① 他说过的话

13 条

每个月都有故事说某个智能体删了点东西，导致别人丢了生产数据库。
Every month there’s a story where someone lost their production database because the agent deleted something.
—— Andy Pavlo · [00:03]

指向原始笔记的链接

但是比如说护城河，如果你愿意这么叫的话，并没有那么大，因为归根结底，它只是一个索引。
But like the moat, if you will, wasn’t that big because at the end of the day, it’s just an index.
—— Andy Pavlo · [03:31]

指向原始笔记的链接

而在一年之内，几乎每一个数据库厂商都有了他们自己的向量索引。现在这已经变成了某种意义上的标准入场筹码。
And within a year, pretty much every single database vendor had their own vector index. And now it’s become sort of standard table stakes.
—— Andy Pavlo · [03:35]

指向原始笔记的链接

多年来，我们一直有能力确保人们不做不该做的事，比如那些蠢事，像删掉一张表或者删除记录。这些控制手段是存在的，只是每个人都想重新发明轮子，然后人们就吃了苦头，才学会去做那些过去早就做过的事。
For years, we’ve had the capabilities to make sure people don’t do things they shouldn’t be doing, like stupid things like dropping a table or deleting records. Those controls exist, it’s just everyone wants to re-event the wheel and people learn the hard way of just doing what’s already been done in the past.
—— Andy Pavlo · [08:03]

指向原始笔记的链接

人们会偷懒，整个公司、整个组织用同一个密码，然后又把同一个密码给了智能体，之后还纳闷为什么智能体开始做不该做的事。
People get lazy, they use the same password across entire company, organization, and then they give the same password to the agent and now wonder why the agent started doing things they shouldn’t do.
—— Andy Pavlo · [09:31]

指向原始笔记的链接

所以我认为将会潜在地有 10 到 100 倍的流量增长，体现在将冲击数据库的查询数量上。
So I think there’s going to be potentially a 10 to 100x increase in volume in the number of queries that are going to hit up against databases.
—— Andy Pavlo · [13:51]

指向原始笔记的链接

所以说到底，每个人都应该把所有东西放进数据库系统里。
So at the end of the day, everybody should be putting everything in a database system.
—— Andy Pavlo · [16:47]

指向原始笔记的链接

我要说的是，我不能说是谁，有两家数据库公司问过我，怎么让智能体在推荐时优先推荐他们的数据库而不是 Postgres。
And I will say, I can’t say who, I’ve had two database companies ask me how to get their database to be recommended first by an agent over Postgres.
—— Andy Pavlo · [18:58]

指向原始笔记的链接

这基本上就像 SEO。怎么让智能体学会，嘿，我应该用我的数据库 X 而不是 Postgres。
It’s basically like SEO. How do you get the agent to learn like, hey, I should use my database X instead of Postgres.
—— Andy Pavlo · [19:20]

指向原始笔记的链接

我还没见过任何基准测试表明图数据库——原生图数据库——能在那些关系型数据库系统拥有正确的 SQL 或 API 构造、从而让你完全在服务器端做图遍历、不用来回往返的情况下，胜过关系型数据库系统。
I have not seen any benchmarks that show graph databases, the native graph databases, outperform the relational databases systems when those related systems have the right constructs in SQL or the API so that you can do graph traversal all on the server side and not go back and forth.
—— Andy Pavlo · [22:23]

指向原始笔记的链接

是的，数据库系统领域有句老话：需要十年，但它是一个系统。你可以在三年里构建出前 90%，然后剩下的 10% 要花接下来七年。
Yeah, the old adage from database systems is that it takes 10 years, but it’s a system. You can build the first 90% in three years and then the remaining 10% takes the next seven years.
—— Andy Pavlo · [29:34]

指向原始笔记的链接

我们的模型通常需要训练好几个小时——前提是你有足够的训练数据——才能产生最完美的最优配置，但 LLM 只要 15 分钟就能进来，产出一个足够好的东西，而对大多数人来说这就够了。
Our models oftentimes would take hours and hours to train, assuming you had enough training data, to produce the pristine optimal configuration, but the elements can come in just like in 15 minutes, produce something that was good enough, and that’s good enough for most people.
—— Andy Pavlo · [34:31]

指向原始笔记的链接

超过 60% 的开源数据库系统的提交来自智能体。
Over 60% of the open source database systems have commits coming from agents.
—— Andy Pavlo · [30:37]

指向原始笔记的链接

② 出现在这些集

1 集

• 《当几十亿个AI智能体冲向你的数据库》 — 作为主持

③ 他谈到的

点进去有真内容 —— 本页主要出口

Matt Turk · 智能体 · 护栏 · 沙箱 · 分支 · 向量数据库 · 向量搜索 · RAG · text to SQL · 语义层

④ 也在聊「智能体」的人