6 articles
A two-year-old builds a spatial map of a playground in minutes. A deep RL robot navigating a virtual maze independently grew the same hexagonal grid-cell structure evolution put in the hippocampus. The convergence isn't coincidence — it's math.
Raf Delgado·
A five-year-old adjusting the wrong wheel on a cardboard car for twenty minutes, a toddler reaching for a moved toy in the wrong spot, an AI model locked onto its training distribution — they all share the same problem. Here's what genuine cognitive flexibility actually requires, and why it's one of the hardest things any mind can do.
Raf Delgado·
Babies keep time before they can walk. AI generates music by counting tokens. The gap between these two things reveals something fundamental about what rhythm actually is — and why closing it matters.
Raf Delgado·
Transformers compute attention over millions of tokens simultaneously. Children pay attention through their bodies, their predictions, their mistakes. The gap between the two reveals something deep about what attention actually is — and why embodied AI keeps failing in kitchens.
Raf Delgado·
During sleep, your hippocampus runs a selective replay of the day's experiences to wire memories into your neocortex. AI has a pale imitation. Here's how far apart the two actually are.
Theo Kask·
Children have a supercharged window for learning motor skills, language, and movement. Deep neural networks face a strikingly similar problem — and the solutions emerging from neuroscience might hold the key.
Raf Delgado·
Neupiphany