new preprint: how does curriculum learning affect representation formation in transformers, and why does it matter for AI safety? with Sebi Bruijns, Mia Whitefield, @RubruckJirko@akaijsa and @FazlBarez .
https://t.co/OJ8U2UXnmI
New in @NatureNeuro: We developed a flexible model that reveals how animals learn tasks—uncovering stages, sudden insights, and gradual improvements unique to each animal.
Learning isn't monotonic, and our model captures that complexity 🐭📊
https://t.co/bLtIsmbw8F