vector function
A mapping from one subset of vector space to another that performs a useful transformation; Chollet's term for the millions of 'programs' stored in an LLM.
As defined in 280 | François Chollet on Deep Learning and the Meaning of Intelligence
Where it comes up · 1
Most important claims · 3 of 3Search all claims for “vector function” →
- 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.280 | François Chollet on Deep Learning and the Meaning of Intelligence
- Word2vec illustrates semantically meaningful vector functions in miniature: words are points in vector space such that adding a consistent vector transforms words in a consistent way—king minus man plus woman equals queen—demonstrating that meaningful operations like pluralization or gender shift can be encoded as vector addition.280 | François Chollet on Deep Learning and the Meaning of Intelligence
- Because LLM transformations are vector programs, you can average or interpolate between them—asking it to talk like a pirate and like Shakespeare simultaneously yields a Shakespearean pirate—which is something you cannot do with an explicit logic program, giving the impression of creativity through interpolation within the convex hull of training representations.280 | François Chollet on Deep Learning and the Meaning of Intelligence