跨国深谈← 返回←Simon Boudrien

① 他说过的话

3 条

但随后我们通过时间看到的是，用户越多，改变他们就越困难。
Uh but then what we saw through time is the more user we’ve had, the harder it became to go and like change them.
—— Simon Boudrien · [35:33]

指向原始笔记的链接

对我们来说发生的事情实际上是，一旦我们删除了整个上下文，eval 开始表现得更好，这是反直觉的，但就是这样，是的，那个文件很大，列出的东西不一定有用，或者不应该进入指导文件。
And what happened for us is actually like the eval started to perform like much better once we deleted the whole context, which was counter uh intuitive, but it’s just like, yeah, that file was pretty big and was listing stuff that was not like necessarily useful or you know, that should not go into like a steering document.
—— Simon Boudrien · [38:11]

指向原始笔记的链接

基于我们的 eval，我认为开放权重模型要做到完全可行，假设基准线不随着该领域的进步而移动，它们需要表现得比今天好大约 50%。
Yeah so so yeah based on our evals I think open weight model to be like fully viable assuming the bar does not move as progress happened in the space would be that they would need to perform about 50% better than they are today.
—— Simon Boudrien · [47:51]

指向原始笔记的链接

② 出现在这些集

1 集

• 《Datadog 4000 人AI赋能实战：删掉上下文反而更好》 — 作为联合主持

③ 他谈到的

点进去有真内容 —— 本页主要出口

Simon Maple · Guy for Germany · Datadog · 智能体 · 评估 · 上下文 · Cursor · 开源权重模型 · 代码审查 · Pi

④ 也在聊「AI 编程」的人