向原始笔记的链接

我经常在前沿方面遇到模型,它们不让我做我想做的事情,因为我很多时候试图做新奇的事情,我到处都撞到护栏。
I run into models all the time on the frontier side that won’t let me do things I want to do because I’m trying to do novel things a lot of the time and I hit guardrails all over the place.
—— Chris Benson · [48:22]

指向原始笔记的链接

我认为人们已经了解到,无论 AI 实验室在这些东西周围设置了什么护栏,你都不能依赖模型来阻止自己或理解上下文。
And I think what people have learned is that regardless of guardrails that the AI labs are putting around these things, you can’t rely on models to stop themselves or to understand context.
—— Nick Warner · [07:16]

指向原始笔记的链接

但是如果只是让你的循环构建所有东西,而在爆炸半径周围没有任何护栏,在关于你如何看待质量的周围没有任何护栏,我认为这是灾难的配方。
But simply just having your loops build everything without having some guardrails around the blast radius, without having guardrails around how you think about quality, I think is a recipe for disaster.
—— Addy Osmani · [66:33]

指向原始笔记的链接

你给一个 LLM 一个目标,它会在护栏之内竭尽所能去解决那个目标。
You give an LLM a goal, it will do everything it can within guardrails to solve that goal.
—— 嘉宾 · [19:26]

指向原始笔记的链接

但是这里的教训,这是元层面的教训,护栏是不够的。
But the learning, here’s the meta learning, guardrails aren’t enough.
—— 嘉宾 · [29:30]

指向原始笔记的链接

② 出现在这些集

46 集

③ 关联

点进去有真内容 —— 本页主要出口

智能体 · OpenAI · Anthropic · 沙箱 · Hugging Face · 推理 · MCP · Codex · Cursor · Claude