ATRIUMsearch → argument graph
DataVideo · 71:50 — 73:20

把ARC-AGI-3游戏的颜色进行置换、并旋转图像,会让这些游戏对人类和算法来说都明显变难,这说明该基准测试本应剔除的人类特有先验(比如颜色/方向惯例)其实渗透进了测试之中。

D Smith揭示了一项实验:把游戏图像的颜色打乱并旋转后,ARC-AGI-3的关卡对人类来说也会变得难得多,这暴露出这个本应只衡量纯粹智能的基准测试中,其实隐藏地渗入了人类的惯例。 ✦ AI 生成 · 平台预翻

D Smith · Machine Learning Street Talk · 2026-07-01 · English original →

所以呢,你可以做的一件事就是很轻松地对游戏做置换。你可以把颜色打乱,还可以旋转一下,呃,图像,这样做了之后,游戏会明显变难。所以说,一旦你去掉那个本不应该算作先验的先验,你其实能看到,人类玩起来也会变难。所以,是的,这也许说明了关于这个基准测试的一些问题。
So if you so one thing you could do you could easily permute the game. So you can permute the colors and also rotate the um images and when you do that the games become significantly harder. So if you just remove that prior which shouldn't actually be prior you can actually see it becomes harder for humans to play. So yes, perhaps that tells something about the benchmark.

回到原声 ↗逐字转录 · 起于 71:50 · 中文为平台译文