definition

LLMs Are Compressed Stores of Vector Programs

Through training on massive data in high-dimensional space, LLMs build a smooth differentiable manifold that, due to compression pressure, encodes millions of reusable semantic 'programs'—vector functions mapping subsets of vector space to others—so the best way to think of an LLM is as a vast interpolative database of programs rather than a reasoning system.

definitionpending

Speaker

François Chollet

Evidence Quote

“the most effective way of thinking about LLMs is that they are big stores of programs, millions of programs... they are more like vector functions”

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...