The correct inference model for AI systems should not be autoregressive token generation but rather optimization over an energy function that measures compatibility between observations and proposed outputs, allowing systems to spend more computation on harder problems (system two thinking) rather than spending identical computation on simple yes-or-no questions and complex questions.
normativepending
Speaker
Yann LeCunEvidence Quote
“the way um a lot of inference in statistics for example that's going to make Mike happy actually um the way inference works is is not that way in uh In classical AI in statistics uh in structure prediction a lot of different domains the way it works is that you have a function that measures the degree of compatibility or incompatibility between your observation and a proposed output and then the inference process consist in finding the value of an output that minimizes this incompatibility measure okay let's call it an energy function”
Created: 8/11/2026, 7:11:43 AM
Your notes
Loading notes...