definition

LLMs Map Tokens to Distances in Vector Space

The core idea of deep learning and LLMs is that relationships between things can be represented as literal distances in a vector space; tokens are mapped to points whose geometric proximity encodes semantic similarity, similar in spirit to Hebbian learning where neurons that fire together wire together.

definitionpending

Speaker

François Chollet

Evidence Quote

“the idea is that you're gonna map your things, so your tokens for instance, into some vector space... you're gonna try to organize these points so that the distance between points represents how semantically similar they are.”

Source

280 | François Chollet on Deep Learning and the Meaning of Intelligence— Sean Carroll's Mindscape
Created: 6/13/2026, 12:07:39 AM

Your notes

Loading notes...