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 CholletEvidence 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 MindscapeCreated: 6/13/2026, 12:07:39 AM
Your notes
Loading notes...