forecast

Small architectural tweaks could close efficiency gap

Sample inefficiency in LLMs could be reduced by small architectural tweaks, like the residual connection that made deep networks learnable, and a few such changes could plausibly close several orders of magnitude, unlike a nativist story requiring large innate structure.

forecastpending

Speaker

Chandra Sripada

Evidence Quote

“A little tweak like that makes something unlearnable before, which is the limiting case of sample inefficiency, learnable.”

Source

363 | Chandra Sripada on How LLMs and Humans are Cognitive Cousins— Sean Carroll's Mindscape
Created: 11/17/2026, 6:53:48 AM

Your notes

Loading notes...