factual

LLMs interpolate while genetic algorithms find novel points

Large language models only interpolate between existing points in vector space, whereas genetic algorithms can discover entirely novel points; combining an LLM trained on human art with a genetic-algorithm randomizing component raises the question of whether the result could be called creative.

factualpending

Speaker

Sean Carroll

Evidence Quote

“In EP 280, François Chollet pointed out that LLMs only interpolate between points in vector space.”

Source

Ask Me Anything | July 2024— Sean Carroll's Mindscape
Created: 6/13/2026, 12:13:22 AM

Your notes

Loading notes...