Classical inference in statistics, structure prediction, and classical AI uses a different paradigm than LLMs: these domains use an energy function that measures the degree of incompatibility between observations and proposed outputs, and inference consists of finding the output that minimizes this energy/incompatibility—this is more akin to human System 2 thinking (deliberate reasoning about actions before taking them) than LLM System 1 (automatic pattern matching without reasoning).
factualpending
Speaker
Yann LeCunEvidence Quote
“you have a function that measures the degree of compatibility or incompatibility...inference consist in finding the value of an output that minimizes this incompatibility”
Created: 8/11/2026, 1:17:36 AM
Your notes
Loading notes...