News for hackers. Stuff that matters.
Re:Chomsky and the Two Cultures of Statistical Learning by lostmsu on Saturday November 07, 2026 @02:15PM (#50407155)
[delayed]
Re:Chomsky and the Two Cultures of Statistical Learning by suddenlybananas on Sunday November 08, 2026 @06:55AM (#50412488)
https://aclanthology.org/2025.babylm-main.28/

The multimodal baselines are _lower_ than the text only baselines. See Table 3. In fact, 10M of text outperforms 100M of text + images.